398 Open source projects that are alternatives of or similar to Places365

PyTorch tutorial for learners

End-to-end one-class instance segmentation based on U-Net architecture for Data Science Bowl 2018 in Kaggle

PyTorch tutorials A to Z

Text classification models. Used a submodule for other projects.

[5 FPS - 150 FPS] Learning Deep Features for One-Class Classification (AnomalyDetection). Corresponds RaspberryPi3. Convert to Tensorflow, ONNX, Caffe, PyTorch. Implementation by Python + OpenVINO/Tensorflow Lite.

generate captions for images using a CNN-RNN model that is trained on the Microsoft Common Objects in COntext (MS COCO) dataset

From Pixels to Sentiment: Fine-tuning CNNs for Visual Sentiment Prediction

Training & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models

Auto-optimizing a neural net (and its architecture) on the CIFAR-100 dataset. Could be easily transferred to another dataset or another classification task.

Feeding images of time series to Conv Nets! (Tensorflow + Keras)

Mobilenet V2(Inverted Residual) Implementation & Trained Weights Using Tensorflow

Android based Vocal Vision for Visually Impaired. Object Detection, Voice Assistance, Optical Character Reader, Read Aloud, Face Recognition, Landmark Recognition, Image Labelling etc.

A End to End CNN Model which predicts the steering wheel angle based on the video/image

DVDnet: A Simple and Fast Network for Deep Video Denoising

Coarse-to-Fine CNN for Image Super-Resolution (IEEE Transactions on Multimedia,2020)

Face identification with cnn+triplet-loss written by Keras.

Face Landmark Detector based on Mobilenet V1

Google Street View House Number(SVHN) Dataset, and classifying them through CNN

A PyTorch implementation of SEGAN based on INTERSPEECH 2017 paper "SEGAN: Speech Enhancement Generative Adversarial Network"

[Deprecated] 🇨🇳中国二代身份证光学识别

Lightweight Image Super-Resolution with Enhanced CNN (Knowledge-Based Systems,2020)

This toolbox is support material for the book on CNN (http://www.convolution.network).

Dockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)

End to End Dialect Identification using Convolutional Neural Network

一个移动端跨平台的gpu+cpu并行计算的cnn框架(A mobile-side cross-platform gpu+cpu parallel computing CNN framework)

A Tensorflow implementation of QANet for machine reading comprehension

🎨 🎨 深度学习 卷积神经网络教程 ：图像识别，目标检测，语义分割，实例分割，人脸识别，神经风格转换，GAN等🎨🎨 https://dataxujing.github.io/CNN-paper2/

a python implementation of MC-CNN

Rough list of my favorite deep learning resources, useful for revisiting topics or for reference. I have got through all of the content listed there, carefully. - Guillaume Chevalier

Sentiment analysis on tweets using Naive Bayes, SVM, CNN, LSTM, etc.

FaceBoxes for hand detection in PyTorch

All about Neural Networks!

Official Implementation of 'Fast AutoAugment' in PyTorch.

TensorFlow Implementation of state-of-the-art models since 2012

Character-level Convolutional Networks for Text Classification论文仿真实现

Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.

Sarcasm detection on tweets using neural network

Code for Statistically-motivated Second-order Pooling, ECCV2018

NN based lossless compression

QA - Answer Selection (Rank candidate answers for a given question)

CNN for intent classification task in a Chatbot

Chinese Question Classifier (Keras Implementation) on BQuLD

Convolutional Neural Network for German Traffic Sign Recognition Benchmark

Image Retrieval Experiment Using Triplet Loss

DLTK Model Zoo

Implementation of Neural Image Captioning model using Keras with Theano backend

A small, interpretable codebase containing the re-implementation of a few "deep" NLP models in PyTorch. Colab notebooks to run with GPUs. Models: word2vec, CNNs, transformer, gpt.

A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.

基于深度学习识别12306验证码

Source code for the 2019 IEEE TIFS paper "PalmNet: Gabor-PCA Convolutional Networks for Touchless Palmprint Recognition"

Fever screening with IR & RGB cameras and Deep CNNs

Fast Shadow Detection from a Single Image Using a Patched CNN

cnn pruning with tensorflow.

keras theano 验证码破解 字母+数字

Chinese & English Cws Pos Ner Entity Recognition implement using CNN bi-directional lstm and crf model with char embedding.基于字向量的CNN池化双向BiLSTM与CRF模型的网络，可能一体化的完成中文和英文分词，词性标注，实体识别。主要包括原始文本数据，数据转换,训练脚本,预训练模型,可用于序列标注研究.注意：唯一需要实现的逻辑是将用户数据转化为序列模型。分词准确率约为93%，词性标注准确率约为90%，实体标注（在本样本上）约为85%。

Deep Learning For Computer Vision With Python

🤖️image regression (base on convnetjs)

End-to-end variable length Captcha recognition using CNN+RNN+Attention/CTC (pytorch implementation). 端到端的不定长验证码识别

WB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].

Caffe to VHDL