Lecture 4 - Image Classification with Convolutional Neural Networks

Livestream Link: https://www.youtube.com/watch?v=TN9fMYQxw4E

Lecture Timing: June 13 (Sat), 8.30 AM PST/9:00 PM IST

Notebooks & References:

What to do after the lecture?

Asking/Answering Questions :
Reply on this thread to ask questions during and after the lecture. Before asking, scroll through the thread and check if your question (or a similar one) is already present. If yes, just like it. During the lecture, we’ll answer 8-10 questions with the most likes. The rest will be answered on the forum. If you see a question you know the answer to, please post your answer as a reply to that question. Let’s help each other learn!


A post was split to a new topic: Is it better to convert color images into black and white?

Hello, I did not formally register, but I have submitted assignments 1-3, and plan to submit the remaining ones. Will I still get a certificate at the end?

Depends on what your goal is and what is the scenario.

  • Color are better for results.
  • B/W for speed and if color is not helping in any way.

Yes, since you’re completing the assignments.


@PrajwalPrashanth Please explain about conv2d and conv3d layers specifically and when to use one ?
Also can you through the documentation of this https://pytorch.org/docs/master/generated/torch.nn.Conv2d.html so that we learn how to learn to read this kind of math extensive documentation.

Conv2d - For images
Conv3d - For videos


This is tough :sweat_smile: i always use google to find blogs, videos to explain them in simple words.

Visualization are great tools to understand.


5 posts were split to a new topic: How significant it is to add non-linearity in a Deep Learning model?

Okay, but these blogs doesn’t help that much to me.

1 Like

Regarding the kaggle competition:

  1. Is there any way to “commit” the local notebook into kaggle?
  2. How to download the dataset to run it locally? I see there’s an option for “Download all” but does kaggle provide some sort of API to download it directly in notebook?

Yes, this https://github.com/Kaggle/kaggle-api contains all the information that you have asked and more.

1 Like

can we use:

    classes = ( "../train") # since we set path to data dir

instead of:

classes = os.listdir(data_dir + "/train")


Why the Featured Blogs is not there?
Missing :upside_down_face:

1 Like

I am not sure to understand this notation:


What is this star for?

2 posts were split to a new topic: What does the random_seed function do?

do we have to install the data each time we ran, is there a way to know and use the already existing dataset created in the kaggle.

How should we select the hyperparameters?
Is there a method of selecting them, or are those completely arbitrary?

My questions so far:

  1. What is a feed forward neural network?
  2. How can I turn off other running notebooks in Kaggle if I get the error message “only one notebook instance” ?

Can you explain how do we decide the parameters using in permute? For example, which dimension causes the image blur in the code ‘img.permute(1, 2, 0)’, thanks

1 Like