训练时model.py在load_darknet_weights处报错

Lam1360 / YOLOv3-model-pruning

在 oxford hand 数据集上对 YOLOv3 做模型剪枝（network slimming）

MIT License

1.67k stars 431 forks source link

训练时model.py在load_darknet_weights处报错 #15

Open gooseable opened 5 years ago

gooseable commented 5 years ago

您好，我进行训练的时候报以下错误

File "train.py", line 77, in model.load_darknet_weights(opt.pretrained_weights) File "/home/cct/YOLOv3-model-pruning/models.py", line 317, in load_darknet_weights conv_w = torch.from_numpy(weights[ptr: ptr + num_w]).view_as(conv_layer.weight) RuntimeError: shape '[256, 128, 3, 3]' is invalid for input of size 160590

请问这个怎么解决？

Lam1360 commented 5 years ago

你预训练权重用的哪个？yolov3 还是 darknet53？

zhangyu96 commented 5 years ago

应该是权重文件不完整

gooseable commented 4 years ago

已经解决了，就是权重文件不完整的问题