pytorch-YOLOv4
pytorch-YOLOv4 copied to clipboard
Tianxiaomo
PyTorch ,ONNX and TensorRT implementation of YOLOv4
I have made a custom object detector with a lot of code on top of it (it also includes a tracker, counts objects, ...). Now I want to integrate this...
RuntimeError: shape '[2, RuntimeError: shape '[2, 3, 7, 56, 56]' is invalid for input of size 2257923, 7, 56, 56]' is invalid for input of size 225792RuntimeError: shape '[2, 3,...
一些bug
1. dataset.py 需要加上import torch 2. coco_eval.py 222行 ```assert set(annsImgIds) == (set(annsImgIds) & set(self.getImgIds())), \ 'Results do not correspond to current coco set'``` 这里引发了异常 3. 多GPU训练时，`torch.load()` 均报错，加个判断是否使用多gpu更好
Traceback (most recent call last): File "train.py", line 628, in model = Yolov4(cfg.pretrained, n_classes=cfg.classes) File "/home/wd337/wly/pytorch-YOLOv4-Tianxiaomo/models.py", line 426, in __init__ pretrained_dict = torch.load(yolov4conv137weight) File "/home/wd337/anaconda3/envs/yolov4-wang/lib/python3.7/site-packages/torch/serialization.py", line 595, in load return...
在进行evaluate的时候，执行boxes[...,2:] = boxes[...,2:] - boxes[...,:2]时遇到这个问题 When evaluating, I encountered this problem when executing ‘boxes[...,2:] = boxes[...,2:]-boxes[...,:2]’
这个问题到底怎么解决，看了issues里面的解答还是解决不了，哪位大佬可以提供一份步骤详细的解答，感激不尽 How can i solve this problem absolutely? it doesn't work when i use the way that is mentioned in issues to try to solve the problem ,which boss can...
when I train my own dataset ,I met a problem and the train process is ended,please help me (base) E:\pytorch-YOLOv4-master>python train.py -l 0.001 -g 4 -pretrained ./yolov.pth -classes 2 -dir...
Hi! I just wanted to run the train.py script and it gave me the following output: ``` Traceback (most recent call last): File "train.py", line 37, in from tool.tv_reference.coco_utils import...
Hi, I have trained a scaled-yolov4 object detection model in darknet, which I have converted to a pytorch model via this repo. When I load the pytorch model onto my...
I was experimenting with 3d printing failure detection with [Obico](https://github.com/TheSpaghettiDetective/obico-server/issues/787) and found your repository very useful to convert original Darknet weights file into ONNX format. But unfortunately, Yolov2 support is...
Metadata
Owner
Metadata
PyTorch ,ONNX and TensorRT implementation of YOLOv4