xingshulicc Goto Github PK

followers: 23.0 following: 3.0 repos: 51.0 gists: 1.0

Name: xingshulicc

Type: User

xingshulicc

Machine learning, deep learning, evolution algorithm, the fans of math

trainval.py is used to generate txt file for detection

interminate_output.py is used to watch the interminate feature maps, the parametes can adjust during running the code are: img_path = '/home/xingshuli/Desktop/test_pictures/luna_female.jpeg' get_ith_layer_output; # i = 37 is better num_feature_maps; # =256 num_top_activation; # top 10 or other numbers

xingshulicc's Projects

channel_attention_selection

Explore the effect of Receptive Field Size and Model Depth on Image Classification Accuracy

$cifar10-classification-using-fractalnet20 icon$ cifar10-classification-using-fractalnet20

I rewrite the code of fractal_net by Keras 2 with tensorflow backend and change the learning rate schedule of original

citrus-diseases-description

Description of 7 citrus diseases

citrus-pest-classification-by-advanced-deep-learning

10 citrus pests classification, VGG-16, ResNet-50, Inception-ResNet-V3, Xception

citrus-pests-description

Description about 17 species of citrus pests and their damage and host plants

crop-pests-and-diseases-recognition-by-incremental-learning-methods

Common agricultural pests and diseases recognition, Incremental learning study

deformable-convolution-neural-network

A good example of deformable convolutional network for mnist classification

dynamic-convolution-pytorch

Pytorch!!!Pytorch!!!Pytorch!!! Dynamic Convolution: Attention over Convolution Kernels (CVPR-2020)

external-attention-pytorch

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

facenet

Face recognition using Tensorflow

focal-transformer

Official code for our NeurIPS 2021 Spotlight "Focal Self-attention for Local-Global Interactions in Vision Transformers"

fungi_species_growth_stage_recognition_deep_learning

Multi-head Image Classification Using Deep Neural Networks

gcvit

Official PyTorch implementation of Global Context Vision Transformers

image_segmentation_deep_learning

Deep learning method for Image segmentation

keras

Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano or TensorFlow.

keras-bert

Implementation of BERT that could load official pre-trained models for feature extraction and prediction

keras-dogs

a baseline for baidu dog classification competition.

keras-focal-loss

Implementation of binary and categorical/multiclass focal loss using Keras with TensorFlow backend

keras-non-local-nets

Keras implementation of Non-local Neural Networks

keras-tcn

Keras Temporal Convolutional Network.

keras-transformer

Transformer implemented in Keras

keras-yolo2

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).