Programming Assignment 3 YOLOv5 Object Detection
Aaron Christopher Tanhar
• 49 min read
- Deskripsi
- Custom Training with YOLOv5
- Step 1: Install Requirements
- Step 2: Assemble Our Dataset
- Annotate
- Version
- Export
- Download Code
- Step 3: Train Our Custom YOLOv5 model
- Evaluate Custom YOLOv5 Detector Performance
- Run Inference With Trained Weights
- Conclusion and Next Steps
Deskripsi
Saya mengambil dataset dari kaggle
Dataset tersebut memiliki gambar cheetah dan hyena. Saya mengambil 900 gambar cheetah dan 900 gambar hyena sehingga total gambar adalah 1800. Kemudian saya menganotasi gambar-gambar tersebut dengan menggunakan roboflow.
Kemudian sesuai langkah-langkah saya menggenerate datasetnya.
Lalu saya menggunakan notebook yang di generate dari wiki
Lalu saya membuat akun Weights and Biases untuk melakukan Weights and Biases Logging.
Selanjutnya kita train dan menyesuaikan epoch. Saya menggunakan epoch sebanyak 150. Sebenarnya sudah mencoba 200 epoch tapi terlalu lama sehingga tidak jadi.
Setelah di train maka kita akan melakukan tes pada weight terbaik yang sudah digenerate setelah training.
Jumlah gambar yang digunakan untuk test adalah 10% dari 1800 yaitu 180. Gambar deteksi ditampilkan dengan bounding box dan confidence. Setelah itu weight disimpan.
Custom Training with YOLOv5
In this tutorial, we assemble a dataset and train a custom YOLOv5 model to recognize the objects in our dataset. To do so we will take the following steps:
- Gather a dataset of images and label our dataset
- Export our dataset to YOLOv5
- Train YOLOv5 to recognize the objects in our dataset
- Evaluate our YOLOv5 model's performance
- Run test inference to view our model at work
!git clone https://github.com/ultralytics/yolov5 # clone repo
%cd yolov5
%pip install -qr requirements.txt # install dependencies
%pip install -q roboflow
import torch
import os
from IPython.display import Image, clear_output # to display images
print(f"Setup complete. Using torch {torch.__version__} ({torch.cuda.get_device_properties(0).name if torch.cuda.is_available() else 'CPU'})")
Cloning into 'yolov5'...
remote: Enumerating objects: 10222, done.
remote: Total 10222 (delta 0), reused 0 (delta 0), pack-reused 10222
Receiving objects: 100% (10222/10222), 10.54 MiB | 24.14 MiB/s, done.
Resolving deltas: 100% (7060/7060), done.
/content/yolov5
|████████████████████████████████| 596 kB 11.5 MB/s
|████████████████████████████████| 145 kB 13.2 MB/s
|████████████████████████████████| 178 kB 42.6 MB/s
|████████████████████████████████| 1.1 MB 17.6 MB/s
|████████████████████████████████| 67 kB 5.1 MB/s
|████████████████████████████████| 138 kB 49.9 MB/s
|████████████████████████████████| 62 kB 755 kB/s
Building wheel for roboflow (setup.py) ... done
Building wheel for wget (setup.py) ... done
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
google-colab 1.0.0 requires requests~=2.23.0, but you have requests 2.26.0 which is incompatible.
datascience 0.10.6 requires folium==0.2.1, but you have folium 0.8.3 which is incompatible.
albumentations 0.1.12 requires imgaug<0.2.7,>=0.2.5, but you have imgaug 0.2.9 which is incompatible.
Setup complete. Using torch 1.10.0+cu111 (Tesla K80)
Step 2: Assemble Our Dataset
In order to train our custom model, we need to assemble a dataset of representative images with bounding box annotations around the objects that we want to detect. And we need our dataset to be in YOLOv5 format.
In Roboflow, you can choose between two paths:
- Convert an existing dataset to YOLOv5 format. Roboflow supports over 30 formats object detection formats for conversion.
- Upload raw images and annotate them in Roboflow with Roboflow Annotate.
Annotate
Version
Export
Download Code
from roboflow import Roboflow
rf = Roboflow(model_format="yolov5", notebook="ultralytics")
upload and label your dataset, and get an API KEY here: https://app.roboflow.com/?model=yolov5&ref=ultralytics
os.environ["DATASET_DIRECTORY"] = "/content/datasets"
from getpass import getpass
rf = Roboflow(api_key=getpass('Enter the api key: '))
project = rf.workspace().project("visikom_pa03")
dataset = project.version(1).download("yolov5")
Enter the api key: ·········· loading Roboflow workspace... loading Roboflow project... Downloading Dataset Version Zip in /content/datasets/Visikom_PA03-1 to yolov5pytorch: 100% [58871666 / 58871666] bytes
Extracting Dataset Version Zip to /content/datasets/Visikom_PA03-1 in yolov5pytorch:: 100%|██████████| 3612/3612 [00:04<00:00, 884.26it/s]
Step 3: Train Our Custom YOLOv5 model
Here, we are able to pass a number of arguments:
- img: define input image size
- batch: determine batch size
- epochs: define the number of training epochs. (Note: often, 3000+ are common here!)
-
data: Our dataset locaiton is saved in the
dataset.location - weights: specify a path to weights to start transfer learning from. Here we choose the generic COCO pretrained checkpoint.
- cache: cache images for faster training
%pip install wandb
!python train.py --img 416 --batch 16 --epochs 150 --data {dataset.location}/data.yaml --weights yolov5s.pt --cache
Collecting wandb
Downloading wandb-0.12.7-py2.py3-none-any.whl (1.7 MB)
|████████████████████████████████| 1.7 MB 10.8 MB/s
Collecting docker-pycreds>=0.4.0
Downloading docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)
Collecting configparser>=3.8.1
Downloading configparser-5.2.0-py3-none-any.whl (19 kB)
Requirement already satisfied: requests<3,>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from wandb) (2.26.0)
Collecting GitPython>=1.0.0
Downloading GitPython-3.1.24-py3-none-any.whl (180 kB)
|████████████████████████████████| 180 kB 35.7 MB/s
Requirement already satisfied: PyYAML in /usr/local/lib/python3.7/dist-packages (from wandb) (6.0)
Requirement already satisfied: six>=1.13.0 in /usr/local/lib/python3.7/dist-packages (from wandb) (1.15.0)
Collecting sentry-sdk>=1.0.0
Downloading sentry_sdk-1.5.1-py2.py3-none-any.whl (140 kB)
|████████████████████████████████| 140 kB 52.1 MB/s
Requirement already satisfied: python-dateutil>=2.6.1 in /usr/local/lib/python3.7/dist-packages (from wandb) (2.8.2)
Collecting subprocess32>=3.5.3
Downloading subprocess32-3.5.4.tar.gz (97 kB)
|████████████████████████████████| 97 kB 7.5 MB/s
Requirement already satisfied: protobuf>=3.12.0 in /usr/local/lib/python3.7/dist-packages (from wandb) (3.17.3)
Requirement already satisfied: promise<3,>=2.0 in /usr/local/lib/python3.7/dist-packages (from wandb) (2.3)
Collecting pathtools
Downloading pathtools-0.1.2.tar.gz (11 kB)
Collecting shortuuid>=0.5.0
Downloading shortuuid-1.0.8-py3-none-any.whl (9.5 kB)
Requirement already satisfied: Click!=8.0.0,>=7.0 in /usr/local/lib/python3.7/dist-packages (from wandb) (7.1.2)
Requirement already satisfied: psutil>=5.0.0 in /usr/local/lib/python3.7/dist-packages (from wandb) (5.4.8)
Collecting yaspin>=1.0.0
Downloading yaspin-2.1.0-py3-none-any.whl (18 kB)
Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.7/dist-packages (from GitPython>=1.0.0->wandb) (3.10.0.2)
Collecting gitdb<5,>=4.0.1
Downloading gitdb-4.0.9-py3-none-any.whl (63 kB)
|████████████████████████████████| 63 kB 1.8 MB/s
Collecting smmap<6,>=3.0.1
Downloading smmap-5.0.0-py3-none-any.whl (24 kB)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.0.0->wandb) (2021.5.30)
Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.0.0->wandb) (2.0.8)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.0.0->wandb) (2.10)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.0.0->wandb) (1.26.6)
Requirement already satisfied: termcolor<2.0.0,>=1.1.0 in /usr/local/lib/python3.7/dist-packages (from yaspin>=1.0.0->wandb) (1.1.0)
Building wheels for collected packages: subprocess32, pathtools
Building wheel for subprocess32 (setup.py) ... done
Created wheel for subprocess32: filename=subprocess32-3.5.4-py3-none-any.whl size=6502 sha256=c4f0c8bbf3ee692fdadc4cdfb644bc95bde858c614a6f9e1aee842b26790c532
Stored in directory: /root/.cache/pip/wheels/50/ca/fa/8fca8d246e64f19488d07567547ddec8eb084e8c0d7a59226a
Building wheel for pathtools (setup.py) ... done
Created wheel for pathtools: filename=pathtools-0.1.2-py3-none-any.whl size=8807 sha256=3b1c5ca3314ab3744af7220119e9ee81f68fac4c126ef6e8344ad5b8b65d7c59
Stored in directory: /root/.cache/pip/wheels/3e/31/09/fa59cef12cdcfecc627b3d24273699f390e71828921b2cbba2
Successfully built subprocess32 pathtools
Installing collected packages: smmap, gitdb, yaspin, subprocess32, shortuuid, sentry-sdk, pathtools, GitPython, docker-pycreds, configparser, wandb
Successfully installed GitPython-3.1.24 configparser-5.2.0 docker-pycreds-0.4.0 gitdb-4.0.9 pathtools-0.1.2 sentry-sdk-1.5.1 shortuuid-1.0.8 smmap-5.0.0 subprocess32-3.5.4 wandb-0.12.7 yaspin-2.1.0
wandb: (1) Create a W&B account
wandb: (2) Use an existing W&B account
wandb: (3) Don't visualize my results
wandb: Enter your choice: (30 second timeout) 2
wandb: You chose 'Use an existing W&B account'
wandb: You can find your API key in your browser here: https://wandb.ai/authorize
wandb: Paste an API key from your profile and hit enter, or press ctrl+c to quit:
wandb: Appending key for api.wandb.ai to your netrc file: /root/.netrc
train: weights=yolov5s.pt, cfg=, data=/content/datasets/Visikom_PA03-1/data.yaml, hyp=data/hyps/hyp.scratch.yaml, epochs=150, batch_size=16, imgsz=416, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, patience=100, freeze=0, save_period=-1, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest
github: up to date with https://github.com/ultralytics/yolov5 ✅
YOLOv5 🚀 v6.0-147-g628817d torch 1.10.0+cu111 CUDA:0 (Tesla K80, 11441MiB)
hyperparameters: lr0=0.01, lrf=0.1, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0
TensorBoard: Start with 'tensorboard --logdir runs/train', view at http://localhost:6006/
wandb: Currently logged in as: lordronz (use `wandb login --relogin` to force relogin)
wandb: Tracking run with wandb version 0.12.7
wandb: Syncing run major-shadow-1
wandb: ⭐️ View project at https://wandb.ai/lordronz/YOLOv5
wandb: 🚀 View run at https://wandb.ai/lordronz/YOLOv5/runs/3j8heu3j
wandb: Run data is saved locally in /content/yolov5/wandb/run-20211216_101614-3j8heu3j
wandb: Run `wandb offline` to turn off syncing.
