I am trying to implement CNN using tensorflow on temporal accelrometer signal.
- I have signal values segmented on every 10ms (200 samples).
- I want to perform 1-D convolution (
- Convolution window size is 20 samples and stride of 1 with 32 features and Valid padding
- I want to apply Max-Pooling with window size of 10 samples
But i am getting errors regarding dimensions of tensors. Any suggestions on how can i set filter size and stride for booth convolution and max-pooling