Capsule Networks - Facial Expression Recognition - machine-learning

I want to experiment Capsule Networks on FER. For now I am using fer2013 Kaggle dataset.
One thing that I didn't understand in Capsule Net was in the first conv layer, size was reduced to 20x20 - having input image as 28x28 and filters as 9x9 with 1 stride. But in the capsules, the size reduces to 6x6. How did this happen? Because with input size as 20x20 and filters as 9x9 and 2 strides, I couldn't get 6x6. Maybe I missed something.
For my experiment, input size image is 48x48. Should I use the same hyperparams for the start or is there any suggested hyperparams that I can use?

At the beginning, the picture is 28*28 and you apply a kernel of size 9, so you lose (9-1) pixels. (4 for each side). So at the end of the first convolutional layer, you have (28-8)*(28-8)=20*20 pixels, and you apply the same kernel, so again, (20-8)*(20-8)=12*12. But for the second layer the stride is 2, so there is only 12/2=6 pixels left.
With 48*48 pixel, if you apply the same convolutional layer, you will have at the end 16*16 picture. ((48-8-8)/2)

Standard Capsnet has two convolution layers. the first one has stride of 1 and the second one has 2.
if you want to have 6*6 capsule numbers, your filter size should be 19*19.
because:
48 - (19-1) = 30
30 - (19-1) = 12
12 / 2 = 6 (because stride is 2)

Related

What are Octaves and Sub levels in KAZE and AKAZE?

I am having a hard time trying to understand the Octaves and Sub-levels in the Non-Linear Scale space (KAZE and AKAZE). For the SIFT- Octaves is a collection of same sized images and sub-level is number of gaussian blurred images to be generated in the octave. How can this be explained in KAZE and AKAZE?
I want to tune the parameters and so need to understand this properly.
The octaves are the number of scale levels. 4 octaves means scales of 1, 1/2, 1/4, 1/8.
The octave layers are the number of diffusion layers per octave. Diffusion is the change in luminance of an image that is farther away. It can be (and it is) aproximated by some gaussian blur.
See the original AKAZE paper for more details:
http://www.robesafe.com/personal/pablo.alcantarilla/papers/Alcantarilla13bmvc.pdf
See figure 2 in this paper, for a representation of the image pyramid:
http://tulipp.eu/wp-content/uploads/2019/03/2017_TUD_HEART_kalms.pdf

MNIST hidden layer intuitive understanding

For the simplest MNIST solution with 1 hidden layer, can I understand the number of hidden neurons as how many parts we divide the inputs?
For example: [784,30,10]
Can I say I divide 784 pixels into 30 small images (784/30 pixels in each image) then do the calculation?
Thanks!
I'm not entirely sure what you mean. If you have a network that is layered like [784, 30, 10], you have 784 input neurons, 30 hidden neurons and 10 output neurons. The neurons don't know anything about 'pixels', they are just parameters. The network is basically calculating 30 values from the first input, and the output calculates 10 values from the previous 30 values.
Can I say I divide 784 pixels into 30 small images (784/30 pixels in each image) then do the calculation?
No, as a neuron is not an image.

Why was the convolution layer in the VGG16 network 64? And how was it determined?

Can someone please explain to me why the width of the VGG16 network is 64 in the first convolutional layer? I understand that the layers double in size along the network but I am not sure how 64 was determined in the beginning.
The input to the first convolutional layer in VGG16 is an image with size 224x224x3. The output volume of the first convolutional layer has the shape 224x244x64 (x3 for each channel in the input image). The value 64 is the depth (or channels - in the paper they call it width which is confusing IMO) of the new volume as the result of the convolution operation on each of the 64 filters over the input volume (image) - think of each filter stacking a new layer onto the volume. The choice of 64 filters in conv1_1 was a design decision that they don't explain but is related to managing the number of trainable parameters.
The doubling of the number of filters (64, 128, 256 ...) is also a design decision. Some people say that a rule of thumb is to increase the number of filters by the inverse of the multiplier in the downsampling operation of the pooling layer. In the VGG16 architecture they use a stride of 2 in their pooling layer. Therefore they roughly downsample the WxH of the input volume by 50% according to this rough equation (width and height are equal):
Widthoutput = ( Widthinput − FilterSize + 2*Padding ) / Stride +1
In VGG16 pool1 output:
Widthoutput = ( 224 − 3 + 2*0 ) / 2 +1 = 111.5 ≅ 112
Pooling downsamples by 50% (224/2), so lets double the filters in the next convolutional layer (64*2)

About max-pooling?

