https://github.com/yarinbou/deep-learning
basic concepts and tools for image understanding using Deep Learning.
https://github.com/yarinbou/deep-learning
ai attention-mechanism cnn deep-learning encoder-decoder image-captioning image-processing neural-network neural-networks object-localization pretrained-models
Last synced: 2 months ago
JSON representation
basic concepts and tools for image understanding using Deep Learning.
- Host: GitHub
- URL: https://github.com/yarinbou/deep-learning
- Owner: YarinBou
- Created: 2021-11-11T13:21:43.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2022-01-19T11:55:10.000Z (over 3 years ago)
- Last Synced: 2025-05-30T13:38:41.819Z (4 months ago)
- Topics: ai, attention-mechanism, cnn, deep-learning, encoder-decoder, image-captioning, image-processing, neural-network, neural-networks, object-localization, pretrained-models
- Language: Jupyter Notebook
- Homepage:
- Size: 5.98 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Deep-Learning
basic concepts and tools for image understanding using Deep Learning.
## Linear Image Classifier
implement a linear image classifier while getting familiar with `numpy` and the benefits of vectorized operations in Python.
This exercise has 2 parts:
1. Implementing loss functions, calculating gradients and implementing gradient descent.
2. Linear perceptron
3. Training and evaluating several classifiers.
4. Visualize my results.
## Neural network from scratch
implement a binary classifier with one linear layer on a small portion of CIFAR-10. In this exercise, you will implement a three layer multi-class neural network.
1. Implement a loss function (Cross-entropy)
2. Implement a L2 Regularization
3. Implement a Fully Connected Layer: Forward Pass, Backward Pass.
4. Implement a Fully ReLU: Forward Pass, Backward Pass.
5. Building the Network.
## Convolutional Neural Network - Classifiying CIFAR-10
1. Train a convolutional network using PyTorch and evaluate it.
2. Visualize a neural network layer and interpet their meaning.
## Object localization using pre-trained CNN model
1. Train a Localization as Regression network using a pre-trained model.
2. Build and train a recurrent neural network that will generate text.
## Image Captioning With Attention - Pytorch
The goal of image captioning is to describe a given image using natural language. Using neural networks, we can partition the problem into two separate challenges. First, we need to extract meaningful features regarding the image that would help us describe it. Second, we need to generate a sequence of words that best fit those features.