Overriding model.yaml nc=80 with nc=2
from n params module arguments
0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2]
1 -1 1 18560 models.common.Conv [32, 64, 3, 2]
2 -1 1 18816 models.common.C3 [64, 64, 1]
3 -1 1 73984 models.common.Conv [64, 128, 3, 2]
4 -1 2 115712 models.common.C3 [128, 128, 2]
5 -1 1 295424 models.common.Conv [128, 256, 3, 2]
6 -1 3 625152 models.common.C3 [256, 256, 3]
7 -1 1 1180672 models.common.Conv [256, 512, 3, 2]
8 -1 1 1182720 models.common.C3 [512, 512, 1]
9 -1 1 656896 models.common.SPPF [512, 512, 5]
10 -1 1 131584 models.common.Conv [512, 256, 1, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 models.common.Concat [1]
13 -1 1 361984 models.common.C3 [512, 256, 1, False]
14 -1 1 33024 models.common.Conv [256, 128, 1, 1]
15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
16 [-1, 4] 1 0 models.common.Concat [1]
17 -1 1 90880 models.common.C3 [256, 128, 1, False]
18 -1 1 147712 models.common.Conv [128, 128, 3, 2]
19 [-1, 14] 1 0 models.common.Concat [1]
20 -1 1 296448 models.common.C3 [256, 256, 1, False]
21 -1 1 590336 models.common.Conv [256, 256, 3, 2]
22 [-1, 10] 1 0 models.common.Concat [1]
23 -1 1 1182720 models.common.C3 [512, 512, 1, False]
24 [17, 20, 23] 1 18879 models.yolo.Detect [2, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
Model Summary: 270 layers, 7025023 parameters, 7025023 gradients, 15.9 GFLOPs
Transferred 343/349 items from yolov5s.pt
Scaled weight_decay = 0.0005
optimizer: SGD with parameter groups 57 weight, 60 weight (no decay), 60 bias
albumentations: version 1.0.3 required by YOLOv5, but version 0.1.12 is currently installed
train: Scanning '/content/datasets/Visikom_PA03-1/train/labels' images and labels...1260 found, 0 missing, 1 empty, 0 corrupted: 100% 1260/1260 [00:00<00:00, 1438.57it/s]
train: New cache created: /content/datasets/Visikom_PA03-1/train/labels.cache
train: Caching images (0.7GB ram): 100% 1260/1260 [00:03<00:00, 343.51it/s]
val: Scanning '/content/datasets/Visikom_PA03-1/valid/labels' images and labels...360 found, 0 missing, 1 empty, 0 corrupted: 100% 360/360 [00:00<00:00, 627.37it/s]
val: New cache created: /content/datasets/Visikom_PA03-1/valid/labels.cache
val: Caching images (0.2GB ram): 100% 360/360 [00:01<00:00, 343.65it/s]
Plotting labels to runs/train/exp3/labels.jpg...
AutoAnchor: 2.82 anchors/target, 1.000 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅
Image sizes 416 train, 416 val
Using 2 dataloader workers
Logging results to runs/train/exp3
Starting training for 150 epochs...
Epoch gpu_mem box obj cls labels img_size
0/149 1.41G 0.08737 0.02249 0.0261 26 416: 100% 79/79 [00:47<00:00, 1.67it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:05<00:00, 2.15it/s]
all 360 359 0.297 0.47 0.321 0.137
Epoch gpu_mem box obj cls labels img_size
1/149 1.62G 0.05617 0.02208 0.02268 31 416: 100% 79/79 [00:44<00:00, 1.77it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.42it/s]
all 360 359 0.592 0.721 0.69 0.408
Epoch gpu_mem box obj cls labels img_size
2/149 1.62G 0.04776 0.01867 0.02015 32 416: 100% 79/79 [00:43<00:00, 1.80it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.68it/s]
all 360 359 0.679 0.766 0.782 0.432
Epoch gpu_mem box obj cls labels img_size
3/149 1.62G 0.04634 0.01718 0.01396 32 416: 100% 79/79 [00:43<00:00, 1.81it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.69it/s]
all 360 359 0.81 0.844 0.871 0.493
Epoch gpu_mem box obj cls labels img_size
4/149 1.62G 0.04274 0.0172 0.01237 40 416: 100% 79/79 [00:43<00:00, 1.81it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.916 0.91 0.963 0.554
Epoch gpu_mem box obj cls labels img_size
5/149 1.62G 0.04086 0.01659 0.0101 31 416: 100% 79/79 [00:43<00:00, 1.81it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.888 0.892 0.957 0.576
Epoch gpu_mem box obj cls labels img_size
6/149 1.62G 0.04176 0.01572 0.01166 23 416: 100% 79/79 [00:43<00:00, 1.82it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.865 0.914 0.909 0.45
Epoch gpu_mem box obj cls labels img_size
7/149 1.62G 0.03997 0.01577 0.009407 33 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.855 0.936 0.93 0.598
Epoch gpu_mem box obj cls labels img_size
8/149 1.62G 0.03879 0.01694 0.01275 40 416: 100% 79/79 [00:43<00:00, 1.82it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.68it/s]
all 360 359 0.886 0.819 0.878 0.456
Epoch gpu_mem box obj cls labels img_size
9/149 1.62G 0.03835 0.01663 0.01203 38 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.75 0.697 0.778 0.385
Epoch gpu_mem box obj cls labels img_size
10/149 1.62G 0.03959 0.0167 0.01182 33 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.935 0.927 0.955 0.466
Epoch gpu_mem box obj cls labels img_size
11/149 1.62G 0.03981 0.01662 0.0118 24 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.874 0.888 0.938 0.552
Epoch gpu_mem box obj cls labels img_size
12/149 1.62G 0.03883 0.01742 0.01256 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.555 0.611 0.571 0.223
Epoch gpu_mem box obj cls labels img_size
13/149 1.62G 0.04124 0.01666 0.0117 34 416: 100% 79/79 [00:43<00:00, 1.82it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.70it/s]
all 360 359 0.807 0.694 0.772 0.363
Epoch gpu_mem box obj cls labels img_size
14/149 1.62G 0.03613 0.01686 0.01048 33 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:05<00:00, 2.11it/s]
all 360 359 0.819 0.835 0.862 0.468
Epoch gpu_mem box obj cls labels img_size
15/149 1.62G 0.0365 0.01643 0.01068 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.9 0.862 0.897 0.537
Epoch gpu_mem box obj cls labels img_size
16/149 1.62G 0.03537 0.01616 0.01032 28 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.857 0.891 0.89 0.539
Epoch gpu_mem box obj cls labels img_size
17/149 1.62G 0.03485 0.01661 0.01113 39 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.841 0.835 0.861 0.498
Epoch gpu_mem box obj cls labels img_size
18/149 1.62G 0.03384 0.01621 0.009891 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.861 0.89 0.928 0.504
Epoch gpu_mem box obj cls labels img_size
19/149 1.62G 0.03192 0.01615 0.008882 35 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.931 0.911 0.948 0.523
Epoch gpu_mem box obj cls labels img_size
20/149 1.62G 0.03336 0.01566 0.01012 30 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.917 0.936 0.964 0.585
Epoch gpu_mem box obj cls labels img_size
21/149 1.62G 0.03161 0.01565 0.009046 30 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.70it/s]
all 360 359 0.758 0.713 0.79 0.422
Epoch gpu_mem box obj cls labels img_size
22/149 1.62G 0.03118 0.01556 0.008691 33 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.937 0.908 0.949 0.605
Epoch gpu_mem box obj cls labels img_size
23/149 1.62G 0.03208 0.01551 0.01003 36 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.924 0.916 0.949 0.596
Epoch gpu_mem box obj cls labels img_size
24/149 1.62G 0.03189 0.01551 0.009232 28 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.944 0.913 0.96 0.604
Epoch gpu_mem box obj cls labels img_size
25/149 1.62G 0.03094 0.01566 0.009471 34 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.92 0.935 0.947 0.593
Epoch gpu_mem box obj cls labels img_size
26/149 1.62G 0.03172 0.01525 0.009872 28 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.931 0.941 0.964 0.613
Epoch gpu_mem box obj cls labels img_size
27/149 1.62G 0.03058 0.01543 0.008616 30 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.954 0.936 0.968 0.644
Epoch gpu_mem box obj cls labels img_size
28/149 1.62G 0.03095 0.01539 0.007603 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.969 0.955 0.977 0.65
Epoch gpu_mem box obj cls labels img_size
29/149 1.62G 0.03067 0.01533 0.008276 22 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:05<00:00, 2.12it/s]
all 360 359 0.955 0.947 0.965 0.63
Epoch gpu_mem box obj cls labels img_size
30/149 1.62G 0.02861 0.01475 0.007799 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.955 0.906 0.965 0.596
Epoch gpu_mem box obj cls labels img_size
31/149 1.62G 0.02922 0.01482 0.008749 29 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.983 0.95 0.978 0.638
Epoch gpu_mem box obj cls labels img_size
32/149 1.62G 0.03008 0.01488 0.007603 35 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.917 0.903 0.944 0.582
Epoch gpu_mem box obj cls labels img_size
33/149 1.62G 0.02989 0.01488 0.007921 28 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.959 0.93 0.971 0.637
Epoch gpu_mem box obj cls labels img_size
34/149 1.62G 0.02913 0.01509 0.008465 33 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.96 0.947 0.974 0.612
Epoch gpu_mem box obj cls labels img_size
35/149 1.62G 0.02787 0.01509 0.008867 33 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.919 0.939 0.965 0.607
Epoch gpu_mem box obj cls labels img_size
36/149 1.62G 0.02961 0.01515 0.008456 35 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.927 0.933 0.964 0.551
Epoch gpu_mem box obj cls labels img_size
37/149 1.62G 0.02832 0.015 0.007445 28 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.923 0.914 0.942 0.593
Epoch gpu_mem box obj cls labels img_size
38/149 1.62G 0.02999 0.01549 0.008603 29 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.936 0.955 0.97 0.637
Epoch gpu_mem box obj cls labels img_size
