May 12

How to run a python code on single CPU?

Using the following command on linux Ubuntu — Using the following command on linux Ubuntu taskset --cpu-list 1-1 python XXX.py

Cpu

1 min read

How to run a python code on single CPU?

Using the following command on linux Ubuntu

taskset --cpu-list 1-1 python XXX.py

Mar 24

MAE is open sourced

The MAE paper from AI research of Meta is open sourced. This paper is interesting as it is the the BERT in CV. — The MAE paper from AI research of Meta is open sourced. This paper is interesting as it is the the BERT in CV. Check it out from HERE if you are interested.

Mae

1 min read

MAE is open sourced

The MAE paper from AI research of Meta is open sourced. This paper is interesting as it is the the BERT in CV.

Check it out from HERE if you are interested.

Mar 14

Awesome Transformer Tutorial and blogs

In this article, I am not summarizing what Transformer is. I am only listing the materials that help me as those materials are really… — In this article, I am not summarizing what Transformer is. I am only listing the materials that help me as those materials are really clear. Blog MUST SEE . It is so clear explained that it can solve most of your problems. Code Nice code from here by Tae-Hwan Jung. …

Transformer

2 min read

Mar 10

How np.random.seed and np.random.randn works

Base on [1]: — Base on [1]: numpy.random.seed(seed=None) This method is called when RandomState is initialized. It can be called again to re-seed the generator. For details, see RandomState. Parameters:seed : int or 1-d array_like, optional Seed for RandomState. Must be convertible to 32 bit unsigned integers. How does it work under the hood? How to use it? For bellow, if we generate a random…

Numpy

3 min read

How np.random.seed and np.random.randn works

Feb 17

Transformer’s Scaled Dot-Product Attention

In the paper transformer, it propose the Scaled Dot-Product Attention: — In the paper transformer, it propose the Scaled Dot-Product Attention: it claims that

Transformer

2 min read

Transformer’s Scaled Dot-Product Attention

In the paper transformer, it propose the Scaled Dot-Product Attention:

it claims that

Feb 16

Python package not found issue

Below are from [1] to help locate the python package location: — Below are from [1] to help locate the python package location: When you install using conda install -c conda-forge folium, the package will be placed in: ./anaconda3/envs/[name env]/lib/python3.7/site-packages/folium When you install using pip (with a anaconda env activated), pip install folium, the package will be placed in: ./anaconda3/lib/python3.7/site-packages/folium

1 min read

Python package not found issue

Below are from [1] to help locate the python package location:

When you install using conda install -c conda-forge folium, the package will be placed in:

./anaconda3/envs/[name env]/lib/python3.7/site-packages/folium

When you install using pip (with a anaconda env activated), pip install folium, the package will be placed in:

./anaconda3/lib/python3.7/site-packages/folium

Reference

[1]https://stackoverflow.com/questions/39811929/package-installed-by-conda-python-cannot-find-it

Jan 26

Cool. Cracking your DL interviewing

Just found a book in arxiv about DL interviewing questions (I did not realize that arxiv can publish such type of book. Pretty interesting… — Just found a book in arxiv about DL interviewing questions (I did not realize that arxiv can publish such type of book. Pretty interesting to know). Well written. Share it here for anyone who want to improve your understanding about the ML/DL concepts or wants to prepare ML interviews.

Deep Learning

1 min read

Cool. Cracking your DL interviewing

Just found a book in arxiv about DL interviewing questions (I did not realize that arxiv can publish such type of book. Pretty interesting to know). Well written. Share it here for anyone who want to improve your understanding about the ML/DL concepts or wants to prepare ML interviews.

Please checkout this article.

Also, one book is not enough. As a DS/MLE/Research Scientist, reading papers will be the only way to learn new ideas as this area is moving forward too fast.

Jan 25

Using Paddlepaddle to recognize flowers

PaddlePaddle is a Chinese based DL framework developped by China’s Google Baidu. If you are interested in exploring this DL framework, here… — PaddlePaddle is a Chinese based DL framework developped by China’s Google Baidu. If you are interested in exploring this DL framework, here is an example of how to use paddlepaddle to train a flower classification model. Install paddlepaddle Following the official instruction, which is pretty clear.

Paddlepaddle

5 min read

Jan 21

A more general modality unspecific representation method: data2vec

Meta’s new paper data2vec — As a member of ML community, especially for NLP professionals, we shold be pretty familar with word2vec. Recently Meta posted a new paper named “data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language”. Based on the abstract, “Instead of predicting modality-specific targets such as words, visual tokens…

Data 2 Vec

5 min read

Jan 19

Two slow and one fast pointer

142. Linked List Cycle II — 142. Linked List Cycle II This problem is cool as we need using several pointers to solve the problem with memory complexity of O(1). Here I am explaining everything in one figure. C++ class Solution { public: ListNode *detectCycle(ListNode *head) {…

Two Pointers

1 min read