MADE

MADE copied to clipboard

I am having trouble understanding your loss function defined [here]() as: ``` pre_output = self.layers[-1].lin_output log_prob = -T.sum(T.nnet.softplus(-target * pre_output + (1 - target) * pre_output), axis=1) loss = (-log_prob).mean()...

dkirkby

TypeError: Cannot convert Type TensorType(float32, matrix) (of Variable Subtensor{int64:int64:}.0) into Type TensorType(float64, matrix). You can try to manually convert Subtensor{int64:int64:}.0 into a TensorType(float64, matrix).

3

I just tried to run your code like the example in the README file: nobody:MADE-ICML2015 apple$ python -u trainMADE.py dna 1e-5 0.95 -1 -1 Full 300 100 30 False 0...

hatimuradin

ValueError: ('object too deep for desired array', 'Container name "mean_square_grad_b0"')

1

ubgpu@ubgpu:~/github/MADE$ sudo python -u trainMADE.py --name mnist_from_paper binarized_mnist 0.01 0 -1 32 Full 300 100 30 False 0 adagrad 0 [8000,8000] 1234 False Output False hinge Orthogonal 0 Using gpu...

andyyuan78