39/149 1.62G 0.02762 0.0148 0.008099 40 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.954 0.94 0.966 0.659
Epoch gpu_mem box obj cls labels img_size
40/149 1.62G 0.02832 0.01501 0.008204 32 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.936 0.939 0.964 0.636
Epoch gpu_mem box obj cls labels img_size
41/149 1.62G 0.0294 0.01469 0.00668 33 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.955 0.955 0.969 0.654
Epoch gpu_mem box obj cls labels img_size
42/149 1.62G 0.02852 0.01446 0.006934 29 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.952 0.969 0.982 0.66
Epoch gpu_mem box obj cls labels img_size
43/149 1.62G 0.0271 0.01424 0.007107 26 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.952 0.94 0.976 0.642
Epoch gpu_mem box obj cls labels img_size
44/149 1.62G 0.02691 0.01452 0.00832 27 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:05<00:00, 2.16it/s]
all 360 359 0.962 0.936 0.972 0.63
Epoch gpu_mem box obj cls labels img_size
45/149 1.62G 0.02767 0.01462 0.006796 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.971 0.948 0.978 0.644
Epoch gpu_mem box obj cls labels img_size
46/149 1.62G 0.02709 0.01452 0.008858 26 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.945 0.916 0.957 0.633
Epoch gpu_mem box obj cls labels img_size
47/149 1.62G 0.02769 0.01406 0.006499 33 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.963 0.964 0.969 0.646
Epoch gpu_mem box obj cls labels img_size
48/149 1.62G 0.0275 0.0142 0.006776 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.965 0.958 0.978 0.65
Epoch gpu_mem box obj cls labels img_size
49/149 1.62G 0.02855 0.01422 0.007241 28 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.945 0.93 0.951 0.632
Epoch gpu_mem box obj cls labels img_size
50/149 1.62G 0.0283 0.01424 0.006446 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.95 0.955 0.972 0.649
Epoch gpu_mem box obj cls labels img_size
51/149 1.62G 0.02732 0.01434 0.006851 38 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.988 0.964 0.982 0.673
Epoch gpu_mem box obj cls labels img_size
52/149 1.62G 0.02799 0.01462 0.006692 32 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.98 0.94 0.98 0.645
Epoch gpu_mem box obj cls labels img_size
53/149 1.62G 0.02623 0.01421 0.007056 32 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.76it/s]
all 360 359 0.971 0.964 0.981 0.675
Epoch gpu_mem box obj cls labels img_size
54/149 1.62G 0.0274 0.01434 0.00672 38 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.977 0.951 0.978 0.648
Epoch gpu_mem box obj cls labels img_size
55/149 1.62G 0.02657 0.01353 0.00648 23 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.955 0.959 0.976 0.668
Epoch gpu_mem box obj cls labels img_size
56/149 1.62G 0.02664 0.01416 0.006136 32 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.972 0.953 0.979 0.659
Epoch gpu_mem box obj cls labels img_size
57/149 1.62G 0.02602 0.01401 0.005861 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.974 0.942 0.98 0.628
Epoch gpu_mem box obj cls labels img_size
58/149 1.62G 0.02547 0.01386 0.00736 30 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.961 0.955 0.979 0.661
Epoch gpu_mem box obj cls labels img_size
59/149 1.62G 0.02651 0.01426 0.00724 37 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:05<00:00, 2.16it/s]
all 360 359 0.949 0.939 0.966 0.624
Epoch gpu_mem box obj cls labels img_size
60/149 1.62G 0.02794 0.01434 0.007534 32 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.963 0.958 0.977 0.675
Epoch gpu_mem box obj cls labels img_size
61/149 1.62G 0.02592 0.0143 0.007021 32 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.976 0.953 0.971 0.661
Epoch gpu_mem box obj cls labels img_size
62/149 1.62G 0.0263 0.01408 0.00603 38 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.70it/s]
all 360 359 0.964 0.957 0.982 0.642
Epoch gpu_mem box obj cls labels img_size
63/149 1.62G 0.02663 0.01429 0.007677 35 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.977 0.963 0.979 0.652
Epoch gpu_mem box obj cls labels img_size
64/149 1.62G 0.02621 0.01432 0.006186 37 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.978 0.961 0.986 0.651
Epoch gpu_mem box obj cls labels img_size
65/149 1.62G 0.02639 0.01381 0.006864 29 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.964 0.953 0.98 0.669
Epoch gpu_mem box obj cls labels img_size
66/149 1.62G 0.02621 0.01408 0.007122 35 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.982 0.98 0.989 0.674
Epoch gpu_mem box obj cls labels img_size
67/149 1.62G 0.02443 0.01354 0.005236 38 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.977 0.975 0.991 0.68
Epoch gpu_mem box obj cls labels img_size
68/149 1.62G 0.02483 0.01371 0.006186 38 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.70it/s]
all 360 359 0.954 0.978 0.984 0.653
Epoch gpu_mem box obj cls labels img_size
69/149 1.62G 0.02532 0.01371 0.007711 24 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.973 0.966 0.982 0.684
Epoch gpu_mem box obj cls labels img_size
70/149 1.62G 0.02365 0.01356 0.005834 38 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.974 0.954 0.979 0.683
Epoch gpu_mem box obj cls labels img_size
71/149 1.62G 0.02526 0.01392 0.005784 36 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.972 0.969 0.981 0.662
Epoch gpu_mem box obj cls labels img_size
72/149 1.62G 0.02485 0.01412 0.00564 35 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.956 0.964 0.974 0.649
Epoch gpu_mem box obj cls labels img_size
73/149 1.62G 0.02547 0.01392 0.005849 28 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.964 0.961 0.98 0.689
Epoch gpu_mem box obj cls labels img_size
74/149 1.62G 0.02515 0.01356 0.006771 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:05<00:00, 2.16it/s]
all 360 359 0.98 0.957 0.98 0.642
Epoch gpu_mem box obj cls labels img_size
75/149 1.62G 0.02445 0.01375 0.005435 24 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.982 0.972 0.984 0.677
Epoch gpu_mem box obj cls labels img_size
76/149 1.62G 0.02377 0.01359 0.004664 29 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.76it/s]
all 360 359 0.988 0.966 0.984 0.699
Epoch gpu_mem box obj cls labels img_size
77/149 1.62G 0.02474 0.01333 0.005772 27 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.98 0.964 0.983 0.682
Epoch gpu_mem box obj cls labels img_size
78/149 1.62G 0.02427 0.01311 0.005514 37 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.971 0.967 0.978 0.708
Epoch gpu_mem box obj cls labels img_size
79/149 1.62G 0.02485 0.01369 0.006131 32 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.988 0.966 0.984 0.701
Epoch gpu_mem box obj cls labels img_size
80/149 1.62G 0.02485 0.01319 0.005135 27 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.963 0.964 0.974 0.685
Epoch gpu_mem box obj cls labels img_size
81/149 1.62G 0.02408 0.01308 0.004953 36 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.987 0.975 0.987 0.682
Epoch gpu_mem box obj cls labels img_size
82/149 1.62G 0.02287 0.01283 0.004554 33 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.97 0.98 0.985 0.703
Epoch gpu_mem box obj cls labels img_size
83/149 1.62G 0.02359 0.01324 0.005014 33 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.70it/s]
all 360 359 0.977 0.97 0.98 0.702
Epoch gpu_mem box obj cls labels img_size
84/149 1.62G 0.02424 0.01314 0.005383 31 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.972 0.962 0.982 0.676
Epoch gpu_mem box obj cls labels img_size
85/149 1.62G 0.02454 0.01269 0.004688 32 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.974 0.955 0.979 0.67
Epoch gpu_mem box obj cls labels img_size
86/149 1.62G 0.02395 0.01342 0.005318 35 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.958 0.975 0.983 0.695
Epoch gpu_mem box obj cls labels img_size
87/149 1.62G 0.02324 0.01317 0.00584 26 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.977 0.975 0.984 0.681
Epoch gpu_mem box obj cls labels img_size
88/149 1.62G 0.02413 0.01323 0.005334 34 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.973 0.969 0.981 0.674
Epoch gpu_mem box obj cls labels img_size
89/149 1.62G 0.02446 0.01315 0.005705 29 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:05<00:00, 2.17it/s]
all 360 359 0.964 0.972 0.983 0.685
Epoch gpu_mem box obj cls labels img_size
90/149 1.62G 0.02435 0.01264 0.005066 26 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.96 0.961 0.977 0.7
Epoch gpu_mem box obj cls labels img_size
91/149 1.62G 0.02291 0.01307 0.004875 39 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.976 0.969 0.983 0.685
Epoch gpu_mem box obj cls labels img_size
92/149 1.62G 0.02444 0.01299 0.004825 36 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.985 0.975 0.989 0.688
Epoch gpu_mem box obj cls labels img_size
93/149 1.62G 0.0229 0.01318 0.005412 36 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.987 0.98 0.987 0.686
Epoch gpu_mem box obj cls labels img_size
94/149 1.62G 0.02302 0.01293 0.004801 34 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.977 0.975 0.986 0.669
Epoch gpu_mem box obj cls labels img_size
95/149 1.62G 0.02396 0.01332 0.004397 36 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.76it/s]
all 360 359 0.956 0.978 0.98 0.685
