SpursLipu / YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone

YOLO ModelCompression MultidatasetTraining
GNU General Public License v3.0
444 stars 136 forks source link

conv_b = torch.from_numpy(weights[ptr:ptr + num_b]).view_as(conv_layer.bias) RuntimeError: shape '[18]' is invalid for input of size 0 #152

Closed Abhishek672 closed 2 years ago

Abhishek672 commented 2 years ago

@SpursLipu @domdal @yingbiaoluo @TianhaoFu

I am trying to train yolov4-tiny with the command.

!python train.py \ --cfg cfg/yolov4-tiny-custom.cfg \ --data data/obj.data \ --weights yolov4-tiny.conv.29 \ --name data/obj.names \ --quantized 1

I have my custom dataset with only 1 class. any idea how to resolve this?