- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I am trying to build a simple CNN with DAAL neural network classes and struggling with a pooling layer.
The model only has two layers, conv layer and pooling layer. With my code, there is no error in compile time and it runs well. But the number of dimensions and values are not correct. My input data is 1x1x28x28 float numbers and filter size in conv layer is 1x5x5. So, I checked the result is sized 1x1x24x24. So far, it works finely. But after going through a max-pooling layer, the number of dimensions becomes 14 instead of 12. Also, the values are just zeros.
Here is the code I wrote. Do you guys have any idea?
float* testData = new float[28*28]; for (int i=0; i < 1; i++) for (int j = 0; j < 28; j++) for (int k = 0; k < 28; k++) testData[i*28*28 + j*28 + k] = float(j) * float(k) + i; size_t nDim = 4, dims[] = {1, 1, 28,28}; SharedPtr<Tensor> bogusData(new HomogenTensor<float>(nDim, dims, (float*)testData)); convolution2d::forward::Batch<> convolution2dLayerForward; maximum_pooling2d::forward::Batch<> pool1(nDim); convolution2dLayerForward.input.set(forward::data, bogusData); convolution2dLayerForward.parameter->kernelSize = convolution2d::KernelSize(5,5); convolution2dLayerForward.parameter->nKernels = 1; convolution2dLayerForward.compute(); // So far, so good. SharedPtr<Tensor> conv1_value; conv1_value = forwardResult->get(forward::value); pool1.input.set(forward::data, conv1_value); pool1.compute(); // Values are strange here.
Thank you.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
1x1x14x14 is output size with default values of padding (2,2).
Pooling layer result tensor has dimensions 1x1x12x12 when layer paddings are set to zeros:
pool1.parameter.padding = pooling2d::Padding(0,0);
Regards,
Daria
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thank you, Daria! I see, I will try without the padding.

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page