Epoch gpu_mem box obj cls labels img_size
96/149 1.62G 0.02245 0.01288 0.005069 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.975 0.971 0.977 0.676
Epoch gpu_mem box obj cls labels img_size
97/149 1.62G 0.0227 0.01285 0.004587 29 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.76it/s]
all 360 359 0.962 0.969 0.974 0.68
Epoch gpu_mem box obj cls labels img_size
98/149 1.62G 0.02241 0.01303 0.004517 29 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.965 0.972 0.98 0.686
Epoch gpu_mem box obj cls labels img_size
99/149 1.62G 0.0226 0.01285 0.005117 30 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.975 0.968 0.984 0.687
Epoch gpu_mem box obj cls labels img_size
100/149 1.62G 0.02183 0.01262 0.004957 29 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.69it/s]
all 360 359 0.968 0.964 0.98 0.674
Epoch gpu_mem box obj cls labels img_size
101/149 1.62G 0.02288 0.01249 0.004623 26 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.988 0.972 0.986 0.676
Epoch gpu_mem box obj cls labels img_size
102/149 1.62G 0.02409 0.01275 0.004394 25 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.988 0.972 0.986 0.703
Epoch gpu_mem box obj cls labels img_size
103/149 1.62G 0.02302 0.01257 0.004585 27 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.987 0.975 0.987 0.692
Epoch gpu_mem box obj cls labels img_size
104/149 1.62G 0.02252 0.01295 0.004913 30 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:05<00:00, 2.14it/s]
all 360 359 0.983 0.972 0.985 0.7
Epoch gpu_mem box obj cls labels img_size
105/149 1.62G 0.02144 0.01253 0.004735 34 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.98 0.983 0.986 0.698
Epoch gpu_mem box obj cls labels img_size
106/149 1.62G 0.02168 0.01258 0.00433 35 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.98 0.98 0.989 0.692
Epoch gpu_mem box obj cls labels img_size
107/149 1.62G 0.02218 0.01276 0.00444 41 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.989 0.978 0.988 0.703
Epoch gpu_mem box obj cls labels img_size
108/149 1.62G 0.02244 0.01288 0.00443 23 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.989 0.972 0.987 0.691
Epoch gpu_mem box obj cls labels img_size
109/149 1.62G 0.02176 0.01268 0.004351 39 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.997 0.972 0.988 0.702
Epoch gpu_mem box obj cls labels img_size
110/149 1.62G 0.02183 0.01269 0.004244 36 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.991 0.969 0.988 0.701
Epoch gpu_mem box obj cls labels img_size
111/149 1.62G 0.02146 0.01253 0.00348 28 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.994 0.975 0.988 0.695
Epoch gpu_mem box obj cls labels img_size
112/149 1.62G 0.02275 0.01286 0.004164 37 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.991 0.975 0.988 0.708
Epoch gpu_mem box obj cls labels img_size
113/149 1.62G 0.02076 0.01225 0.003907 29 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.991 0.966 0.989 0.707
Epoch gpu_mem box obj cls labels img_size
114/149 1.62G 0.02082 0.01268 0.004174 37 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.988 0.968 0.99 0.696
Epoch gpu_mem box obj cls labels img_size
115/149 1.62G 0.02191 0.01258 0.004781 35 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.984 0.972 0.988 0.698
Epoch gpu_mem box obj cls labels img_size
116/149 1.62G 0.02202 0.01268 0.004343 34 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.985 0.978 0.991 0.705
Epoch gpu_mem box obj cls labels img_size
117/149 1.62G 0.02202 0.01246 0.00401 34 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.958 0.982 0.98 0.702
Epoch gpu_mem box obj cls labels img_size
118/149 1.62G 0.02192 0.01251 0.00479 29 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.985 0.969 0.986 0.702
Epoch gpu_mem box obj cls labels img_size
119/149 1.62G 0.0219 0.01239 0.005176 33 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:05<00:00, 2.17it/s]
all 360 359 0.988 0.964 0.985 0.682
Epoch gpu_mem box obj cls labels img_size
120/149 1.62G 0.02184 0.01245 0.005212 30 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.991 0.975 0.987 0.698
Epoch gpu_mem box obj cls labels img_size
121/149 1.62G 0.02065 0.01269 0.003958 33 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.983 0.974 0.988 0.704
Epoch gpu_mem box obj cls labels img_size
122/149 1.62G 0.02057 0.01247 0.005235 31 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.70it/s]
all 360 359 0.985 0.978 0.989 0.695
Epoch gpu_mem box obj cls labels img_size
123/149 1.62G 0.02204 0.01298 0.004128 24 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.991 0.978 0.989 0.704
Epoch gpu_mem box obj cls labels img_size
124/149 1.62G 0.02168 0.01226 0.004521 23 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.994 0.972 0.987 0.705
Epoch gpu_mem box obj cls labels img_size
125/149 1.62G 0.02112 0.01225 0.004018 35 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.988 0.972 0.989 0.698
Epoch gpu_mem box obj cls labels img_size
126/149 1.62G 0.01991 0.0123 0.003286 36 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.985 0.965 0.988 0.701
Epoch gpu_mem box obj cls labels img_size
127/149 1.62G 0.02063 0.01242 0.003427 34 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.982 0.966 0.987 0.703
Epoch gpu_mem box obj cls labels img_size
128/149 1.62G 0.02077 0.01225 0.004466 31 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.974 0.962 0.98 0.69
Epoch gpu_mem box obj cls labels img_size
129/149 1.62G 0.02104 0.01258 0.004293 35 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.985 0.975 0.987 0.708
Epoch gpu_mem box obj cls labels img_size
130/149 1.62G 0.02099 0.0123 0.005538 35 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.982 0.966 0.985 0.692
Epoch gpu_mem box obj cls labels img_size
131/149 1.62G 0.0213 0.01252 0.003567 25 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.974 0.969 0.984 0.686
Epoch gpu_mem box obj cls labels img_size
132/149 1.62G 0.02114 0.01254 0.004359 35 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.985 0.975 0.989 0.71
Epoch gpu_mem box obj cls labels img_size
133/149 1.62G 0.02098 0.0121 0.003789 28 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.984 0.972 0.989 0.718
Epoch gpu_mem box obj cls labels img_size
134/149 1.62G 0.02099 0.01211 0.004553 37 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:05<00:00, 2.18it/s]
all 360 359 0.988 0.972 0.99 0.717
Epoch gpu_mem box obj cls labels img_size
135/149 1.62G 0.0204 0.01198 0.003828 36 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.982 0.972 0.988 0.703
Epoch gpu_mem box obj cls labels img_size
136/149 1.62G 0.02085 0.01248 0.003578 35 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.70it/s]
all 360 359 0.987 0.978 0.987 0.702
Epoch gpu_mem box obj cls labels img_size
137/149 1.62G 0.02018 0.01218 0.004048 26 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.987 0.972 0.989 0.71
Epoch gpu_mem box obj cls labels img_size
138/149 1.62G 0.02031 0.0123 0.00356 29 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.988 0.972 0.989 0.71
Epoch gpu_mem box obj cls labels img_size
139/149 1.62G 0.02092 0.01213 0.003891 26 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.988 0.975 0.99 0.71
Epoch gpu_mem box obj cls labels img_size
140/149 1.62G 0.02009 0.01209 0.004039 32 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.988 0.975 0.988 0.705
Epoch gpu_mem box obj cls labels img_size
141/149 1.62G 0.02059 0.01228 0.0038 33 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.991 0.969 0.989 0.713
Epoch gpu_mem box obj cls labels img_size
142/149 1.62G 0.02049 0.01189 0.004289 35 416: 100% 79/79 [00:42<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.73it/s]
all 360 359 0.994 0.972 0.99 0.715
Epoch gpu_mem box obj cls labels img_size
143/149 1.62G 0.01981 0.01201 0.003328 27 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.71it/s]
all 360 359 0.991 0.972 0.989 0.703
Epoch gpu_mem box obj cls labels img_size
144/149 1.62G 0.02104 0.01206 0.00451 32 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.75it/s]
all 360 359 0.99 0.978 0.987 0.707
Epoch gpu_mem box obj cls labels img_size
145/149 1.62G 0.02065 0.01219 0.004047 35 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.76it/s]
all 360 359 0.979 0.978 0.987 0.697
Epoch gpu_mem box obj cls labels img_size
146/149 1.62G 0.02067 0.01179 0.004503 29 416: 100% 79/79 [00:43<00:00, 1.84it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.987 0.977 0.988 0.695
Epoch gpu_mem box obj cls labels img_size
147/149 1.62G 0.02039 0.01239 0.004225 29 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.74it/s]
all 360 359 0.982 0.975 0.986 0.7
Epoch gpu_mem box obj cls labels img_size
148/149 1.62G 0.02021 0.01201 0.003914 30 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:04<00:00, 2.72it/s]
all 360 359 0.985 0.975 0.987 0.704
Epoch gpu_mem box obj cls labels img_size
149/149 1.62G 0.02054 0.01199 0.003628 38 416: 100% 79/79 [00:43<00:00, 1.83it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:05<00:00, 2.15it/s]
all 360 359 0.982 0.978 0.987 0.694
150 epochs completed in 2.008 hours.
Optimizer stripped from runs/train/exp3/weights/last.pt, 14.3MB
Optimizer stripped from runs/train/exp3/weights/best.pt, 14.3MB
Validating runs/train/exp3/weights/best.pt...
