I am trying to run the code used here: https://github.com/hanzhanggit/StackGAN-v2
OS: Ubuntu 18.04.1 LTS
Python: 2.7 Anaconda
Torch: 1.0.0a0+aa02231(built from source)
NVCC:
premlal@infinity:~/anaconda2/bin$ nvcc --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2018 NVIDIA Corporation Built on Sat_Aug_25_21:08:01_CDT_2018
The error trace is here, and I really don’t know what to do here. Any help with this error will be most appreciated.
Traceback (most recent call last):
File "main.py", line 144, in <module>
algo.train()
File "/home/premlal/StackGAN_V2/code/trainer.py", line 667, in train
self.inception_model, start_count = load_network(self.gpus)
File "/home/premlal/StackGAN_V2/code/trainer.py", line 148, in load_network
inception_model = INCEPTION_V3()
File "/home/premlal/StackGAN_V2/code/model.py", line 18, in __init__
self.model = models.inception_v3()
File "build/bdist.linux-x86_64/egg/torchvision/models/inception.py", line 30, in inception_v3
File "build/bdist.linux-x86_64/egg/torchvision/models/inception.py", line 65, in __init__
RuntimeError: The expanded size of the tensor (3) must match the existing size (864) at non-singleton dimension 3. Target sizes: [32, 3, 3, 3]. Tensor sizes: [864]