PyTorch_YOLOv4

PyTorch_YOLOv4 copied to clipboard

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

3

This error comes out when training with multiple gpus. Go to `build_target` function in the file `utils/general.py`. Add `anchors = anchors.to(targets.device)` right below the line `anchors = model.module.module_list[jj].anchor_vec if multi_gpu...

youngtuotuo

 from 0 - 21 epoch ：precision=recall =0 from 22- 199 epoch: precision = 1 recall = 0.000231 我跑的是自己的数据集。 同等超参下能达到比YOLOV7还高的MAP，这令人非常疑惑。

diplomatist

Multiple GPUs Problem

5

The code can run successfully when I use a single GPU to train my data. However, when I add "--device 0,1" in my command line, it shows: `" RuntimeError: Expected...

jerryWTMH

PermissionError: [WinError 5] 拒绝访问

5

你好，我想知道为什么我训练途中会出错？ 使用 --resume 后效果很差，并且也会出现同样的错误 Epoch gpu_mem GIoU obj cls total targets img_size 79/299 6.01G 0.02431 0.04288 0.01463 0.08182 35 608: 100%|██████████| 289/289 [02:33

YChao99

How to Adjust the thickness and font size？

1

How to adjust the thickness and font size of the box marked on the graph during prediction？

taoyuan-Zhang

Hello @WongKinYiu , Thanks so much for your effort in making this repo. I have some trouble with calculating auto-anchors. In [train.py ](https://github.com/WongKinYiu/PyTorch_YOLOv4/blob/master/train.py#L208) I have uncommented the part and run...

rak7045

Bumps [numpy](https://github.com/numpy/numpy) from 1.17 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

After training. I cannot run test.py ordetect.py

3

I change weight, data, cfg on test.py. But when run it. I meet error. Please help me fix it. Model Summary: 327 layers, 6.39431e+07 parameters, 6.39431e+07 gradients, 141.5 GFLOPS Traceback...

minhhoai1001

你好我训练到最后一步报这个错， 测试也测试过不了，检测也用不了

6

def output_to_target(output, width, height): # Convert model output to target format [batch_id, class_id, x, y, w, h, conf] if isinstance(output, torch.Tensor): output = output.cpu().numpy() targets = [] for i, o...

Huxufeng666

I had " ValueError: too many values to unpack (expected 2) " error

3

Hi everyone when I run train.py, I got the error as below, those message including which hyper parameter be used. > Namespace(adam=False, batch_size=1, bucket='', cache_images=False, cfg='cfg/yolov4.cfg', data='data/coco.yaml', device='', epochs=5, evolve=False,...

Anthony1011