Fusing layers...
Model Summary: 213 layers, 7015519 parameters, 0 gradients, 15.8 GFLOPs
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 12/12 [00:07<00:00, 1.54it/s]
all 360 359 0.984 0.972 0.989 0.718
cheetah 360 180 0.997 1 0.995 0.783
hyena 360 179 0.971 0.944 0.983 0.653
wandb: Waiting for W&B process to finish, PID 417... (success).
wandb:
wandb: Run history:
wandb: metrics/mAP_0.5 ▁▅▇▇▆▇▇▇█▇▇██▇██████████████████████████
wandb: metrics/mAP_0.5:0.95 ▁▃▅▄▄▄▅▆▆▅▅▇▆▆▇▆▇▇▇▇▇██▇▇▇▇▇█▇█████████▇
wandb: metrics/precision ▁▅▆▆▆▇▇▇█▇▇▇█▇███▇█▇█████▇█████▇████████
wandb: metrics/recall ▁▄▇▅▅▆▆▇▇▇▆▇▇▇█▇▇▇█▇████████████████████
wandb: train/box_loss █▆▅▅▄▃▃▃▃▂▃▃▂▃▂▂▂▂▂▂▂▂▂▂▂▂▁▂▁▁▁▁▁▁▁▁▁▁▁▁
wandb: train/cls_loss █▅▃▄▄▃▃▃▃▃▂▂▂▂▂▂▂▂▃▂▂▂▂▂▂▁▂▁▁▁▁▁▁▁▁▁▁▁▁▁
wandb: train/obj_loss █▅▄▄▄▄▃▃▃▃▃▃▃▃▃▂▃▂▂▂▂▂▂▂▂▂▂▁▂▁▁▁▁▁▁▁▁▁▁▁
wandb: val/box_loss ██▅▇▇▆▃▃▃▃▃▂▂▄▂▂▃▂▂▂▂▁▂▁▂▂▂▂▂▂▁▁▁▂▂▂▂▂▂▂
wandb: val/cls_loss █▃▂▂▆▂▂▁▁▁▂▁▁▂▁▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
wandb: val/obj_loss █▄▂▃▃▃▂▂▂▃▂▂▂▂▁▂▁▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
wandb: x/lr0 ▁▃▅█████▇▇▇▇▇▆▆▆▆▅▅▅▅▄▄▄▃▃▃▃▂▂▂▂▂▂▁▁▁▁▁▁
wandb: x/lr1 ▁▃▅█████▇▇▇▇▇▆▆▆▆▅▅▅▅▄▄▄▃▃▃▃▂▂▂▂▂▂▁▁▁▁▁▁
wandb: x/lr2 █▇▄▂▂▂▂▂▂▂▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁
wandb:
wandb: Run summary:
wandb: metrics/mAP_0.5 0.98723
wandb: metrics/mAP_0.5:0.95 0.69447
wandb: metrics/precision 0.98229
wandb: metrics/recall 0.97765
wandb: train/box_loss 0.02054
wandb: train/cls_loss 0.00363
wandb: train/obj_loss 0.01199
wandb: val/box_loss 0.02168
wandb: val/cls_loss 5e-05
wandb: val/obj_loss 0.00354
wandb: x/lr0 0.001
wandb: x/lr1 0.001
wandb: x/lr2 0.001
wandb:
wandb: Synced 5 W&B file(s), 337 media file(s), 1 artifact file(s) and 0 other file(s)
wandb: Synced major-shadow-1: https://wandb.ai/lordronz/YOLOv5/runs/3j8heu3j
wandb: Find logs at: ./wandb/run-20211216_101614-3j8heu3j/logs/debug.log
wandb:
Results saved to runs/train/exp3
Evaluate Custom YOLOv5 Detector Performance
Training losses and performance metrics are saved to Tensorboard and also to a logfile.
If you are new to these metrics, the one you want to focus on is mAP_0.5 - learn more about mean average precision here.
# Launch after you have started training
# logs save in the folder "runs"
%load_ext tensorboard
%tensorboard --logdir runs
!python detect.py --weights runs/train/exp3/weights/best.pt --img 416 --conf 0.1 --source {dataset.location}/test/images
detect: weights=['runs/train/exp3/weights/best.pt'], source=/content/datasets/Visikom_PA03-1/test/images, imgsz=[416, 416], conf_thres=0.1, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False YOLOv5 🚀 v6.0-147-g628817d torch 1.10.0+cu111 CUDA:0 (Tesla K80, 11441MiB) Fusing layers... Model Summary: 213 layers, 7015519 parameters, 0 gradients, 15.8 GFLOPs image 1/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_005_resized_jpg.rf.63051f6977b3f3c0de7a7ca2d0eb857f.jpg: 416x416 1 cheetah, Done. (0.028s) image 2/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_006_resized_jpg.rf.dc5b98e584c4e754af38c5da0642792d.jpg: 416x416 1 cheetah, Done. (0.028s) image 3/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_015_resized_jpg.rf.ebea7c18d01ef8bd591bac856ba7f35d.jpg: 416x416 1 cheetah, Done. (0.028s) image 4/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_025_resized_jpg.rf.c512cef7dc1757ea2afa53afeadb7e3b.jpg: 416x416 1 cheetah, Done. (0.028s) image 5/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_027_resized_jpg.rf.cbad621e440ec2877116ad89fa09d9cb.jpg: 416x416 1 cheetah, Done. (0.028s) image 6/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_032_resized_jpg.rf.081e952ba959c9c1b40b944d5b6ef476.jpg: 416x416 1 cheetah, Done. (0.028s) image 7/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_034_resized_jpg.rf.d9580c4e7b077e6d932b21d779eafc24.jpg: 416x416 1 cheetah, Done. (0.028s) image 8/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_036_resized_jpg.rf.3da3f5a5142795088f3f1ebeaa93b9f4.jpg: 416x416 1 cheetah, Done. (0.028s) image 9/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_050_resized_jpg.rf.873f1c85b5bf5f7b2fa70d51e47c6710.jpg: 416x416 1 cheetah, Done. (0.028s) image 10/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_054_resized_jpg.rf.6456cf429d68d5cbe8310815996c438f.jpg: 416x416 1 cheetah, Done. (0.028s) image 11/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_073_resized_jpg.rf.ec0f494f708f2e70497c24e1aeafb25a.jpg: 416x416 1 cheetah, 1 hyena, Done. (0.028s) image 12/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_095_resized_jpg.rf.aca36a5afa428ce867eef5e3c54c6010.jpg: 416x416 1 cheetah, Done. (0.028s) image 13/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_099_resized_jpg.rf.0450c277400afaa6551c76219d05d177.jpg: 416x416 1 cheetah, Done. (0.028s) image 14/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_118_resized_jpg.rf.dcc6154de15bc3fd6478c71d205a07fd.jpg: 416x416 1 cheetah, Done. (0.028s) image 15/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_121_resized_jpg.rf.a96a3c01751ee8926e0a2db5ff5c2772.jpg: 416x416 1 cheetah, Done. (0.028s) image 16/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_123_resized_jpg.rf.a7c96ba143caa2fb5e18a2f61996fc40.jpg: 416x416 1 cheetah, Done. (0.028s) image 17/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_125_resized_jpg.rf.a9edf11b4a4704c32d814386844d6805.jpg: 416x416 1 cheetah, Done. (0.028s) image 18/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_134_resized_jpg.rf.8adfc24cd4d80964d4815d10c6719c56.jpg: 416x416 1 cheetah, Done. (0.028s) image 19/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_146_resized_jpg.rf.76c073af5ba474e584508b7740c6b64c.jpg: 416x416 1 cheetah, Done. (0.028s) image 20/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_147_resized_jpg.rf.366e021c2612b1b8abb0834de478ce84.jpg: 416x416 1 cheetah, Done. (0.027s) image 21/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_161_resized_jpg.rf.3323e6c32711ab18f1588c2abb2f030b.jpg: 416x416 1 cheetah, Done. (0.027s) image 22/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_165_resized_jpg.rf.2643aac0d5b01d39f6753f97323c4a74.jpg: 416x416 1 cheetah, Done. (0.028s) image 23/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_196_resized_jpg.rf.3d59a3e10d2bb28fac9e7c2f2206c928.jpg: 416x416 1 cheetah, Done. (0.027s) image 24/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_197_resized_jpg.rf.dc5df696cba07b9c6433b94431a82c4e.jpg: 416x416 1 cheetah, Done. (0.028s) image 25/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_215_resized_jpg.rf.f3b9f5d9e36fa21535dffedbc807b826.jpg: 416x416 1 cheetah, Done. (0.028s) image 26/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_222_resized_jpg.rf.0dbc89bb96bb48d9b337ad7cf1e8c71a.jpg: 416x416 1 cheetah, Done. (0.028s) image 27/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_229_resized_jpg.rf.a14e4f92d9f043f4867bcbc1cf005ab3.jpg: 416x416 1 cheetah, Done. (0.028s) image 28/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_261_resized_jpg.rf.c9bb1109a4053eed6388f86e389ff59a.jpg: 416x416 1 cheetah, Done. (0.028s) image 29/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_269_resized_jpg.rf.b8c784c25695ca4e04c0e343fe8517a6.jpg: 416x416 1 cheetah, Done. (0.027s) image 30/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_275_resized_jpg.rf.ed6a898edcfe3003d5cf8c0452a29472.jpg: 416x416 1 cheetah, Done. (0.028s) image 31/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_303_resized_jpg.rf.8d608f02aa58cad13f41e854e9e5861d.jpg: 416x416 1 cheetah, Done. (0.028s) image 32/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_323_resized_jpg.rf.cb89dd3b86ec343c811e6fddbb596bde.jpg: 416x416 2 cheetahs, Done. (0.027s) image 33/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_332_resized_jpg.rf.16e01f268b84378693eb70d97ae464e5.jpg: 416x416 1 