Pytorch Implementation and Performance Analysis of the Popular Vision Architectures from Scratch.

This Project uses Convolutional Neural Networks (CNN) for the classification and prediction of handwritten Devanagari script. Leveraging transfer learning techniques, it adapts pre-trained models to recognize and forecast characters in Devanagari, enhancing accuracy and efficiency.

Journey to Learn Deep Learning with Pytorch from scratch i.e, from Tensor & Gradients to Advance topic like Generative Adversarial Networks

Training using an alternative approach: forward-thinking

A set of experiments inspired by the paper "Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs" by Jonathan Frankle, David J. Schwab, Ari S. Morcos

High Accuracy ResNet Model under 5 Million parameters.

A collection of small-scale projects that helped me learn the basics of the PyTorch framework

Optimize ResNet Learning Process

Simple implementation of a residually connected convolutional neural network in PyTorch

An experiment in training a fully connected residual net to learn the argmax function.

Simple Multi-GPU Implementation of ResNet in Tensorflow

Yolov3 with multi backbone

Implemented Deep Residual Learning for Image Recognition Paper and achieved lower error rate by customizing different parts of the architecture.

Robustness of Deep Neural Networks using Trainable Activation Functions

The aim is to build a Deep Convolutional Network using Residual Networks (ResNet). Here we build ResNet 50 using Keras.

Implemented the Deep Residual Learning for Image Recognition Paper and achieved better accuracy by customizing different parts of the architecture.

A computer vision web-app that uses deep learning and Residual Neural Networks to identify your Pokémon and then tells you all about it.

👣 “恒锐杯”鞋印花纹图像类别判定挑战赛

Residual Embedding Similarity-based Network Selection (RESNets) for forecasting network dynamics.