Pinned Repositories
AdvancedEAST
AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.
AdvancedEAST-caffe
caffe 实现 AdvancedEAST+mobilenetv3
Aggregation-Cross-Entropy
Aggregation Cross-Entropy for Sequence Recognition. CVPR 2019.
AggregationCrossEntropyLoss4Caffe
Aggregation Cross Entropy Loss Layer for Caffe Python Layer Version
android-vulkan-tutorials
A set of samples to illustrate Vulkan API on Android
attention-is-all-you-need-pytorch
A PyTorch implementation of the Transformer model in "Attention is All You Need".
Bert_OCR.pytorch
Unofficial PyTorch implementation of 2D Attentional Irregular Scene Text Recognizer
OPENCL_convolution
opencl实现简单的卷积计算
pytorch_AdvancedEast
pytorch实现AdvancedEast+mobilenetv3
tinyCNN
将MNN拆解的简易前向推理框架(for study!)
corleonechensiyu's Repositories
corleonechensiyu/Caffe_Manual
Caffe使用教程
corleonechensiyu/caffe_ocr_for_linux
corleonechensiyu/Computer_Vision_Using_TensorFlowLite
On this project, AlexNet Convolution Neural Network is trained using traffic sign images from the German Road Traffic Sign Benchmark. The initially trained network is then quantized and optimized for deployment on mobile devices using TensorFlow Lite
corleonechensiyu/nerual_style_change
使用VGG19迁移学习实现图像风格迁移。
corleonechensiyu/SpatialTransformerLayer
corleonechensiyu/Swift
Basic C++ library on linux platform
corleonechensiyu/threadpool
based on C++11 , a mini threadpool , accept variable number of parameters 基于C++11的线程池,简洁且可以带任意多的参数
corleonechensiyu/vulkanComputeExample
Example for Vulkan Compute Shaders
corleonechensiyu/warp-ctc
Fast parallel CTC.