cheetah, Done. (0.027s) image 34/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_339_resized_jpg.rf.b646953b258652df9d2ac4a8ed498a8a.jpg: 416x416 1 cheetah, Done. (0.027s) image 35/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_347_resized_jpg.rf.579c2e18a9cdcc97ec55ec3869fe6f34.jpg: 416x416 1 cheetah, Done. (0.027s) image 36/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_353_resized_jpg.rf.1ad5b9c410cdfb799e2ad3fc8614984b.jpg: 416x416 1 cheetah, Done. (0.027s) image 37/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_358_resized_jpg.rf.eac92dd8cf34f8fd2e64337c766e74cf.jpg: 416x416 1 cheetah, Done. (0.027s) image 38/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_363_resized_jpg.rf.95c2a38fd8bc59b794334ca6d0d957f7.jpg: 416x416 1 cheetah, Done. (0.027s) image 39/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_373_resized_jpg.rf.d4d2d88b46f73e786cc93e02d551cf29.jpg: 416x416 1 cheetah, Done. (0.027s) image 40/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_378_resized_jpg.rf.ca53e4392d9a87e48aacce939002be04.jpg: 416x416 1 cheetah, Done. (0.027s) image 41/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_384_resized_jpg.rf.5b6dfbf22ada47e51883abccc93fac7f.jpg: 416x416 1 cheetah, Done. (0.027s) image 42/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_401_resized_jpg.rf.755d6d41877de6631fd4d05d42112bd2.jpg: 416x416 1 cheetah, Done. (0.027s) image 43/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_402_resized_jpg.rf.e73afb6ccfcb93c8c52d5e282d989687.jpg: 416x416 1 cheetah, Done. (0.027s) image 44/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_431_resized_jpg.rf.407efd6135f33ca98a1cf0935632a64d.jpg: 416x416 1 cheetah, Done. (0.027s) image 45/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_438_resized_jpg.rf.60a68d972ed4d38734198272cf2c4029.jpg: 416x416 1 cheetah, Done. (0.027s) image 46/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_443_resized_jpg.rf.f687c110ef576889d29bff9c34d81344.jpg: 416x416 1 cheetah, Done. (0.027s) image 47/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_458_resized_jpg.rf.eb7686faaa117752dcf772c1a6bc7ac2.jpg: 416x416 1 cheetah, Done. (0.027s) image 48/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_489_resized_jpg.rf.de4ef86dd3e0bcd859fac6d7925b17eb.jpg: 416x416 1 cheetah, Done. (0.027s) image 49/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_492_resized_jpg.rf.09101af9f4da8145adb83ed9cd875955.jpg: 416x416 1 cheetah, Done. (0.026s) image 50/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_500_resized_jpg.rf.4d6179602039bbd0cbefb8f1d768f256.jpg: 416x416 1 cheetah, Done. (0.027s) image 51/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_515_resized_jpg.rf.d05517e77bc05389e20b491a62cac7f8.jpg: 416x416 1 cheetah, Done. (0.027s) image 52/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_519_resized_jpg.rf.b84c316069f048a7c06b0fed85f89369.jpg: 416x416 1 cheetah, Done. (0.027s) image 53/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_529_resized_jpg.rf.abed8ff727ecc14cc30f845bc04a37e0.jpg: 416x416 1 cheetah, Done. (0.027s) image 54/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_539_resized_jpg.rf.84a4652da89d26e30aa96c345398c3f0.jpg: 416x416 1 cheetah, Done. (0.027s) image 55/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_576_resized_jpg.rf.24082367a1b9af9355bcdcae6c77723f.jpg: 416x416 1 cheetah, Done. (0.027s) image 56/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_583_resized_jpg.rf.7d2f9998c403d43bb0add0ce8befc737.jpg: 416x416 1 cheetah, Done. (0.027s) image 57/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_587_resized_jpg.rf.640b57d7dd553ceb4380e2b4853049dc.jpg: 416x416 1 cheetah, Done. (0.027s) image 58/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_589_resized_jpg.rf.598d14abad1b2c238677eb24ac23e382.jpg: 416x416 1 cheetah, Done. (0.027s) image 59/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_591_resized_jpg.rf.ed9e7d816851b1f0f23094efda14f6cc.jpg: 416x416 1 cheetah, Done. (0.027s) image 60/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_599_resized_jpg.rf.e5014f9e7833dc8f82c7e9628d3ea21f.jpg: 416x416 1 cheetah, Done. (0.027s) image 61/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_602_resized_jpg.rf.d2bf304462a76ab82debd724d1e05058.jpg: 416x416 1 cheetah, Done. (0.027s) image 62/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_614_resized_jpg.rf.9c64a97b6fa5a00ecc619a47b2cdcc0b.jpg: 416x416 1 cheetah, Done. (0.027s) image 63/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_623_resized_jpg.rf.f844bbd7e68986671fbe9bcb7fa4f8f1.jpg: 416x416 1 cheetah, Done. (0.027s) image 64/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_624_resized_jpg.rf.f414da12b643d10c57f4533dc7e843da.jpg: 416x416 1 cheetah, Done. (0.027s) image 65/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_627_resized_jpg.rf.4aff71ec96fddbd3c86235d5ed6ad71f.jpg: 416x416 1 cheetah, Done. (0.027s) image 66/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_639_resized_jpg.rf.e396d7fa48c133226305de25f9114ec7.jpg: 416x416 1 cheetah, Done. (0.027s) image 67/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_645_resized_jpg.rf.8ae9ddb296dbc6d4bed191875a5632da.jpg: 416x416 1 cheetah, Done. (0.027s) image 68/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_661_resized_jpg.rf.87b388ce3063568de96402a8b84ffd81.jpg: 416x416 1 cheetah, Done. (0.027s) image 69/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_678_resized_jpg.rf.9743aeacc0d38677e47681eac1456d0c.jpg: 416x416 1 cheetah, Done. (0.027s) image 70/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_682_resized_jpg.rf.591aeab321876785fa7622836fe1fbe2.jpg: 416x416 1 cheetah, Done. (0.027s) image 71/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_691_resized_jpg.rf.b5961e317898cab3e957c6510683e310.jpg: 416x416 1 cheetah, Done. (0.027s) image 72/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_716_resized_jpg.rf.74f29c4b7225afbe75e14df4e3927845.jpg: 416x416 1 cheetah, Done. (0.026s) image 73/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_721_resized_jpg.rf.dc1cc2e07de2ed7545365d62d94c4df9.jpg: 416x416 1 cheetah, Done. (0.026s) image 74/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_728_resized_jpg.rf.440fc6395e97be80f6a2cdd17878b62c.jpg: 416x416 1 cheetah, Done. (0.026s) image 75/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_729_resized_jpg.rf.9ee063a3a217acc1b9d2f9d22a25e19e.jpg: 416x416 1 cheetah, Done. (0.026s) image 76/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_735_resized_jpg.rf.d5bdd8512fe5f4a0802c73c9b8b598f3.jpg: 416x416 1 cheetah, Done. (0.026s) image 77/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_752_resized_jpg.rf.44f1405e0febe5ee7c52a9f371c624b8.jpg: 416x416 1 cheetah, Done. (0.027s) image 78/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_754_resized_jpg.rf.a0d062f6c190e48a95c07e6295c2fb3a.jpg: 416x416 1 cheetah, Done. (0.026s) image 79/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_772_resized_jpg.rf.ecd71c228a03095ef1abc08989792cc7.jpg: 416x416 1 cheetah, Done. (0.026s) image 80/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_777_resized_jpg.rf.8a3d32da0a6a7b7fef6403f38c2db8c3.jpg: 416x416 1 cheetah, Done. (0.026s) image 81/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_782_resized_jpg.rf.0036b44d96c9feab1f66074f1be21d56.jpg: 416x416 1 cheetah, Done. (0.026s) image 82/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_787_resized_jpg.rf.8194fe836ec5876de3689c7c1854e950.jpg: 416x416 1 cheetah, Done. (0.026s) image 83/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_833_resized_jpg.rf.cc8fac66fb9754fe1a755bdcd3895fcd.jpg: 416x416 1 cheetah, Done. (0.026s) image 84/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_837_resized_jpg.rf.c32603f6c858b7c91f6653cd6dbc14f0.jpg: 416x416 1 cheetah, Done. (0.026s) image 85/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_838_resized_jpg.rf.39ce4568af414a00a7b0f3996ca24229.jpg: 416x416 1 cheetah, Done. (0.027s) image 86/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_841_resized_jpg.rf.fe77d7038f3054c491f7594460d49e05.jpg: 416x416 1 cheetah, Done. (0.026s) image 87/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_868_resized_jpg.rf.b0b124e30d2dae898a9d0667b4d68a24.jpg: 416x416 1 cheetah, Done. (0.027s) image 88/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_892_resized_jpg.rf.05a12252000caa07e117b6a4286f891c.jpg: 416x416 1 cheetah, Done. (0.026s) image 89/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_893_resized_jpg.rf.ae87fe1e1b89792aa31aec6e069f5686.jpg: 416x416 1 cheetah, Done. (0.026s) image 90/180 /content/datasets/Visikom_PA03-1/test/images/cheetah_894_resized_jpg.rf.ef1fc54771bfcfb250fba10720294509.jpg: 416x416 1 cheetah, Done. (0.026s) image 91/180 /content/datasets/Visikom_PA03-1/test/images/hyena_004_resized_jpg.rf.fd5010d5313af6dc0d1bd73df6dda5fe.jpg: 416x416 1 hyena, Done. (0.026s) image 92/180 /content/datasets/Visikom_PA03-1/test/images/hyena_008_resized_jpg.rf.70f189d8a781bf56d91b730f09c107db.jpg: 416x416 1 hyena, Done. (0.026s) image 93/180 /content/datasets/Visikom_PA03-1/test/images/hyena_011_resized_jpg.rf.2c09a97bb06cda0bb0b9b804a9b3e578.jpg: 416x416 1 hyena, Done. (0.026s) image 94/180 /content/datasets/Visikom_PA03-1/test/images/hyena_012_resized_jpg.rf.89b83d5b20a1d53dfe464dc0f6276703.jpg: 416x416 1 hyena, Done. (0.027s) image 95/180 /content/datasets/Visikom_PA03-1/test/images/hyena_031_resized_jpg.rf.0c4a6c1021cb4caef232a533c68792ef.jpg: 416x416 1 hyena, Done. (0.027s) image 96/180 /content/datasets/Visikom_PA03-1/test/images/hyena_054_resized_jpg.rf.b5fc935ec91f4f9b0efc3b99b9a57cb5.jpg: 416x416 1 hyena, Done. (0.026s) image 97/180 /content/datasets/Visikom_PA03-1/test/images/hyena_056_resized_jpg.rf.e37995a577b2b8442aa02bfa52e84969.jpg: 416x416 1 hyena, Done. (0.026s) image 98/180 /content/datasets/Visikom_PA03-1/test/images/hyena_070_resized_jpg.rf.a3d01fdfdcf94df1750c8a4c464fb846.jpg: 416x416 1 hyena, Done. (0.026s) image 99/180 /content/datasets/Visikom_PA03-1/test/images/hyena_077_resized_jpg.rf.5c4ebfe0a786b9cd72f04e8e1456fb0d.jpg: 416x416 2 hyenas, Done. (0.027s) image 100/180 /content/datasets/Visikom_PA03-1/test/images/hyena_089_resized_jpg.rf.443b8ff18f7f4acc4d77c660a1bcf26e.jpg: 416x416 1 hyena, Done. (0.027s) image 101/180 /content/datasets/Visikom_PA03-1/test/images/hyena_094_resized_jpg.rf.96cb2e68e04c046fe02ccbf486dd8056.jpg: 416x416 1 hyena, Done. (0.026s) image 102/180 /content/datasets/Visikom_PA03-1/test/images/hyena_109_resized_jpg.rf.cf804ed0007301d6813e1b5e67023547.jpg: 416x416 1 hyena, Done. (0.026s) image 103/180 /content/datasets/Visikom_PA03-1/test/images/hyena_110_resized_jpg.rf.c083d2087c8dd025b61249051df1f3cb.jpg: 416x416 1 hyena, Done. (0.026s) image 104/180 /content/datasets/Visikom_PA03-1/test/images/hyena_119_resized_jpg.rf.a6b86838ad2a92ec49a239d72a498a0b.jpg: 416x416 1 hyena, Done. (0.026s) image 105/180 /content/datasets/Visikom_PA03-1/test/images/hyena_123_resized_jpg.rf.6dce5cba622a4ecb57dd89410b483f2a.jpg: 416x416 1 hyena, Done. (0.027s) image 106/180 /content/datasets/Visikom_PA03-1/test/images/hyena_146_resized_jpg.rf.348e28f088cec983476d3c62d3b2bb4f.jpg: 416x416 1 hyena, Done. (0.026s) image 107/180 /content/datasets/Visikom_PA03-1/test/images/hyena_150_resized_jpg.rf.669286f62963fb635bcb2a86fdcf4703.jpg: 416x416 1 hyena, Done. (0.026s) image 108/180 /content/datasets/Visikom_PA03-1/test/images/hyena_159_resized_jpg.rf.776fb1a0fec18f349fd7025a49514acf.jpg: 416x416 1 hyena, Done. (0.027s) image 109/180 /content/datasets/Visikom_PA03-1/test/images/hyena_200_resized_jpg.rf.dc227f48cde6ebe9f4e855096eb13eb9.jpg: 416x416 1 hyena, Done. (0.026s) image 110/180 /content/datasets/Visikom_PA03-1/test/images/hyena_216_resized_jpg.rf.431002a92f2dc9b100342749ce419ffa.jpg: 416x416 1 hyena, Done. (0.026s) image 111/180 /content/datasets/Visikom_PA03-1/test/images/hyena_218_resized_jpg.rf.8d5cc065a6b5614ed579b3a9f48d0c82.jpg: 416x416 1 hyena, Done. (0.027s) image 112/180 /content/datasets/Visikom_PA03-1/test/images/hyena_228_resized_jpg.rf.0b3c943fee5ca85ea18ca1e22928c7e0.jpg: 416x416 1 hyena, Done. (0.026s) image 113/180 /content/datasets/Visikom_PA03-1/test/images/hyena_234_resized_jpg.rf.55a063937db4e216a7c623c9bf5bb9eb.jpg: 416x416 1 hyena, Done. (0.027s) image 114/180 /content/datasets/Visikom_PA03-1/test/images/hyena_238_resized_jpg.rf.d568052282884b216002ffa9173dd914.jpg: 416x416 1 hyena, Done. (0.027s) image 115/180 /content/datasets/Visikom_PA03-1/test/images/hyena_245_resized_jpg.rf.aeb50005325b2dfaf9118f9610acd9e7.jpg: 416x416 1 hyena, Done. (0.026s) image 116/180 /content/datasets/Visikom_PA03-1/test/images/hyena_250_resized_jpg.rf.2ebe031d7f2f254d5eb1dded7366fa47.jpg: 416x416 1 hyena, Done. (0.026s) image 117/180 /content/datasets/Visikom_PA03-1/test/images/hyena_257_resized_jpg.rf.5060dd4dc7176d3d4ef4bf3b2384418a.jpg: 416x416 1 hyena, Done. (0.026s) image 118/180 /content/datasets/Visikom_PA03-1/test/images/hyena_263_resized_jpg.rf.15e1d3d8db3729815f024b778e8ddb84.jpg: 416x416 1 hyena, Done. (0.027s) image 119/180 /content/datasets/Visikom_PA03-1/test/images/hyena_279_resized_jpg.rf.0b0c6d8178a8f1817c9705ee329c6d8d.jpg: 416x416 1 hyena, Done. (0.027s) image 120/180 /content/datasets/Visikom_PA03-1/test/images/hyena_327_resized_jpg.rf.4bb1471c8be9de00b2b637f17c745cc9.jpg: 416x416 1 hyena, Done. (0.026s) image 121/180 /content/datasets/Visikom_PA03-1/test/images/hyena_334_resized_jpg.rf.8eee848c54b760c1c97ab7598426c052.jpg: 416x416 1 hyena, Done. (0.026s) image 122/180 /content/datasets/Visikom_PA03-1/test/images/hyena_337_resized_jpg.rf.0dc070afe637542a890f5eaabca91a66.jpg: 416x416 1 hyena, Done. (0.027s) image 123/180 /content/datasets/Visikom_PA03-1/test/images/hyena_359_resized_jpg.rf.524d5f44dd8bfcd339c7b5446b3ddb71.jpg: 416x416 1 hyena, Done. (0.027s) image 124/180 /content/datasets/Visikom_PA03-1/test/images/hyena_363_resized_jpg.rf.9315ad927e30337a548210e2fb44f286.jpg: 416x416 1 hyena, Done. (0.026s) image 125/180 /content/datasets/Visikom_PA03-1/test/images/hyena_364_resized_jpg.rf.669b4a83f37bc33cbf1df9b144184a1e.jpg: 416x416 1 hyena, Done. (0.027s) image 126/180 /content/datasets/Visikom_PA03-1/test/images/hyena_377_resized_jpg.rf.5b2a53d30beb2870f2a4b06f79517ba9.jpg: 416x416 1 hyena, Done. (0.027s) image 127/180 /content/datasets/Visikom_PA03-1/test/images/hyena_385_resized_jpg.rf.dc6b958347ec3b895c2848733d2f4d73.jpg: 416x416 2 hyenas, Done. (0.026s) image 128/180 /content/datasets/Visikom_PA03-1/test/images/hyena_387_resized_jpg.rf.38213444b05639fb254dd9e2c57c125e.jpg: 416x416 2 hyenas, Done. (0.026s) image 129/180 /content/datasets/Visikom_PA03-1/test/images/hyena_388_resized_jpg.rf.f12a6acda15facf991afebcd262e8a12.jpg: 416x416 2 hyenas, Done. (0.026s) image 130/180 /content/datasets/Visikom_PA03-1/test/images/hyena_389_resized_jpg.rf.a6f41406fdd99aa54d0d9be92a450561.jpg: 416x416 1 hyena, Done. (0.027s) image 131/180 /content/datasets/Visikom_PA03-1/test/images/hyena_390_resized_jpg.rf.f03c79da900bb549fa672b2dcc844dd6.jpg: 416x416 1 hyena, Done. (0.027s) image 132/180 /content/datasets/Visikom_PA03-1/test/images/hyena_391_resized_jpg.rf.e5e2f2113e380739e54988a6dd524f9e.jpg: 416x416 1 hyena, Done. (0.026s) image 133/180 /content/datasets/Visikom_PA03-1/test/images/hyena_395_resized_jpg.rf.965924d36b552a4832bd06e0cdf9ef4d.jpg: 416x416 1 hyena, Done. (0.026s) image 134/180 /content/datasets/Visikom_PA03-1/test/images/hyena_397_resized_jpg.rf.ef9e774780286062d7a246d06be13b21.jpg: 416x416 2 hyenas, Done. (0.026s) image 135/180 /content/datasets/Visikom_PA03-1/test/images/hyena_415_resized_jpg.rf.1f5cd77ed68e4b19e9cabf820fad04b2.jpg: 416x416 1 