Lim Zhen Xian

Guys, dont use this version of pytorch YOLOv4, its a total waste of time.

10

This repository is like a trap, like a hole without ending. Everything in this repository got bugs and no one is using them already. The bug continue and continues emerges...

anno_json = glob.glob('./coco/annotations/instances_val*.json')[0] # annotations json

6

我有翻过你之前的帖子 分别是两个一个是说 试看改成这样，我试了还是不working勒 > anno_json = glob.glob('./coco/annotations/instances_val*.json')[0] # annotations json 另一个是说找不到ground truthfile 不过hor，这问题就来了，为什么如果我只train8个或以下的epoch的时候，他就不会触发这个error呢？

How do I know if all the 1500 images is unique?

1

I wonder if all 1500 images in this dataset is unique?

大佬 请问你可以教我如何写一个test.py吗？

3

你好，我是来自马来西亚的学生。你是我少数看到现在还活跃的yolov4大佬，我想跟你请教如何写一个test.py。因为我在跟着一个tianxiaomo的yolov4但是他没有做test.py。所以我的教授要求我去写一个，但是我看来看去（比如说看他的train.py，比如说看你的train.py和test.py，和别人的），我真的不懂我在看什么。（哭）

Can we discuss how to break the model into separate component? I want to output the validation loss graph.

1

Hi sovit, its been a long time. I finally released from my finals. Now that I would like to continue to study this model, so that it could output the...

How to solve this error? RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

9

Traceback (most recent call last): File "/content/PyTorch_YOLOv4/train.py", line 537, in train(hyp, opt, device, tb_writer, wandb) File "/content/PyTorch_YOLOv4/train.py", line 288, in train loss, loss_items = compute_loss(pred, targets.to(device), model) # loss scaled...