TJU Deep Learning & Neural Network

Last update: Jan 19, 2022

Overview

Deep_Learning & Neural_Network_Lab

实验环境

Python 3.9
Anaconda3(官网下载或清华镜像都行)
PyTorch 1.10.1(安装代码如下)

conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch

数据集下载

实验使用MNIST数据集
下载地址: http://yann.lecun.com/exdb/mnist/

运行方式

启动PyTorch环境

conda activate pytorch

在该环境下运行程序(30-60 minutes per file)

python GAN.py               # 运行GAN.py
python CGAN.py              # 运行CGAN.py
python DCGAN.py             # 运行DCGAN.py
python WGAN.py              # 运行WGAN.py
python Improved_WGAN.py     # 运行Improved_WGAN.py

实验结果

Model	epoch	1	5	10	50	100	150	200
GAN	d_loss	0.510469	0.342887	0.248609	0.170712	0.120419	0.169989	0.192855
	g_loss	0.956933	1.874407	2.537149	3.263798	3.905378	3.570554	3.132934
CGAN	d_loss	0.106481	0.135711	0.194618	0.17816	0.124881	0.106104	0.097463
	g_loss	0.660399	0.585134	0.415263	0.474954	0.632873	0.689216	0.718078
DCGAN	d_loss	0.692203	0.631018	0.588311	0.463967	0.334903	0.242517	0.103577
	g_loss	0.694127	0.829934	0.936831	1.402277	2.230488	2.936166	2.757655
WGAN	d_loss	-0.291029	-0.329138	-0.468464	-0.214993	-0.123098	-0.080621	-0.060724
	g_loss	-12.6155	-0.209976	-0.662237	-0.456756	-0.427529	-0.388925	-0.197952
Improved_WGAN	d_loss	-0.246925	-7.846449	-6.713724	-3.10867	-2.067324	-1.634501	-1.393292
	g_loss	-14.636739	0.762477	1.745449	-2.624076	-2.965248	-2.781996	-2.585317

具体数据详见 data.xls 文件

🔮 Execution time predictions for deep neural network training iterations across different GPUs.

Habitat: A Runtime-Based Computational Performance Predictor for Deep Neural Network Training Habitat is a tool that predicts a deep neural network's

44 Dec 27, 2022

The official implementation of the IEEE S&P`22 paper "SoK: How Robust is Deep Neural Network Image Classification Watermarking".

Watermark-Robustness-Toolbox - Official PyTorch Implementation This repository contains the official PyTorch implementation of the following paper to

49 Dec 19, 2022

Face Mask Detection is a project to determine whether someone is wearing mask or not, using deep neural network.

face-mask-detection Face Mask Detection is a project to determine whether someone is wearing mask or not, using deep neural network. It contains 3 scr

13 Jan 18, 2022

This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL [Deep Graph Library] and PyTorch.

519 Jan 2, 2023

Facilitates implementing deep neural-network backbones, data augmentations

Introduction Nowadays, the training of Deep Learning models is fragmented and unified. When AI engineers face up with one specific task, the common wa

40 Dec 29, 2022

CUP-DNN is a deep neural network model used to predict tissues of origin for cancers of unknown of primary.

CUP-DNN CUP-DNN is a deep neural network model used to predict tissues of origin for cancers of unknown of primary. The model was trained on the expre

1 Oct 27, 2021

A collection of easy-to-use, ready-to-use, interesting deep neural network models

Interesting and reproducible research works should be conserved. This repository wraps a collection of deep neural network models into a simple and un

16 Jun 16, 2022

SpinalNet: Deep Neural Network with Gradual Input

SpinalNet: Deep Neural Network with Gradual Input This repository contains scripts for training different variations of the SpinalNet and its counterp

142 Dec 30, 2022

Use tensorflow to implement a Deep Neural Network for real time lane detection

LaneNet-Lane-Detection Use tensorflow to implement a Deep Neural Network for real time lane detection mainly based on the IEEE IV conference paper "To

1.9k Jan 8, 2023

TJU Deep Learning & Neural Network

Related tags

Overview

Deep_Learning & Neural_Network_Lab

实验环境

数据集下载

运行方式

实验结果

You might also like...

🔮 Execution time predictions for deep neural network training iterations across different GPUs.

The official implementation of the IEEE S&P`22 paper "SoK: How Robust is Deep Neural Network Image Classification Watermarking".

Face Mask Detection is a project to determine whether someone is wearing mask or not, using deep neural network.

This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL [Deep Graph Library] and PyTorch.

Facilitates implementing deep neural-network backbones, data augmentations

CUP-DNN is a deep neural network model used to predict tissues of origin for cancers of unknown of primary.

A collection of easy-to-use, ready-to-use, interesting deep neural network models

SpinalNet: Deep Neural Network with Gradual Input

Use tensorflow to implement a Deep Neural Network for real time lane detection

Owner

St3ve Lee

This is a model made out of Neural Network specifically a Convolutional Neural Network model

Bayesian-Torch is a library of neural network layers and utilities extending the core of PyTorch to enable the user to perform stochastic variational inference in Bayesian deep neural networks

Visualizer for neural network, deep learning, and machine learning models

This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

PPLNN is a Primitive Library for Neural Network is a high-performance deep-learning inference engine for efficient AI inferencing

Neuralnetwork - Basic Multilayer Perceptron Neural Network for deep learning

Pytorch Implementation of Adversarial Deep Network Embedding for Cross-Network Node Classification

Neural-net-from-scratch - A simple Neural Network from scratch in Python using the Pymathrix library

A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.

[ICLR 2021] "CPT: Efficient Deep Neural Network Training via Cyclic Precision" by Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin