YOLO V5 for custom training and detection

bugmany commented 3 years ago

❔Question

1.train: python3 train.py --data custom.yaml --cfg yolov5s.yaml --weights weights/yolov5s.pt --epochs 5 train: Scanning 'data/custom/labels/train.cache' images and labels... 6 found, 0 missing, 0 empty, 0 corrupted: 100%|█| 6/6 [0 val: Scanning 'data/custom/labels/train.cache' images and labels... 6 found, 0 missing, 0 empty, 0 corrupted: 100%|█| 6/6 [00:Plotting labels... val: Scanning 'data/custom/labels/train.cache' images and labels... 6 found, 0 missing, 0 empty, 0 corrupted: 100%|█| 6/6 [00:

autoanchor: Analyzing anchors... anchors/target = 3.86, Best Possible Recall (BPR) = 1.0000 Image sizes 640 train, 640 test Using 4 dataloader workers Logging results to runs/train/exp3 Starting training for 5 epochs...

 Epoch   gpu_mem       box       obj       cls     total    labels  img_size
   0/4        0G    0.1254   0.04242   0.08415     0.252        37       640: 100%|█████████| 1/1 [00:05<00:00,  5.10s/it]
           Class      Images      Labels           P           R      mAP@.5  mAP@.5:.95: 100%|█| 1/1 [00:03<00:00,  3.89s
             all           6           0           0           0           0           0

Images sizes do not match. This will causes images to be display incorrectly in the UI.

 Epoch   gpu_mem       box       obj       cls     total    labels  img_size
   1/4        0G    0.1246   0.04416   0.08551    0.2543        42       640: 100%|█████████| 1/1 [00:06<00:00,  6.93s/it]
           Class      Images      Labels           P           R      mAP@.5  mAP@.5:.95: 100%|█| 1/1 [00:03<00:00,  3.41s
             all           6           0           0           0           0           0

 Epoch   gpu_mem       box       obj       cls     total    labels  img_size
   2/4        0G    0.1251   0.05065   0.08903    0.2648        46       640: 100%|█████████| 1/1 [00:05<00:00,  5.33s/it]
           Class      Images      Labels           P           R      mAP@.5  mAP@.5:.95: 100%|█| 1/1 [00:03<00:00,  3.72s
             all           6           0           0           0           0           0

 Epoch   gpu_mem       box       obj       cls     total    labels  img_size
   3/4        0G   0.07845   0.04337   0.05434    0.1762        36       640: 100%|█████████| 1/1 [00:05<00:00,  5.19s/it]
           Class      Images      Labels           P           R      mAP@.5  mAP@.5:.95: 100%|█| 1/1 [00:03<00:00,  3.28s
             all           6           0           0           0           0           0

 Epoch   gpu_mem       box       obj       cls     total    labels  img_size
   4/4        0G    0.1235    0.0542   0.08529     0.263        54       640: 100%|█████████| 1/1 [00:04<00:00,  4.73s/it]
           Class      Images      Labels           P           R      mAP@.5  mAP@.5:.95: 100%|█| 1/1 [00:03<00:00,  3.22s
             all           6           0           0           0           0           0

5 epochs completed in 0.014 hours.

Optimizer stripped from runs/train/exp3/weights/last.pt, 14.5MB Optimizer stripped from runs/train/exp3/weights/best.pt, 14.5MB Images sizes do not match. This will causes images to be display incorrectly in the UI.

wandb: Waiting for W&B process to finish, PID 79757 wandb: Program ended successfully.

2.detect: python3 detect.py --source data/images --weights weights/best.pt --conf 0.25 Fusing layers... Model Summary: 224 layers, 7113244 parameters, 0 gradients, 16.5 GFLOPS image 1/2 /Users/home/dev/yolov5/data/images/bus.jpg: 640x480 Done. (0.182s) image 2/2 /Users/home/dev/yolov5/data/images/zidane.jpg: 384x640 Done. (0.148s) Results saved to runs/detect/exp2 Done. (0.400s)

at last, i did not detect anything information with my train models ("best.pt"), can anyone help me?

Additional context

github-actions[bot] commented 3 years ago

👋 Hello @bugmany, thank you for your interest in 🚀 YOLOv5! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

Google Colab and Kaggle notebooks with free GPU:
Google Cloud Deep Learning VM. See GCP Quickstart Guide
Amazon Deep Learning AMI. See AWS Quickstart Guide
Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

glenn-jocher commented 3 years ago

@bugmany 👋 Hello! Thanks for asking about improving training results. Most of the time good results can be obtained with no changes to the models or training settings, provided your dataset is sufficiently large and well labelled. If at first you don't get good results, there are steps you might be able to take to improve, but we always recommend users first train with all default settings before considering any changes. This helps establish a performance baseline and spot areas for improvement.

If you have questions about your training results we recommend you provide the maximum amount of information possible if you expect a helpful response, including results plots (train losses, val losses, P, R, mAP), PR curve, confusion matrix, training mosaics, test results and dataset statistics images such as labels.png. All of these are located in your project/name directory, typically yolov5/runs/train/exp.

We've put together a full guide for users looking to get the best results on their YOLOv5 trainings below.

Dataset

Images per class. ≥1.5k images per class
Instances per class. ≥10k instances (labeled objects) per class total
Image variety. Must be representative of deployed environment. For real-world use cases we recommend images from different times of day, different seasons, different weather, different lighting, different angles, different sources (scraped online, collected locally, different cameras) etc.
Label consistency. All instances of all classes in all images must be labelled. Partial labelling will not work.
Label accuracy. Labels must closely enclose each object. No space should exist between an object and it's bounding box. No objects should be missing a label.
Background images. Background images are images with no objects that are added to a dataset to reduce False Positives (FP). We recommend about 0-10% background images to help reduce FPs (COCO has 1000 background images for reference, 1% of the total).

Model Selection

Larger models like YOLOv5x will produce better results in nearly all cases, but have more parameters and are slower to run. For mobile applications we recommend YOLOv5s/m, for cloud or desktop applications we recommend YOLOv5l/x. See our README table for a full comparison of all models.

To start training from pretrained weights simply pass the name of the model to the --weights argument. Models download automatically from the latest YOLOv5 release.

python train.py --data custom.yaml --weights yolov5s.pt
                                             yolov5m.pt
                                             yolov5l.pt
                                             yolov5x.pt

YOLOv5 Models

Training Settings

Before modifying anything, first train with default settings to establish a performance baseline. A full list of train.py settings can be found in the train.py argparser.

Epochs. Start with 300 epochs. If this overfits early then you can reduce epochs. If overfitting does not occur after 300 epochs, train longer, i.e. 600, 1200 etc epochs.
Image size. COCO trains at native resolution of --img 640, though due to the high amount of small objects in the dataset it can benefit from training at higher resolutions such as --img 1280. If there are many small objects then custom datasets will benefit from training at native or higher resolution. Best inference results are obtained at the same --img as the training was run at, i.e. if you train at --img 1280 you should also test and detect at --img 1280.
Batch size. Use the largest --batch-size that your hardware allows for. Small batch sizes produce poor batchnorm statistics and should be avoided.
Hyperparameters. Default hyperparameters are in hyp.scratch.yaml. We recommend you train with default hyperparameters first before thinking of modifying any. In general, increasing augmentation hyperparameters will reduce and delay overfitting, allowing for longer trainings and higher final mAP. Reduction in loss component gain hyperparameters like hyp['obj'] will help reduce overfitting in those specific loss components. For an automated method of optimizing these hyperparameters, see our Hyperparameter Evolution Tutorial.

ultralytics / yolov5