hyena, Done. (0.026s) image 136/180 /content/datasets/Visikom_PA03-1/test/images/hyena_428_resized_jpg.rf.06460db3fe4041b1767d1f65b1871568.jpg: 416x416 1 hyena, Done. (0.027s) image 137/180 /content/datasets/Visikom_PA03-1/test/images/hyena_431_resized_jpg.rf.87187cfb73f647241c7f572a7652e7f6.jpg: 416x416 1 hyena, Done. (0.026s) image 138/180 /content/datasets/Visikom_PA03-1/test/images/hyena_463_resized_jpg.rf.916057f28b5bc17d63186b5c45527dfb.jpg: 416x416 1 hyena, Done. (0.027s) image 139/180 /content/datasets/Visikom_PA03-1/test/images/hyena_480_resized_jpg.rf.3047f91a3076ce2a5c442a50c60adf3a.jpg: 416x416 1 hyena, Done. (0.027s) image 140/180 /content/datasets/Visikom_PA03-1/test/images/hyena_504_resized_jpg.rf.573e9a288bd6b23a371213f85c44635b.jpg: 416x416 1 hyena, Done. (0.027s) image 141/180 /content/datasets/Visikom_PA03-1/test/images/hyena_514_resized_jpg.rf.cb95b645caa520b4b49f2ada43a401ee.jpg: 416x416 1 hyena, Done. (0.027s) image 142/180 /content/datasets/Visikom_PA03-1/test/images/hyena_557_resized_jpg.rf.c0b8fe6f8a2ea2246df77d81a58310d4.jpg: 416x416 1 hyena, Done. (0.026s) image 143/180 /content/datasets/Visikom_PA03-1/test/images/hyena_559_resized_jpg.rf.112638174d23ee98f062855176c68783.jpg: 416x416 1 hyena, Done. (0.026s) image 144/180 /content/datasets/Visikom_PA03-1/test/images/hyena_561_resized_jpg.rf.299488b121f3a6b5818e920a5a90c13b.jpg: 416x416 1 hyena, Done. (0.027s) image 145/180 /content/datasets/Visikom_PA03-1/test/images/hyena_568_resized_jpg.rf.b309d1597ddd7a4f52c84ad4fae17fcc.jpg: 416x416 1 hyena, Done. (0.027s) image 146/180 /content/datasets/Visikom_PA03-1/test/images/hyena_594_resized_jpg.rf.d515cec39c6aec0a849459f6265cd540.jpg: 416x416 1 hyena, Done. (0.026s) image 147/180 /content/datasets/Visikom_PA03-1/test/images/hyena_599_resized_jpg.rf.efef44abdcdf803d8ec06a678eff4f6c.jpg: 416x416 1 hyena, Done. (0.027s) image 148/180 /content/datasets/Visikom_PA03-1/test/images/hyena_605_resized_jpg.rf.fd47b0f546256c819d86fa526acbe551.jpg: 416x416 1 hyena, Done. (0.027s) image 149/180 /content/datasets/Visikom_PA03-1/test/images/hyena_609_resized_jpg.rf.e0f3dde1607646c5fc1b05a40d45f91c.jpg: 416x416 1 hyena, Done. (0.027s) image 150/180 /content/datasets/Visikom_PA03-1/test/images/hyena_613_resized_jpg.rf.52ec1c7e2eae5ba08e2fdc6c729955e3.jpg: 416x416 1 hyena, Done. (0.027s) image 151/180 /content/datasets/Visikom_PA03-1/test/images/hyena_618_resized_jpg.rf.f1f4e7733003fd37abf72b39069d4ff1.jpg: 416x416 1 hyena, Done. (0.026s) image 152/180 /content/datasets/Visikom_PA03-1/test/images/hyena_621_resized_jpg.rf.b6df1601362a91fb7087333425c63acd.jpg: 416x416 1 hyena, Done. (0.026s) image 153/180 /content/datasets/Visikom_PA03-1/test/images/hyena_624_resized_jpg.rf.69aac35e9cff0d62f83171b5e217eeac.jpg: 416x416 1 hyena, Done. (0.027s) image 154/180 /content/datasets/Visikom_PA03-1/test/images/hyena_627_resized_jpg.rf.f8b4b3c4a59ecf4fca25447a3701e9b6.jpg: 416x416 1 hyena, Done. (0.027s) image 155/180 /content/datasets/Visikom_PA03-1/test/images/hyena_663_resized_jpg.rf.cb9492badceebbbd1799019234729d96.jpg: 416x416 1 hyena, Done. (0.026s) image 156/180 /content/datasets/Visikom_PA03-1/test/images/hyena_686_resized_jpg.rf.dfc7abff9efc63d3335f93a2d19bab30.jpg: 416x416 1 hyena, Done. (0.026s) image 157/180 /content/datasets/Visikom_PA03-1/test/images/hyena_704_resized_jpg.rf.fe64bdf956c67f6e07acba8451a1d9c4.jpg: 416x416 1 hyena, Done. (0.026s) image 158/180 /content/datasets/Visikom_PA03-1/test/images/hyena_705_resized_jpg.rf.5c20a25638f6e68936e3fd3341e7eefd.jpg: 416x416 1 hyena, Done. (0.027s) image 159/180 /content/datasets/Visikom_PA03-1/test/images/hyena_711_resized_jpg.rf.8d232e66ad0c2c051341eab901237c3e.jpg: 416x416 1 hyena, Done. (0.027s) image 160/180 /content/datasets/Visikom_PA03-1/test/images/hyena_712_resized_jpg.rf.e15281507ce3b379c24bc696d6c0c637.jpg: 416x416 1 hyena, Done. (0.027s) image 161/180 /content/datasets/Visikom_PA03-1/test/images/hyena_716_resized_jpg.rf.d56b6047bcae57c87c437b2252f54947.jpg: 416x416 1 hyena, Done. (0.027s) image 162/180 /content/datasets/Visikom_PA03-1/test/images/hyena_718_resized_jpg.rf.09ba10d59c6078e8571ca5f5dc75c9b1.jpg: 416x416 1 hyena, Done. (0.026s) image 163/180 /content/datasets/Visikom_PA03-1/test/images/hyena_722_resized_jpg.rf.5f9ce4b516d2037363f4fc3502253875.jpg: 416x416 1 hyena, Done. (0.027s) image 164/180 /content/datasets/Visikom_PA03-1/test/images/hyena_730_resized_jpg.rf.8eb2146b9a49b2cd25e56e0d9084eb29.jpg: 416x416 1 hyena, Done. (0.026s) image 165/180 /content/datasets/Visikom_PA03-1/test/images/hyena_749_resized_jpg.rf.7dd30be63fdad6f93abf73b30c223663.jpg: 416x416 1 hyena, Done. (0.026s) image 166/180 /content/datasets/Visikom_PA03-1/test/images/hyena_755_resized_jpg.rf.5e967d33988cc3fa088d649507676ed3.jpg: 416x416 1 hyena, Done. (0.026s) image 167/180 /content/datasets/Visikom_PA03-1/test/images/hyena_765_resized_jpg.rf.684d06bd32c8577503101910a6d97f21.jpg: 416x416 1 hyena, Done. (0.027s) image 168/180 /content/datasets/Visikom_PA03-1/test/images/hyena_766_resized_jpg.rf.6de5929d11cfb0e8027563eeb0b15877.jpg: 416x416 1 hyena, Done. (0.027s) image 169/180 /content/datasets/Visikom_PA03-1/test/images/hyena_802_resized_jpg.rf.01d88c6300c64f61496bf864d28eb306.jpg: 416x416 1 hyena, Done. (0.026s) image 170/180 /content/datasets/Visikom_PA03-1/test/images/hyena_822_resized_jpg.rf.fdfb249015b2d584a59bc287aec24f71.jpg: 416x416 1 hyena, Done. (0.027s) image 171/180 /content/datasets/Visikom_PA03-1/test/images/hyena_832_resized_jpg.rf.a4eac36705aa61b49e41182468b95124.jpg: 416x416 1 hyena, Done. (0.026s) image 172/180 /content/datasets/Visikom_PA03-1/test/images/hyena_836_resized_jpg.rf.3a4ef0bfa42f16ed7ef2c2dc2a3c297b.jpg: 416x416 1 hyena, Done. (0.027s) image 173/180 /content/datasets/Visikom_PA03-1/test/images/hyena_849_resized_jpg.rf.a148999c8db5c76e9037dfbc3a2db0fe.jpg: 416x416 1 hyena, Done. (0.026s) image 174/180 /content/datasets/Visikom_PA03-1/test/images/hyena_869_resized_jpg.rf.0bb619f9316d78a115f928a6b06fd101.jpg: 416x416 1 hyena, Done. (0.026s) image 175/180 /content/datasets/Visikom_PA03-1/test/images/hyena_873_resized_jpg.rf.bd6bd21ffc47c453114699b1833b54df.jpg: 416x416 2 hyenas, Done. (0.026s) image 176/180 /content/datasets/Visikom_PA03-1/test/images/hyena_880_resized_jpg.rf.5e26aaf2a029784229643b1f78a3c105.jpg: 416x416 1 hyena, Done. (0.026s) image 177/180 /content/datasets/Visikom_PA03-1/test/images/hyena_886_resized_jpg.rf.b7e0fa6bb5267435e2c581798d5ff8f6.jpg: 416x416 1 hyena, Done. (0.026s) image 178/180 /content/datasets/Visikom_PA03-1/test/images/hyena_893_resized_jpg.rf.67254702fc04b402aa56146eab0be0e6.jpg: 416x416 1 hyena, Done. (0.026s) image 179/180 /content/datasets/Visikom_PA03-1/test/images/hyena_894_resized_jpg.rf.fe58a03c03172e2293bef4050fd773de.jpg: 416x416 1 hyena, Done. (0.026s) image 180/180 /content/datasets/Visikom_PA03-1/test/images/hyena_895_resized_jpg.rf.68a767552b8337cec74fcc8d4d2a25a3.jpg: 416x416 1 hyena, Done. (0.026s) Speed: 0.3ms pre-process, 26.8ms inference, 1.3ms NMS per image at shape (1, 3, 416, 416) Results saved to runs/detect/exp2
#collapse-output
import glob
from IPython.display import Image, display
for imageName in glob.glob('/content/yolov5/runs/detect/exp2/*.jpg'): #assuming JPG
display(Image(filename=imageName))
print("\n")
Conclusion and Next Steps
Congratulations! You've trained a custom YOLOv5 model to recognize your custom objects.
To improve you model's performance, we recommend first interating on your datasets coverage and quality. See this guide for model performance improvement.
To deploy your model to an application, see this guide on exporting your model to deployment destinations.
Once your model is in production, you will want to continually iterate and improve on your dataset and model via active learning.
from google.colab import files
files.download('./runs/train/exp3/weights/best.pt')