shape '[1024, 512, 3, 3]' is invalid for input of size 2794830

[BeLEEU]

Traceback (most recent call last): File "D:/DEEPL/pytorch-yolo-v3-master/detect.py", line 118, in model.load_weights(args.weightsfile) File "D:\DEEPL\pytorch-yolo-v3-master\darknet.py", line 469, in load_weights conv_weights = conv_weights.view_as(conv.weight.data) RuntimeError: shape '[1024, 512, 3, 3]' is invalid for input of size 2794830

[fourth-archive]

@BeLEEU I recommend you try this YOLOv3 tutorial to solve your problem: https://github.com/ultralytics/yolov3/wiki/Train-Custom-Data

The accompanying repository works on MacOS, Windows and Linux, includes multigpu and multithreading, performs inference on images, videos, webcams, and an iOS app. It also tests to slightly higher mAPs than darknet, including on the latest YOLOv3-SPP.weights (60.7 COCO mAP), and offers the ability to train custom datasets from scratch to darknet performance, all using PyTorch :) https://github.com/ultralytics/yolov3

[Sam813]

@BeLEEU I have the same issue. have you solved it?

[OUYANGYAFEI]

did you solve it ,i met the same problem and i trapeed into it for a longtime ,i dont know it appears in the code