DeepLearningImplementations/Colorful Error when I try to train on dataset generated by images with dimension greater than 64x64

[JulienCriss]

Hello @tdeboissiere ,

I can not train with a dataset generated from 68x68 images dimensions or other dimenisions like 128x128. The only dimension that works it is 64x64, with other dimensions it gives me this error:

**Traceback (most recent call last): File "C:\Anaconda3\envs\py35\lib\site-packages\theano\compile\function_module.py", line 884, in call self.fn() if output_subset is None else\ ValueError: GpuReshape: trying to reshape an array of total size 5769216 into an array of total size 2894624.

During handling of the above exception, another exception occurred:

ValueError: GpuReshape: trying to reshape an array of total size 5769216 into an array of total size 2894624. Apply node that caused the error: GpuReshape{2}(GpuElemwise{add,no_inplace}.0, TensorConstant{[9248 313]}) Toposort index: 1562 Inputs types: [GpuArrayType(float32, (False, False, False, False)), TensorType(int32, vector)] Inputs shapes: [(2, 36, 256, 313), (2,)] Inputs strides: [(11538432, 320512, 1252, 4), (4,)] Inputs values: ['not shown', array([9248, 313])] Outputs clients: [[InplaceGpuDimShuffle{0,1,x,x}(GpuReshape{2}.0)]]**

I have as backend Theano and I use the GPU to train.

[tdeboissiere]

Hi,

the error message is, as you've noted, a reshape error. 3 options:

• At some point, you feed inputs of unexpected dimension
• Your image dimensions are not supported (I'd assume it would work for at least 32x32 and 64x64, check the model architecture with keras' graphviz for other image inputs)
• There is a bug somewhere in my code

I'm pretty sure you'll find the error in the first 2 points. To solve it, just adapt the convolutions and upsampling/downsampling to your image.