Greating,
I've searched it everywhere on YouTube, Google and also read some articles and research papers but can't seem to find the exact answer to my questions
I've few questions regarding CONVOLUTIONAL NEURAL NETWORK, I'm confused with this question: why do we use MaxPooling size 2x2 why don't we use any other size like 3x3, 4x4 ... nxn(of course less than the size of input) and can we even use any other than 2x2? And my other question is that: why do we always use MaxPooling most of the times? Does it depend on the images? For example if we have some noisy images then would it be suitable to use MaxPooling or should we use any other type of pooling?
Thank you!
MaxPool2D downsamples its input along its spatial dimensions (height and width) by taking the maximum value over an input window (of size defined by pool_size) for each channel of the input. For example, if I apply 2x2 MaxPooling2D on this array:
array = np.array([
[[5],[8]],
[[7],[2]]
])
Then the result would be 8, which is the maximum value of an element in this array.
Another example, if I apply a 2x2 MaxPooling2D on this array:
array = tf.constant([[[1.], [2.], [3.]],
[[4.], [5.], [6.]],
[[7.], [8.], [9.]]])
Then the output would be this:
([
[[5.], [6.]],
[[8.], [9.]]
])
What MaxPooling2D did here is that it slided a 2x2 window and took the maximum value of it, resulting in halving the dimension of the input array along both its height and width. If you still have any problem how this works, check this from keras and this from SO
Now that it is clear that MaxPool2D downsamples the input, let's get back to your question-
Why is a 2x2 MaxPooling used everywhere and not 3x3 or 4x4?
Well, the reason is that it reduces the data, applying a 3x3 MaxPooling2D on a matrix of shape (3,3,1) would result in a (1,1,1) matrix, and applying a 2x2 MaxPooling2D on a matrix of shape (3,3,1) would result in a (2,2,1) matrix. Obviously (2,2,1) matrix can keep more data than a matrix of shape (1,1,1). Often times, applying a MaxPooling2D operation with a pooling size of more than 2x2 results in a great loss of data, and so 2x2 is a better option to choose. This is why, you see 2x2 MaxPooling2D 'everywhere', like in ResNet50, VGG16 etc.
I've recently read the RetinaNet paper and I have yet to understood one minor detail:
We have the multi-scale feature maps obtained from the FPN (P2,...P7).
Then the two FCN heads (the classifier head and regessor head) are convolving each one of the feature maps.
However, each feature map has different spatial scale, so, how does the classifier head and regressor head maintain fixed output volumes, given all their convolution parameters are fix? (i.e. 3x3 filter with stride 1, etc).
Looking at this line at PyTorch's implementation of RetinaNet, I see the heads just convolve each feature and then all features are stacked somehow (the only common dimension between them is the Channel dimension which is 256, but spatially they are double from each other).
Would love to hear how are they combined, I wasn't able to understand that point.
After the convolution at each pyramid step, you reshape the outputs to be of shape (H*W, out_dim) (with out_dim being num_classes * num_anchors for the class head and 4 * num_anchors for the bbox regressor).
Finally, you can concatenate the resulting tensors along the H*W dimension, which is now possible because all the other dimensions match, and compute losses as you would on a network with a single feature layer.
So, I'm trying to learn fixed vector representations for segments of about 200 songs (~ 3-5 minutes per song) and wanted to use an LSTM-based Sequence-to-sequence Autoencoder for it.
I'm preprocessing the audio (using librosa) as follows:
I'm first just getting a raw audio signal time series of shape around (1500000,) - (2500000,) per song.
I'm then slicing each raw time series into segments and getting a lower-level mel spectrogram matrix of shape (512, 3000) - (512, 6000) per song. Each of these (512,) vectors can be referred to as 'mini-songs' as they represent parts of the song.
I vertically stack all these mini-songs of all the songs together to create the training data (let's call this X). X turns out to be (512, 600000) in size, where the first dimension (512) is the window size and the second dimension (600000) is the total number of 'mini-songs' in the dataset.
Which is to say, there are about 600000 mini-songs in X - each column in X represents a mini-song of length (512,).
Each of these (512,) mini-song vectors should be encoded into a (50,) vector per mini-song i.e. we will have 600000 (50,) vectors at the end of the process.
In more standard terminology, I have 600000 training samples each of length 512. [Think of this as being similar to an image dataset - 600000 images, each of length 784, where the images are of resolution 32x32. Except in my case I want to treat the 512-length samples as sequences that have temporal properties.]
I read the example here and was looking to extend that for my use case. I was wondering what the timesteps and input_dim parameters to the Input layer should be set to.
I'm setting timesteps = X.shape[0] (i.e. 512 in this case) and input_dim = X.shape[1] (i.e 600000). Is this the correct way to go about it?
Edit: Added clarifications above.
Your input is actually a 1D sequence not a 2D image.
The input tensor will be (600000, 512, 1) and you need to set the input_dim to 1 and the timesteps to 512.
The shape input does not take the first dimension of the tensor (i.e. 600000 in your case).
The Keras tutorial gives the following code example (with comments):
# apply a convolution 1d of length 3 to a sequence with 10 timesteps,
# with 64 output filters
model = Sequential()
model.add(Convolution1D(64, 3, border_mode='same', input_shape=(10, 32)))
# now model.output_shape == (None, 10, 64)
I am confused about the output size. Shouldn't it create 10 timesteps with a depth of 64 and a width of 32 (stride defaults to 1, no padding)? So (10,32,64) instead of (None,10,64)
In k-Dimensional convolution you will have a filters which will somehow preserve a structure of first k-dimensions and will squash the information from all other dimension by convoluting them with a filter weights. So basically every filter in your network will have a dimension (3x32) and all information from the last dimension (this one with size 32) will be squashed to a one real number with the first dimension preserved. This is the reason why you have a shape like this.
You could imagine a similar situation in 2-D case when you have a colour image. Your input will have then 3-dimensional structure (picture_length, picture_width, colour). When you apply the 2-D convolution with respect to your first two dimensions - all information about colours will be squashed by your filter and will no be preserved in your output structure. The same as here.
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])