Max-pooling is useful in vision for two reasons:
By eliminating non-maximal values, it reduces computation for upper
layers.
It provides a form of translation invariance. Imagine cascading a
max-pooling layer with a convolutional layer. There are 8 directions
in which one can translate the input image by a single pixel. If
max-pooling is done over a 2x2 region, 3 out of these 8 possible
configurations will produce exactly the same output at the
convolutional layer. For max-pooling over a 3x3 window, this jumps to
5/8.
Since it provides additional robustness to position, max-pooling is a
“smart” way of reducing the dimensionality of intermediate
representations.
I can't understand, what does 8 directions mean? And what does
"If max-pooling is done over a 2x2 region, 3 out of these 8 possible
configurations will produce exactly the same output at the
convolutional layer. For max-pooling over a 3x3 window, this jumps to
5/8."
mean?
There are 8 directions in which one can translate the input image by a single pixel.
They are considering 2 horizontal, 2 vertical and 4 diagonal 1-pixel shifts. That gives 8 in total.
If max-pooling is done over a 2x2 region, 3 out of these 8 possible configurations will produce exactly the same output at the convolutional layer. For max-pooling over a 3x3 window, this jumps to 5/8.
Imagine we are taking the maximum value in a 2x2 region of an image. The image is pre-convolved, though it doesn't matter for the purpose of this explanation.
No matter where exactly in a 2x2 region the maximum value resides, there will be 3 possible 1-pixel translations of the image that result in the maximum value remaining in that particular 2x2 region. Of course an even greater value may be brought from a neighbouring region, but that's beside the point. The point is you get some translation invariance.
With a 3x3 region it gets more complex, as the number of 1-pixel translations that keep the maximum value within the region depends on where exactly in the region that maximum value resides. The 5 translations they mention correspond to a location in the middle of an edge in a 3x3 pixel block. A corner location will give 3 translations, while the center one will give all 8.

What is Depth of a convolutional neural network?

