Using python 3.7.4 after modified np.load(image_path +'CLEVR_dict.npy' , allow_pickle=True, encoding='bytes').item()

[CyberFork]

Traceback (most recent call last): File "main_clevr.py", line 99, in algo.train(imageloader, storyloader, testloader) File "P:\StoryGAN\code\trainer.py", line 100, in train netG, netD_im, netD_st = self.load_networks() File "P:\StoryGAN\code\trainer.py", line 49, in load_networks netG = StoryGAN(self.video_len) File "P:\StoryGAN\code\model.py", line 222, in init self.define_module() File "P:\StoryGAN\code\model.py", line 234, in define_module nn.Linear(ninput, ngf * 4 * 4 / 2, bias=False), File "P:\Python37\lib\site-packages\torch\nn\modules\linear.py", line 72, in init self.weight = Parameter(torch.Tensor(out_features, in_features)) TypeError: new() received an invalid combination of arguments - got (float, int), but expected one of: * (torch.device device) * (torch.Storage storage) * (Tensor other) * (tuple of ints size, torch.device device) didn't match because some of the arguments have invalid types: (float, int) * (object data, torch.device device) didn't match because some of the arguments have invalid types: (float, int)

[yitong91]

The current .npy is saved by python2. There should be some compatibility issue. The easiest solution may be using python 2 to open and see the data structure. Then generate a new .npy file from python 3.

[martinezhermes]

DEPRECATION: Python 2.7 will reach the end of its life on January 1st, 2020. Please upgrade your Python as Python 2.7 won't be maintained after that date.