Closed c1a1o1 closed 5 years ago
I never saw this error. Can you provide more information such as 1) which command did you run? 2) which version of python, numpy, pytorch are you using?
--img_size 128 --shortcut_layers 1 --inject_layers 1 --experiment_name 128_shortcut1_inject1_none --gpu pytorch 0.4.1
I cannot reproduce your error. I'm using python 3 and pytorch 0.4.1. The following is my pip3 list
.
Package Version
--------------- -----------
cloudpickle 0.8.0
cycler 0.10.0
dask 1.1.4
decorator 4.3.2
kiwisolver 1.0.1
matplotlib 3.0.3
networkx 2.2
numpy 1.16.2
Pillow 5.4.1
pip 19.0.3
protobuf 3.7.0
pyparsing 2.3.1
python-dateutil 2.8.0
PyWavelets 1.0.2
PyYAML 3.13
scikit-image 0.14.2
scipy 1.2.1
setuptools 40.8.0
six 1.12.0
tensorboardX 1.6
toolz 0.9.0
torch 0.4.1
torchvision 0.2.2.post3
tqdm 4.31.1
wheel 0.33.1
Or perhaps you didn't create the correct dataset: data/img_align_celeba/*.jpg
and data/list_attr_celeba.txt
.
I also have the same problem. Does the landlord solve it?
Traceback (most recent call last): File "F:/humanpose/AttGAN-PyTorch-master/train.py", line 121, in
fixed_img_a, fixed_att_a = next(iter(valid_dataloader))
File "E:\Users\Raytine\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 314, in next
batch = self.collate_fn([self.dataset[i] for i in indices])
File "E:\Users\Raytine\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 314, in
batch = self.collate_fn([self.dataset[i] for i in indices])
File "F:\humanpose\AttGAN-PyTorch-master\data.py", line 46, in getitem
att = torch.tensor((self.labels[index] + 1) // 2)
TypeError: can't convert np.ndarray of type numpy.int32. The only supported types are: double, float, float16, int64, int32, and uint8.