pytorch-YOLOv4

pytorch-YOLOv4 copied to clipboard

the loss is too high

3

When I used the coin data set provided by the author, training Loss was large and it took about 700 epochs to converge. When I adopted my own data set,...

781458112

convert .pth file to .weights file

1

**Hi.I want to convert my pth file to weights file, and I run this script** ` model = Darknet(cfgfile='/media/hkuit164/WD20EJRX/yolov4.cfg') model.load_state_dict(torch.load("/media/hkuit164/WD20EJRX/pytorch-YOLOv4/yolov4.pth", map_location=torch.device('cpu'))) model.save_weights(outfile='newYolov4.weights', cutoff=-1)` **But there is an error:** `/home/hkuit164/anaconda3/envs/v4/bin/python3.7 /media/hkuit164/WD20EJRX/pytorch-YOLOv4/tool/darknet2pytorch.py...

Sean-hku

Does it support multi GPUs?

5

How to train it with numlti gpus?

yxy1995123

Where are the codes of the APs, APm, and APl you detected in your README? thanks. 

Zengyf-CVer

Training Custom Dataset using tiny-yolo-v4

1

Hello @Tianxiaomo, I am trying to train my custom dataset using tiny-yolo-v4. I have made changes in the .cfg file and trying to train the network. The following error has...

rak7045

Hi @Tianxiaomo, thank you for the repository, It has been very useful for my thesis! One question bothers me btw. I started my with no knowledge about yolo or object...

RicRicci22

I can not run train because the gradient can not be counted

2

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [1, 3, 19, 19, 121]], which is output 0 of AsStridedBackward, is at...

qam1314

Did you check accuracy of YOLOv4 by using your implementation on MSCOCO?

19

@Tianxiaomo Hi, * Did you check accuracy of YOLOv4 by using your implementation, do you get the same 43.5% AP (65.7% AP50) for yolov4.cfg 608x608 on MS COCO testdev? *...

AlexeyAB

very slow when evaluate on COCO dataset, about half hour per image!

4

this is the command, and the weight is default "yolov4.weight". ``` python evaluate_on_coco.py -dir COCO_dataset/val2017 -gta COCO_dataset/instances_val2017.json -c cfg/yolov4.cfg -g 1 ``` I made slight changes on _evaluate_on_coco.py_, otherwise it...

liukaigua

I saw https://medium.com/analytics-vidhya/train-a-custom-yolov4-tiny-object-detector-using-google-colab-b58be08c9593 article and with my custom data, it infer very well ! now I'm trying to convert my weight file to pt file so that I can use...

kotran88