I was taking a look at Convolutional Neural Network from CS231n Convolutional Neural Networks for Visual Recognition. In Convolutional Neural Network, the neurons are arranged in 3 dimensions(height, width, depth). I am having trouble with the depth of the CNN. I can't visualize what it is.
In the link they said The CONV layer's parameters consist of a set of learnable filters. Every filter is small spatially (along width and height), but extends through the full depth of the input volume.
For example loook at this picture. Sorry if the image is too crappy.
I can grasp the idea that we take a small area off the image, then compare it with the "Filters". So the filters will be collection of small images? Also they said We will connect each neuron to only a local region of the input volume. The spatial extent of this connectivity is a hyperparameter called the receptive field of the neuron. So is the receptive field has the same dimension as the filters? Also what will be the depth here? And what do we signify using the depth of a CNN?
So, my question mainly is, if i take an image having dimension of [32*32*3] (Lets say i have 50000 of these images, making the dataset [50000*32*32*3]), what shall i choose as its depth and what would it mean by the depth. Also what will be the dimension of the filters?
Also it will be much helpful if anyone can provide some link that gives some intuition on this.
EDIT:
So in one part of the tutorial(Real-world example part), it says The Krizhevsky et al. architecture that won the ImageNet challenge in 2012 accepted images of size [227x227x3]. On the first Convolutional Layer, it used neurons with receptive field size F=11, stride S=4 and no zero padding P=0. Since (227 - 11)/4 + 1 = 55, and since the Conv layer had a depth of K=96, the Conv layer output volume had size [55x55x96].
Here we see the depth is 96. So is depth something that i choose arbitrarily? or something i compute? Also in the example above(Krizhevsky et al) they had 96 depths. So what does it mean by its 96 depths? Also the tutorial stated Every filter is small spatially (along width and height), but extends through the full depth of the input volume.
So that means the depth will be like this? If so then can i assume Depth = Number of Filters?
In Deep Neural Networks the depth refers to how deep the network is but in this context, the depth is used for visual recognition and it translates to the 3rd dimension of an image.
In this case you have an image, and the size of this input is 32x32x3 which is (width, height, depth). The neural network should be able to learn based on this parameters as depth translates to the different channels of the training images.
UPDATE:
In each layer of your CNN it learns regularities about training images. In the very first layers, the regularities are curves and edges, then when you go deeper along the layers you start learning higher levels of regularities such as colors, shapes, objects etc. This is the basic idea, but there lots of technical details. Before going any further give this a shot : http://www.datarobot.com/blog/a-primer-on-deep-learning/
UPDATE 2:
Have a look at the first figure in the link you provided. It says 'In this example, the red input layer holds the image, so its width and height would be the dimensions of the image, and the depth would be 3 (Red, Green, Blue channels).' It means that a ConvNet neuron transforms the input image by arranging its neurons in three dimeonsion.
As an answer to your question, depth corresponds to the different color channels of an image.
Moreover, about the filter depth. The tutorial states this.
Every filter is small spatially (along width and height), but extends through the full depth of the input volume.
Which basically means that a filter is a smaller part of an image that moves around the depth of the image in order to learn the regularities in the image.
UPDATE 3:
For the real world example I just browsed the original paper and it says this : The first convolutional layer filters the 224×224×3 input image with 96 kernels of size 11×11×3 with a stride of 4 pixels.
In the tutorial it refers the depth as the channel, but in real world you can design whatever dimension you like. After all that is your design
The tutorial aims to give you a glimpse of how ConvNets work in theory, but if I design a ConvNet nobody can stop me proposing one with a different depth.
Does this make any sense?
Depth of CONV layer is number of filters it is using.
Depth of a filter is equal to depth of image it is using as input.
For Example: Let's say you are using an image of 227*227*3.
Now suppose you are using a filter of size of 11*11(spatial size).
This 11*11 square will be slided along whole image to produce a single 2 dimensional array as a response. But in order to do so, it must cover every aspect inside of 11*11 area. Therefore depth of filter will be depth of image = 3.
Now suppose we have 96 such filter each producing different response. This will be depth of Convolutional layer. It is simply number of filters used.
I'm not sure why this is skimped over so heavily. I also had trouble understanding it at first, and very few outside of Andrej Karpathy (thanks d00d) have explained it. Although, in his writeup (http://cs231n.github.io/convolutional-networks/), he calculates the depth of the output volume using a different example than in the animation.
Start by reading the section titled 'Numpy examples'
Here, we go through iteratively.
In this case we have an 11x11x4. (why we start with 4 is kind of peculiar, as it would be easier to grasp with a depth of 3)
Really pay attention to this line:
A depth column (or a fibre) at position (x,y) would be the activations
X[x,y,:].
A depth slice, or equivalently an activation map at depth d
would be the activations X[:,:,d].
V[0,0,0] = np.sum(X[:5,:5,:] * W0) + b0
V is your output volume. The zero'th index v[0] is your column - in this case V[0] = 0 this is the first column in your output volume.
V[1] = 0 this is the first row in your output volume. V[3]= 0 is the depth. This is the first output layer.
Now, here's where people get confused (at least I did). The input depth has absolutely nothing to do with your output depth. The input depth only has control of the filter depth. W in Andrej's example.
Aside: A lot of people wonder why 3 is the standard input depth. For color input images, this will always be 3 for plain ole images.
np.sum(X[:5,:5,:] * W0) + b0 (convolution 1)
Here, we are calculating elementwise between a weight vector W0 which is 5x5x4. 5x5 is an arbitrary choice. 4 is the depth since we need to match our input depth. The weight vector is your filter, kernel, receptive field or whatever obfuscated name people decide to call it down the road.
if you come at this from a non python background, that's maybe why there's more confusion since array slicing notation is non-intuitive. The calculation is a dot product of your first convolution size (5x5x4) of your image with the weight vector. The output is a single scalar value which takes the position of your first filter output matrix. Imagine a 4 x 4 matrix representing the sum product of each of these convolution operations across the entire input. Now stack them for each filter. That shall give you your output volume. In Andrej's writeup, he starts moving along the x axis. The y axis remains the same.
Here's an example of what V[:,:,0] would look like in terms of convolutions. Remember here, the third value of our index is the depth of your output layer
[result of convolution 1, result of convolution 2, ..., ...]
[..., ..., ..., ..., ...]
[..., ..., ..., ..., ...]
[..., ..., ..., result of convolution n]
The animation is best for understanding this, but Andrej decided to swap it with an example that doesn't match the calculation above.
This took me a while. Partly because numpy doesn't index the way Andrej does in his example, at least it didn't I played around with it. Also, there's some assumptions that the sum product operation is clear. That's the key to understand how your output layer is created, what each value represents and what the depth is.
Hopefully that helps!
Since the input volume when we are doing an image classification problem is N x N x 3. At the beginning it is not difficult to imagine what the depth will mean - just the number of channels - Red, Green, Blue. Ok, so the meaning for the first layer is clear. But what about the next ones? Here is how I try to visualize the idea.
On each layer we apply a set of filters which convolve around the input. Lets imagine that currently we are at the first layer and we convolve around a volume V of size N x N x 3. As #Semih Yagcioglu mentioned at the very beginning we are looking for some rough features: curves, edges etc... Lets say we apply N filters of equal size (3x3) with stride 1. Then each of these filters is looking for a different curve or edge while convolving around V. Of course, the filter has the same depth, we want to supply the whole information not just the grayscale representation.
Now, if M filters will look for M different curves or edges. And each of these filters will produce a feature map consisting of scalars (the meaning of the scalar is the filter saying: The probability of having this curve here is X%). When we convolve with the same filter around the Volume we obtain this map of scalars telling us where where exactly we saw the curve.
Then comes feature map stacking. Imagine stacking as the following thing. We have information about where each filter detected a certain curve. Nice, then when we stack them we obtain information about what curves / edges are available at each small part of our input volume. And this is the output of our first convolutional layer.
It is easy to grasp the idea behind non-linearity when taking into account 3. When we apply the ReLU function on some feature map, we say: Remove all negative probabilities for curves or edges at this location. And this certainly makes sense.
Then the input for the next layer will be a Volume $V_1$ carrying info about different curves and edges at different spatial locations (Remember: Each layer Carries info about 1 curve or edge).
This means that the next layer will be able to extract information about more sophisticated shapes by combining these curves and edges. To combine them, again, the filters should have the same depth as the input volume.
From time to time we apply Pooling. The meaning is exactly to shrink the volume. Since when we use strides = 1, we usually look at a pixel (neuron) too many times for the same feature.
Hope this makes sense. Look at the amazing graphs provided by the famous CS231 course to check how exactly the probability for each feature at a certain location is computed.
In simple terms, it can explain as below,
Let's say you have 10 filters where each filter is the size of 5x5x3. What does this mean? the depth of this layer is 10 which is equal to the number of filters. Size of each filter can be defined as we want e.g., 5x5x3 in this case where 3 is the depth of the previous layer. To be precise, depth of each filer in the next layer should be 10 ( nxnx10) where n can be defined as you want like 5 or something else. Hope will make everything clear.
The first thing you need to note is
receptive field of a neuron is 3D
ie If the receptive field is 5x5 the neuron will be connected to 5x5x(input depth) number of points. So whatever be your input depth, one layer of neurons will only develop 1 layer of output.
Now, the next thing to note is
depth of output layer = depth of conv. layer
ie The output volume is independent of the input volume, and it only depends on the number filters(depth). This should be pretty obvious from the previous point.
Note that the number of filters (depth of the cnn layer) is a hyper parameter. You can take it whatever you want, independent of image depth. Each filter has it's own set of weights enabling it to learn a different feature on the same local region covered by the filter.
The depth of the network is the number of layers in the network. In the Krizhevsky paper, the depth is 9 layers (modulo a fencepost issue with how layers are counted?).
If you are referring to the depth of the filter (I came to this question searching for that) then this diagram of LeNet is illustrating
Source http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf
How to create such a filter; Well in python like https://github.com/alexcpn/cnn_in_python/blob/main/main.py#L19-L27
Which will give you a list of numpy arrays and length of the list is the depth
Example in the code above,but adding a depth of 3 for color (RGB), the below is the network. The first Convolutional layer is a filter of shape (5,5,3) and depth 6
Input (R,G,B)= [32.32.3] *(5.5.3)*6 == [28.28.6] * (5.5.6)*1 = [24.24.1] * (5.5.1)*16 = [20.20.16] *
FC layer 1 (20, 120, 16) * FC layer 2 (120, 1) * FC layer 3 (20, 10) * Softmax (10,) =(10,1) = Output
In Pytorch
np.set_printoptions(formatter={'float': lambda x: "{0:0.2f}".format(x)})
# Generate a random image
image_size = 32
image_depth = 3
image = np.random.rand(image_size, image_size)
# to mimic RGB channel
image = np.stack([image,image,image], axis=image_depth-1) # 0 to 2
image = np.moveaxis(image, [2, 0], [0, 2])
print("Image Shape=",image.shape)
input_tensor = torch.from_numpy(image)
m = nn.Conv2d(in_channels=3,out_channels=6,kernel_size=5,stride=1)
output = m(input_tensor.float())
print("Output Shape=",output.shape)
Image Shape= (3, 32, 32)
Output Shape= torch.Size([6, 28, 28])

Resources