Python_NN
Andrew-NG-Notes
Python_NN | Andrew-NG-Notes | |
---|---|---|
1 | 1 | |
0 | 2,248 | |
- | - | |
0.0 | 0.0 | |
almost 2 years ago | 2 months ago | |
Jupyter Notebook | Jupyter Notebook | |
GNU General Public License v3.0 only | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Python_NN
-
Difficulty in using LSTMs for text generation
About the issue with repeating characters, it is supposed to happen. There are certain loops that repeat. To solve this you must remove the line q1 = np.argmax(p1.cpu(), axis=1)[-1].item() and instead, do sampling based on the softmax probabilities. Check this code where I perform sampling. The vec = vec**(2) is used to decrease randomness you can see how your model works and either keep it or leave it.
Andrew-NG-Notes
What are some alternatives?
Deep-Learning-Computer-Vision - My assignment solutions for Stanford’s CS231n (CNNs for Visual Recognition) and Michigan’s EECS 498-007/598-005 (Deep Learning for Computer Vision), version 2020.
Mathematics-for-Machine-Learning-and-Data-Science-Specialization-Coursera - Mathematics for Machine Learning and Data Science Specialization - Coursera - deeplearning.ai - solutions and notes
machine_learning_complete - A comprehensive machine learning repository containing 30+ notebooks on different concepts, algorithms and techniques.
gdrl - Grokking Deep Reinforcement Learning
fsdl-text-recognizer-2022-labs - Complete deep learning project developed in Full Stack Deep Learning, 2022 edition. Generated automatically from https://github.com/full-stack-deep-learning/fsdl-text-recognizer-2022
DeepNeuralNetworksFromScratch - Different kinds of deep neural networks (DNNs) implemented from scratch using Python and NumPy, with a TensorFlow-like object-oriented API.
strategy-ml-nn - This example shows how to use neural networks for writing a trading system on stocks.
embedml - pytorch like machine learning framework from scratch
Note - Easily implement parallel training and distributed training. Machine learning library. Note.neuralnetwork.tf package include Llama2, Llama3, CLIP, ViT, ConvNeXt, SwiftFormer, etc, these models built with Note are compatible with TensorFlow and can be trained with TensorFlow.
linear-regression-from-scratch - A data science project for part II physics project E (surveying using stars)
Data-Science-Free - Free Resources For Data Science created by Shubham Kumar
gan-vae-pretrained-pytorch - Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch.