Open Miracle-hpf opened 4 years ago
you can solve it as follows tmp = buf[start:start+num_w] tmp = tmp.view(conv_model.weight.shape) conv_model.weight.data.copy(tmp)
you can solve it as follows tmp = buf[start:start+num_w] tmp = tmp.view(conv_model.weight.shape) conv_model.weight.data.copy(tmp)
Thanks for your reply!I reduce the torch version to 0.3.1 and now can run.
you can solve it as follows tmp = buf[start:start+num_w] tmp = tmp.view(conv_model.weight.shape) conv_model.weight.data.copy(tmp)
Hello, i have some questions about the training samplse, can you help me? 'train = ./voc_train.txt' in the 'cfg/metayolo.data', it contains 20 categories, so it contains the novel categories. Should we use 15 base categories instead?
Sorry for troubling you.I follow your instruction and when I run train_meta.py, a runtimeerror occured as follow:![1](https://user-images.githubusercontent.com/60056969/73269908-a7cb7a80-4218-11ea-850e-57ea29b5d1a2.png)
Could you tell me how to solve it?