3

Then how do each filter differ by? Is it in hovering over the input matrix? Or is it in the values contained by filter itself? Or differs in both hovering and content? The filters (aka kernels) are the learnable parameters of the CNN, in the same way that the weights of the connections between the neurons (or nodes) are the learnable parameters of a multi-...


3

The point is that in the expansive path you have two forms of information: the information from the contracting path, which includes all high-level features extracted from the original image. the information from the skip-connections, which copy a cropped version of the feature maps in the contracting path. Because, as we go forward through the expansive ...


2

For learning image features with CNNs, we use 2D Convolutions. Here 2D does not refer to the input of the operation, but the output. Consider you have an input tensor of size 224 x 224 x 3. Say for example you have 64 different convolution kernels. Theses kernels are also 3 dimensional. Each kernel will produce a 2D matrix as output. Since you have 64 ...


2

The 64 here is the number of filters that are used. The picture is kind of misleading in that it leaves out the transition of the maxpool. Below is a text description of the size of the features as they go through the network with the number of filters in bold. The first 2 layers in the diagram you posted contain 64 3x3 convs resulting in a 224x224x64 ...


2

Only the first convolutional layer, with filters that process the input [colour] channels directly, can be rendered directly as image patches in the same domain as the input. The left-most panel in your example looks like that. Further layers of the neural network cannot be rendered like this for two reasons: They have a number of input channels based on ...


1

The application of 1 kernel (aka filter) to an input (with a 2d convolution) is a matrix (a 2d array), which is often known as a feature map (aka activation map). The application of $k$ kernels to the same input is a 3d array (sometimes called tensor, though this may not be exactly correct, or 3d volume) with depth $k$, i.e. you have $k$ concatenated feature ...


1

All filters move across the same area, but the filter values (also called filter kernels) are different for each filter. This makes it possible to "filter out" different features.


1

In my experience, neural networks with convolutional layers take much much longer to train, so try increasing the number of iterations (time steps). After running, save the network model (I dont know how to do it in torch, but in tensorflow it was model.save("filename"+".h5") ). Then, load this saved model file and do a test run to see if ...


1

The channel sizes 32, 128, etc. are used because of memory and efficiency. There is nothing holy about these numbers. The intuition behind choosing the number of channels is as follows- The initial layers extract low-level features- they consist of edge detectors, etc. There aren't many such features. So, we won't gain much by adding a lot of filters(of ...


1

Yes, in Keras you can apply different strides by giving a tuple/list, specifying the value of strides along the height and width. If you just give a single value the API assumes the same value for all spatial dimensions. You can find the official documentation here In Pytorch, too you can specify the values in a tuple for the stride argument. Link to Pytorch ...


1

Yes, in Keras this is simply implemented by using a tuple for the stride argument of a convolutional layer, with each element of the tuple corresponding to the stride of each dimension.


1

It seems that a similar question has been raised here: https://stackoverflow.com/questions/57438922/different-size-filters-in-the-same-layer-with-tensorflow-2-0 Like answered in the link above, you could combine severall Conv2D ops with different kernel sizes on the same input. You would have to adapt each output with padding, or cropping, so that you could ...


1

Does the next convolutional filter have a depth of 40? So, would the filter dimensions be 3x3x40? Yes. The depth of the next layer $l$ (which corresponds to the number of feature maps) will be 40. If you apply $8$ kernels with a $3\times 3$ window to $l$, then the number of features maps (or the depth) of layer $l+1$ will be $8$. Each of these $8$ kernels ...


Only top voted, non community-wiki answers of a minimum length are eligible