YOLOv3 pytorch版源代码

# PyTorch-YOLOv3 A minimal PyTorch implementation of YOLOv3, with support for training, inference and evaluation. ## Installation ##### Clone and install requirements $ git clone https://github.com/eriklindernoren/PyTorch-YOLOv3 $ cd PyTorch-YOLOv3/ $ sudo pip3 install -r requirements.txt ##### Download pretrained weights $ cd weights/ $ bash download_weights.sh ##### Download COCO $ cd data/ $ bash get_coco_dataset.sh ## Test Evaluates the model on COCO test. $ python3 test.py --weights weights/yolov3.weights | Model | mAP (min. 50 IoU) | | ----------------------- |:-----------------:| | YOLOv3 608 (paper) | 57.9 | | YOLOv3 608 (this impl.) | 57.3 | | YOLOv3 416 (paper) | 55.3 | | YOLOv3 416 (this impl.) | 55.5 | ## Inference Uses pretrained weights to make predictions on images. Below table displays the inference times when using as inputs images scaled to 256x256. The ResNet backbone measurements are taken from the YOLOv3 paper. The Darknet-53 measurement marked shows the inference time of this implementation on my 1080ti card. | Backbone | GPU | FPS | | ----------------------- |:--------:|:--------:| | ResNet-101 | Titan X | 53 | | ResNet-152 | Titan X | 37 | | Darknet-53 (paper) | Titan X | 76 | | Darknet-53 (this impl.) | 1080ti | 74 | $ python3 detect.py --images data/samples/ <p align="center"><img src="assets/giraffe.png" width="480"\></p> <p align="center"><img src="assets/dog.png" width="480"\></p> <p align="center"><img src="assets/traffic.png" width="480"\></p> <p align="center"><img src="assets/messi.png" width="480"\></p> ## Train For argument descriptions have a lock at `python3 train.py --help` #### Example (COCO) To train on COCO using a Darknet-53 backend pretrained on ImageNet run: ``` $ python3 train.py --data config/coco.data --pretrained_weights weights/darknet53.conv.74 ``` #### Training log ``` ---- [Epoch 7/100, Batch 7300/14658] ---- +------------+--------------+--------------+--------------+ | Metrics | YOLO Layer 0 | YOLO Layer 1 | YOLO Layer 2 | +------------+--------------+--------------+--------------+ | grid_size | 16 | 32 | 64 | | loss | 1.554926 | 1.446884 | 1.427585 | | x | 0.028157 | 0.044483 | 0.051159 | | y | 0.040524 | 0.035687 | 0.046307 | | w | 0.078980 | 0.066310 | 0.027984 | | h | 0.133414 | 0.094540 | 0.037121 | | conf | 1.234448 | 1.165665 | 1.223495 | | cls | 0.039402 | 0.040198 | 0.041520 | | cls_acc | 44.44% | 43.59% | 32.50% | | recall50 | 0.361111 | 0.384615 | 0.300000 | | recall75 | 0.222222 | 0.282051 | 0.300000 | | precision | 0.520000 | 0.300000 | 0.070175 | | conf_obj | 0.599058 | 0.622685 | 0.651472 | | conf_noobj | 0.003778 | 0.004039 | 0.004044 | +------------+--------------+--------------+--------------+ Total Loss 4.429395 ---- ETA 0:35:48.821929 ``` #### Tensorboard Track training progress in Tensorboard: * Initialize training * Run the command below * Go to http://localhost:6006/ ``` $ tensorboard --logdir='logs' --port=6006 ``` Storing the logs on a slow drive possibly leads to a significant training speed decrease. You can adjust the log directory using `--logdir <path>` when running `tensorboard` or the `train.py`. ## Train on Custom Dataset #### Custom model Run the commands below to create a custom model definition, replacing `<num-classes>` with the number of classes in your dataset. ``` $ cd config/ # Navigate to config dir $ bash create_custom_model.sh <num-classes> # Will create custom model 'yolov3-custom.cfg' ``` #### Classes Add class names to `data/custom/classes.names`. This file should have one row per class name. #### Image Folder Move the images of your dataset to `data/custom/images/`. #### Annotation Folder Move your annotations to `data/custom/labels/`. The dataloader expects that the annotation file corresponding to the image `data/custom/images/train.jpg` has the path `data/custom/labels/train.txt`. Each row in the annotation file should define one bounding box, using the syntax `label_idx x_center y_center width height`. The coordinates should be scaled `[0, 1]`, and the `label_idx` should be zero-indexed and correspond to the row number of the class name in `data/custom/classes.names`. #### Define Train and Validation Sets In `data/custom/train.txt` and `data/custom/valid.txt`, add paths to images that will be used as train and validation data respectively. #### Train To train on the custom dataset run: ``` $ python3 train.py --model config/yolov3-custom.cfg --data config/custom.data ``` Add `--pretrained_weights weights/darknet53.conv.74` to train using a backend pretrained on ImageNet. ## Credit ### YOLOv3: An Incremental Improvement _Joseph Redmon, Ali Farhadi_ <br> **Abstract** <br> We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that’s pretty swell. It’s a little bigger than last time but more accurate. It’s still fast though, don’t worry. At 320 × 320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 AP50 in 51 ms on a Titan X, compared to 57.5 AP50 in 198 ms by RetinaNet, similar performance but 3.8× faster. As always, all the code is online at https://pjreddie.com/yolo/. [[Paper]](https://pjreddie.com/media/files/papers/YOLOv3.pdf) [[Project Webpage]](https://pjreddie.com/darknet/yolo/) [[Authors' Implementation]](https://github.com/pjreddie/darknet) ``` @article{yolov3, title={YOLOv3: An Incremental Improvement}, author={Redmon, Joseph and Farhadi, Ali}, journal = {arXiv}, year={2018} } ```