Practical use of basic tool for machine learning using PyTorch lib
-
Updated
Oct 5, 2024 - Python
Practical use of basic tool for machine learning using PyTorch lib
Reduce multiple PyTorch TensorBoard runs to new event (or CSV) files.
MLP classifier on the MNIST dataset implemented in JAX with a GUI for entering hyperparameters, and a custom visualization of runs on TensorBoard.
A Wrapper class for the Tensorflow's Tensorboard.
Yet Another Word2Vec Implementation
Crack detection and segmentation using a Mask RCNN model from detectron2 library
Using tensorboardX (tensorboard for pytorch) e.g. ploting more than one graph in the same chat etc.
Dissertation completed for the award of MSci in Computer Science. This dissertation is about automated breast cancer detection in low-resolution whole-slide pathology images using a deep convolutional neural network pipeline.
This is a Pytorch package that can be used directly with PyTorch and Tensorboard to simplify the implementation process.
Comprehensive image classification for training multilayer perceptron (MLP), LeNet, LeNet5, conv2, conv4, conv6, VGG11, VGG13, VGG16, VGG19 with batch normalization, ResNet18, ResNet34, ResNet50, MobilNetV2 on MNIST, CIFAR10, CIFAR100, and ImageNet1K.
U-Net for biomedical image segmentation
This project uses Deep Reinforcement Learning to solve the Lunar Lander environment of the OpenAI-Gym
Crack detection and Crack Length estimation using Deep Neural Networks. Reference: Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks (Young-Jin Cha & Wooram Choi)
DCGAN implementation
PyTorch implementation of (Hinton) Knowledge Distillation and a base class for simple implementation of other distillation methods.
This repo helps to track model Weights, Biases and Gradients during training with loss tracking and gives detailed insight for Classification-Model Evaluation
Data visualization using Matplotlib, pandas, seaborn and tensorboard
Simple Feed-Forward Neural Network that classifies characters on the mnist dataset.
Add a description, image, and links to the tensorboard-pytorch topic page so that developers can more easily learn about it.
To associate your repository with the tensorboard-pytorch topic, visit your repo's landing page and select "manage topics."