AI and DataScience Reources - USeful

Samples, Reference Architectures & Best Practices : https://github.com/microsoft/AI (Microsoft)

I have listed very import weblinks. Basically these resources and already explained in video as well. Please check out if you want to learn python in depth.

Django RestFramework ViewSet.. Simple way to define Views in DRF.

Standard Error Estimate on Regression Problems in ML

👉🏼👨🏻‍💻
Catalyst is a PyTorch framework developed with the intent of advancing research and development in the domain of deep learning.

🔸 Purpose :
It enables creating deep learning pipelines with just a few lines of code.

🔸 Compatibility
It is compatible with Python 3.6+ and PyTorch 1.3+ versions.

🔸 Other features
It enables creating configuration files for storing the model’s hyperparameters.

It supports some of the best deep learning R&D practices such as Stochastic Weight Averaging (SWA), Ranger optimizer, one-cycle training, fp16 precision, distributed training and so on.

🔸Installation
pip install -U catalyst


Learn more about Deep learning pipelines
🦾🤓

content by (iampython.com - A Python Opensource Community For Tech Practitioners )

GraphQL is a great technology for building APIs and it is very useful for exposing the output from machine learning models and other calculations.

For Freshers - Posted on 10APR2021

https://paypal.rolepoint.com/?shorturl=Um2qk#job/ahBzfnJvbGVwb2ludC1wcm9kchALEgNKb2IYgICo6d3zgQoM


For Experience - Posted on 10APR2021

https://paypal.rolepoint.com/?shorturl=fu2Ok#job/ahBzfnJvbGVwb2ludC1wcm9kchALEgNKb2IYgICotbuoqAsM


For Other Global Paypal opportunities
https://paypal.rolepoint.com/?shorturl=fu2Ok

👉🏼👨🏻‍💻 🔸 Cardea, a software system built by researchers and software engineers at MIT's Data to AI Lab (DAI Lab)
One-stop machine learning platform turns health care data into insights

Github Link :
https://github.com/MLBazaar/Cardea

Django Rest-framework (Half the way to go)


Code
https://github.com/iampython-team/DjangoRestFramework

Doc
https://github.com/iampython-team/DjangoRestFramework/blob/master/DRF_Doc.pdf

Video Playlist
https://youtube.com/playlist?list=PLw945x_O7SHqseUNT1V_6EpKlon-mxylb

👉Alternative for Keras ::

⚡️TFLearn.
⚡️Knet.
⚡️Clarifai.
⚡️DeepPy.
⚡️Torch.
⚡️NVIDIA Deep Learning GPU Training System (DIGITS)
⚡️RustNN.


👨‍🎤⛄️❄️🐋💁🏻‍♂️🙅🏼‍♀️

Hello Python Developers !!!

Next week, we'll reach 300,000 projects in the pypi package index.

That's up from 200,000 on 14 Oct 2019 and 100,000 on 4 Mar 2017.

What is your prediction for when we'll reach 400,000?

Current project Count : 299,092 projects

If your machine learning model is 99% correct, something is wrong

Possible reasons:

⚡️Wrong evaluation metric
⚡️Bad validation set
⚡️Overfitting
⚡️Leakage

⚡️Accepted data as "objective" or "authoritative"

⚡️you're accidentally using 100% of the training set as your test set

⚡️You just don't understand your data.

⚡️Model is clearly memorizing data. Could be that number of features being used is more than the number of data points?

⚡️Forget that all data are shaped through human intervention at many stages

we need to understand saving trained ML model in different formats