Notes

I bought my first car last month, on June 15th to be precise! It’s a Subaru Outback Premium 2020, fully loaded, in green metallic color. I spent little time on research this time. I decided to go with Subaru early on because of its insistence on safety before everything else. I initially wanted to buy a used car so as to save on depreciation costs. But when I learnt that there wasn’t a substantial difference between used and new cars for Subaru, I was left to decide between Outback, Forester and Crosstrek. ...

Fastai: Dense blocks use more memory but are a good choice for lower resolution images. In CNNs, you usually double the number of channels whenever you do stride 2. Otherwise, with stride 1, you keep the number of channels the same. (I say usually because I don’t know if this is a universal recommendation.)

Fastai: Res-blocks decrease the bumpiness of the loss landscape, thereby helping in improving results.

Fastai: Unets are useful when the size of your outputs is similar to that of the input. So, any kind of generative modeling such as segmentation or decrappification. They don’t make sense for classification problems. Unets have a downsampling and upsampling path. These parts are also called encoder and decoder respectively. A layer in a neural network is always an affine function, such as a matrix multiplication, followed by a non-linearity, such as a relu.

Run the following to change Git user information globally: git config --global user.name "Ketan Vijayvargiya" git config --global user.email "hi@ketanvijayvargiya.com" To change on a repository level, simply omit the --global flag.

On the AI/Fastai front: If x is a torch.Tensor and x.shape is torch.Size([4, 3, 5]), it means x contains 4 2D matrices with 3 rows and 5 columns. Also, x is 3D matrix, the technical term for which would be a rank-3 tensor. When images are represented using PyTorch tensors, the first dimension corresponds to the number of channels in it. (For e.g., an RGB image will contain 3 channels and, therefore, the first element in the tensor shape will be 3.) Matplotlib’s imshow function expects number of channels at the end and you can modify a tensor to that by applying the permute function.

The following Youtube video reminded me to focus on the more important things in life. Lately, I’ve been worrying too much about non-essential things. I should instead constantly remind myself of what’s essential and reorient my priorities towards that. The video also mentioned how 20% effort leads to 80% result. And often times, I can offload the remaining 20% results to someone else (for some work-related projects) or not do them at all (in personal projects). So, it’d be a good idea to try and identify where to put the first 20% effort in any project. In other words, be effective before efficient.

Revert an environment: Find out the revision number to revert to by running: conda list --revisions. Then revert using: conda install --revision 22.

Pandas: If df2 is a DataFrame, df2['A'] returns a Series whereas both df2[['A']] and df2[['A', 'B']] return a DataFrame. Fastai: Embeddings are indeed created for categorical variables. For example, in the Excel sheet on collaborative filtering, Jeremy had created embeddings for user-ids and movie-ids both of which were categorical variables. Let’s say we do a stride 2 in a CNN. While the output height and width will halve, we still double the number of output channels probably because the output channels detect various features of the images and we care more about capturing those features.

Update one package in an environment: conda update -n pytorch_p36 numpy Update all (which is generally advised): conda update --all