alfo5123 / variational-sparse-coding Goto Github PK

python train-vsc.py --dataset mnist --epochs 20 --report-interval 4 --lr 0.001 --alpha 0.2 --hidden-size 2000,2000 --latent-size 800

VSC Baseline Experiments

Using cuda device...
Loading mnist dataset...
Done!

Traceback (most recent call last):
  File "train-vsc.py", line 31, in <module>
    args.normalize)
TypeError: __init__() missing 1 required positional argument: 'flatten'

python train-vae.py --dataset mnist --epochs 500 --report-interval 50 --lr 0.01

VAE Baseline Experiments

Using cuda device...
Loading mnist dataset...
Done!

Traceback (most recent call last):
  File "train-vae.py", line 30, in <module>
    normalize=args.normalize)
  File "/home/xd/project/Variational-Sparse-Coding/src/models/vae.py", line 58, in __init__
    self.model = VAE(self.input_sz, self.hidden_sz, latent_sz).to(device)
  File "/home/xd/project/Variational-Sparse-Coding/src/models/vae.py", line 15, in __init__
    self.fc1 = nn.Linear(input_sz, hidden_szs[0])
  File "/home/xd/anaconda3/envs/vsc/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 72, in __init__
    self.weight = Parameter(torch.Tensor(out_features, in_features))
TypeError: new(): argument 'size' must be tuple of ints, but found element of type tuple at pos 2