'is convolution kernel size of 1 meaningful?

I have time series data of 32x32 size and I used sliding window to form a 3d array of timestepsx32x32. So my input are shape of (batchsize x timesteps x 32 x 32)

I tried a (1,3,3) conv3d filter and a (3,3) timedistributed conv2d filter separately. The performance is different.

Can I say that a convolution kernel of size 1 can extract features? what's the difference between these 2 kernels?

deep-learning conv-neural-network

Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution	Source

'is convolution kernel size of 1 meaningful?

Sources

Related Questions