wlufy

The output shape of PSPNet is `(batch, class_num, h, w)`. Now i want to get the feature(one vector) of every class. What shuold i do to get it? Thanks!

``` targets = np.zeros((len(captions), max_sentence_num + 1, max_word_num)) prob = np.zeros((len(captions), max_sentence_num + 1)) ``` When i read the dataset code, i found that the second dim of this two...

hi, thanks for you share the code! I'm a little confused about the shortcut connection: You add the source features to the sub-layer outputs, it seems that the V’ shape...

hi, i meet the error when i use multi gpus. `RuntimeError: Expected tensor for argument #1 'input' to have the same device as tensor for argument #2 'weight'; but device...