PyTorch_YOLOv4

PyTorch_YOLOv4 copied to clipboard

IndexError: list index out of range

2

Traceback (most recent call last): File "train.py", line 438, in train(hyp, opt, device, tb_writer) File "train.py", line 308, in train save_dir=log_dir) File "/home/w/文档/PyTorch_YOLOv4/test.py", line 206, in test plot_images(img, output_to_target(output, width,...

dreamitpossible1

How to add attention module to train

1

how can i add attention like CBAM to train to see if the result is better?

shaun881017

I wonder why the batch size was 8 when measuring FPS. In general, I know that the batch size is set to 1.

ohjunee

您好，我发现general.py文件里面有很多丢失的类别，问一下这个工程是否真的能跑通，并得到想要的效果

xiong224

BottleneckCSP2

7

Had the BottleneckCSP2 module been used in Alexey's paper also used in YOLOv4? I wonder if this is updated from YOLov5 or in the YOLov4 paper.

ohjunee

Step size in plots is not uniform (wandb)

3

Hi, training a YOLOv4 model on my custom dataset, I see that the step size in the wandb plots is not uniform between the various metrics: for instance, after 2...

antimo22

Add Weights & Biases Logging support

9

This PR adds support for debugging models using W&B, only if the library is already found installed. When using W&B, users of YOLOV5 can debug their models easily inside a...

AyushExel

Use 4-channel images for training. Work in Progress. Not merge yet

jcmayoral

Hello, is JDE supported with yolov4 and yolor? I see track-yolo in the development log, but it is a broken link. If yes, where do I find the code for...

kenrickfernandes

wandb图片的Step和实际训练的epoch不一致

27

作者你好，我在train.py里将--epochs参数设置为1000，但是在wandb里所有曲线图的横坐标Step都是0-12K，对应不上。这是怎么回事呢？如何修改正确？wandb中的Logs也是训练到1000轮，为什么Step最大值会显示为12K呢？谢谢   

Wanghe1997