search

bingykang / Fewshot_Detection

Few-shot Object Detection via Feature Reweighting
https://arxiv.org/abs/1812.01866
529 stars 112 forks source link

RuntimeError: The size of tensor a (3) must match the size of tensor b (864) at non-singleton dimension 3 #76

Open edlawson opened 2 years ago

edlawson commented 2 years ago

I'm having some issues running train_meta. Specifically, I get the above error. All messages are:

~/Fewshot_Detection$ python train_meta.py cfg/metayolo.data cfg/darknet_dynamic.cfg cfg/reweighting_net.cfg darknet19_448.conv.23 /home/elawson/Fewshot_Detection/data/coco.names save_interval 10 ['bird', 'bus', 'cow', 'motorbike', 'sofa'] base_ids [0, 1, 3, 4, 6, 7, 8, 10, 11, 12, 14, 15, 16, 18, 19] logging to backup/metayolo_novel0_neg1 class_scale 1 Traceback (most recent call last): File "train_meta.py", line 87, in model.load_weights(weightfile) File "/home/elawson/Fewshot_Detection/darknet_meta.py", line 378, in load_weights start = load_conv_bn(buf, start, model[0], model[1]) File "/home/elawson/Fewshot_Detection/cfg.py", line 455, in load_conv_bn convmodel.weight.data.copy(torch.from_numpy(buf[start:start+num_w])); start = start + num_w RuntimeError: The size of tensor a (3) must match the size of tensor b (864) at non-singleton dimension 3

Suggestions?

WqxLoveCoding commented 2 years ago

hello, have you fixed it yet? I met the same problem

fish-kong commented 2 years ago

hello, have you fixed it yet? I met the same problem

2563895797 commented 2 years ago

hello, have you fixed it yet? I met the same problem

xyqqqfs commented 2 years ago

https://github.com/bingykang/Fewshot_Detection/issues/7#issuecomment-753658247 I followed this method and it worked, you can try it

STSTERANDMOMO commented 1 year ago

TypeError: only integer tensors of a single element can be converted to an index Have you met this problem?