This repository consists of all files related to Deep-Learning and Machine Learning.
Please find the folders present and direct access to code.
basic_ml_algos: This folder consists of different machine learning algorithms.
Autoencoder: Code to Autoencoder based implementation.Linear Regression: Code to Linear Regression based implementation.Logistic Regression: Code to Logistic Regression based implementation.Multi-Layered Perceptron: Code to Multi-Layered Perceptron based implementation.Nearest Neighbour: Code to Nearest Neighbour based implementation.
matched_filter_using_neural_nets: This folder consists of Matched Filter implementation.
It is a concept in signal processing to increase signal to noise ratio. This is implemented using MLP and RNN. the code for the related project is found here.
Blog can be found here
classification_scripts : the generic classification script as a notebook. The code for the same can be found here
- The script has below following aspects.
compute and plot means and std deviation of all images
split dataset in train, test and validation
option to fine-tune or perform transfer learning
option to load different architectures like resnet, densenet, vgg, inception..,
perform training
visualize the confusion matrix
test
view classification report
Object_detection_scripts: The object detection script to check various scenarios and load and train based on pretrained network
-
Centroid_Resolution.ipynb: This notebook helps in finding the centroid of the bounding boxes in an image. This helps in analysing and balancing the bboxes in the image. It also shows the code to plot resolutions of images if there are of different sizes. And plot number of images in the range. The code for the same can be found here -
main_script_pytorch.ipynb: The Object detection based code is written using PyTorch. The Pytorch provides torchvision library which has flexible apis to create great working model with high accuracy. Find the explanation and compact code here -
split_data.ipynb: split the images and xml files created for the object detection. The code for the same can be found here -
xml_to_pkl.ipynb: Convert the xml files to pickle or csv files. The code for the same can be found here -
pkl_tfrecords.ipynb: Convert the pickle or csv files to tensorflow records. The code for the same can be found here