cs231n | My solutions to cs231n course

This might come across as a seriously newbie question, but I have not many options as I am not sure which direction I should be heading.

Now I am studying Deep Learning frequently and I want to toy around with Stanford's CS231N's Convolutional Neural Network Demo as I find it extremely user friendly. The visuals are embedded in this website. I really want to toy around with this but I do not know how and where to start.

I have knowledge of Python and VS-Code if that helps.

I'm trying to do it by myself the assignments from Stanford CS231n 2017 CNN course.

I'm trying to compute L2 distance using only matrix multiplication and sum broadcasting with Numpy. L2 distance is:

And I think I can do it if I use this formula:

The following code shows three methods to compute L2 distance. If I compare the output from the method compute_distances_two_loops with the output from method compute_distances_one_loop, both are equals. But I compare the output from the method compute_distances_two_loops with the output from the method compute_distances_no_loops, where I have implemented the L2 distance using only matrix multiplication and sum broadcasting, they are different.

I have decided to complete cs231 course and do its assignment. I happily watched the first 2 videos of the course and now I had to solve the first assignments. I followed the guidelines step by step which was shown in the video in this link: https://cs231n.github.io/setup-instructions/ Then, when I run the first cell, which is not the cell shown in the video but nonetheless it's in the assignments1 file which I downloaded from their site, I get a nasty error which has paralyzed me four a couple of hours. I'd be happy if anyone could respond. IF you take a look at my picture, you'll see that files are added in the google drive, but surprisingly, it gives an error out of nowhere. Thanks.

===========================================================================

Update: Here is the snapshot of the video provided to guide students how to setup their google colab (in that link).

As you can see, in their vide the first chunk of code specifies their working directory but in the file that they have uploaded as their assignment1, they have not done so!

In the following code written by Karpathy, why do we have this line(Why do we need to compare with the uniform distribution to select an action while the policy function did that)

I'm going through CS231n to understand the basics of neural networks.

Attached is the slide in which Justin (the tutor) gives the reasoning for why data preprocessing is required and I don't completely understand. The explanation given is similar to the one given on the slide and I don't get it. The slide is below.

The second question I have is: is it actually normalisation or standardisation? This link implies that it is standardisation, whereas the course material says it is normalisation.

Any help will be appreciated.

Does Eigen support getting next block with stride =2?

I observed the default behavior is with stride =1 in this:

I run into this problem when implementing the vectorized svm gradient for cs231n assignment1. here is an example:

I'm trying to use scipy's ndimage.convolve function to perform a convolution on a 3 dimensional image (RGB, width, height).

Taking a look here:

It is clear to see that for any input, each kernel/filter should only ever have an output of NxN, with strictly a depth of 1.

This is a problem with scipy, as when you do ndimage.convolve with an input of size (3, 5, 5) and a filter/kernel of size (3, 3, 3), the result of this operation produces an output size of (3, 5, 5), clearly not summing the different channels.

Is there a way to force this summation without manually doing so? I try to do as little in base python as possible, as a lot of external libraries are written in c++ and do the same operations faster. Or is there an alternative?

Let's say input to intermediate CNN layer is of size 512×512×128 and that in the convolutional layer we apply 48 7×7 filters at stride 2 with no padding. I want to know what is the size of the resulting activation map?

I checked some previous posts (e.g., here or here) to point to this Stanford course page. And the formula given there is (W − F + 2P)/S + 1 = (512 - 7)/2 + 1, which would imply that this set up is not possible, as the value we get is not an integer.

However if I run the following snippet in Python 2.7, the code seems to suggest that the size of activation map was computed via (512 - 6)/2, which makes sense but does not match the formula above: