PyTorch-YOLOv3

PyTorch-YOLOv3 copied to clipboard

Bumps [tensorboard](https://github.com/tensorflow/tensorboard) from 2.7.0 to 2.10.0. Release notes Sourced from tensorboard's releases. TensorBoard 2.10.0 The 2.10 minor series tracks TensorFlow 2.10. Features Time Series is now the default dashboard when...

dependabot[bot]

TypeError: Caught TypeError in DataLoader worker process 0.

1

Traceback (most recent call last): File "C:/Users/dell/Desktop/wc/PyTorch-YOLOv3-master/PyTorch-YOLOv3-master/pytorchyolo/train.py", line 257, in run() File "C:/Users/dell/Desktop/wc/PyTorch-YOLOv3-master/PyTorch-YOLOv3-master/pytorchyolo/train.py", line 154, in run for batch_i, (_, imgs, targets) in enumerate(tqdm.tqdm(dataloader,desc=f"Training Epoch{epoch}")): File "D:\Anaconda\envs\cyb\lib\site-packages\tqdm\_tqdm.py", line 1060, in...

lambert66

Having some doubts for build_target

1

Hello there, After learning your code, I still have some doubts. If one label has a chance to appear in each layer(13 13, 26 26, 52 52) and many anchors....

d5423197

this repo is good ONLY for INFERENCE with PROVIDED WEIGHTS.

8

like the title said, this implementation suffers serious issue when trained from scratch with mAP stalling at around 20%. If you are planning to train this on custom data, I...

ScottHoang

- [ ] add support to multi-GPU training by wrapping the model with `DtataParallel` - [ ] add function to automatically save the best checkpoint

XZLeo

Pinning of setup tools

1

Is this still necessary? https://github.com/eriklindernoren/PyTorch-YOLOv3/blob/3f7f04bb4137219e8f0f1bde0af15f08ab6fb746/.github/workflows/main.yml#L25

jaagut

Tiny YOLOv3 vs YOLOv5s

1

Hi, I'm trying to compare the 2 models by training them on the same custom dataset. However, after testing I realized that the Tiny YOLOv3 performs at an mAP0.5 of...

wiky231

why the default anchor is 10,13, 16,30, 33,23.... and as for my kmeans result on VOC2007, there aren't the anchor size like 10 ? (the first is 23,31)

1

same as above.

clw5180

Caught RuntimeError in DataLoader worker process 0 while running test.py for COCO

8

**command:** python test.py --weights_path yolov3.weights **error:** Namespace(batch_size=8, class_path='data/coco.names', conf_thres=0.001, data_config='config/coco.data', img_size=416, iou_thres=0.5, model_def='config/yolov3.cfg', n_cpu=8, nms_thres=0.5, weights_path='yolov3.weights') Compute mAP... Detecting objects: 0%| | 0/625 [00:00

alyssa121

## Proposed changes - Add flake8 linter as dev dependency - Resolve linter warnings ## Related issues ## Necessary checks - [x] Update poetry package version [semantically](https://semver.org/) - [ ]...

jaagut