The following error occurred when I use yolov4-tiny.cfg:
Traceback (most recent call last):
File "/Users/ren_yx/PycharmProjects/Object detection/YOLO_pruning/train.py", line 542, in
train() # train normally
File "/Users/ren_yx/PycharmProjects/Object detection/YOLO_pruning/train.py", line 143, in train
cutoff = load_darknet_weights(model, weights)
File "/Users/ren_yx/PycharmProjects/Object detection/YOLO_pruning/models.py", line 353, in load_darknet_weights
conv_w = torch.from_numpy(weights[ptr:ptr + num_w]).view_as(conv_layer.weight)
RuntimeError: shape '[256, 384, 3, 3]' is invalid for input of size 875238
tanluren
commented
4 years ago
The following error occurred when I use yolov4-tiny.cfg: Traceback (most recent call last): File "/Users/ren_yx/PycharmProjects/Object detection/YOLO_pruning/train.py", line 542, in
train() # train normally
File "/Users/ren_yx/PycharmProjects/Object detection/YOLO_pruning/train.py", line 143, in train
cutoff = load_darknet_weights(model, weights)
File "/Users/ren_yx/PycharmProjects/Object detection/YOLO_pruning/models.py", line 353, in load_darknet_weights
conv_w = torch.from_numpy(weights[ptr:ptr + num_w]).view_as(conv_layer.weight)
RuntimeError: shape '[256, 384, 3, 3]' is invalid for input of size 875238