Pinned Repositories
Caffe-TRT
Import Caffe model into TensorRT using Python
llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
taichi-voxel-challenge
tensorflow-serving-gpu
Serve a pre-trained model (Mask-RCNN, Faster-RCNN, SSD) on Tensorflow:Serving.
Tensorflow1.14-cuda10.1
This is a general guidance of compiling Tensorflow from source
time-series-forcasting
Using K-NN, SVM, Bayes, LSTM, and multi-variable LSTM models on time series forecasting
UNet-CRF-RNN
Edge-aware U-Net with CRF-RNN layer for Medical Image Segmentation
Zero-Cofig-IoT
security zero configuration IoT smart home system
object
A unified interface for reading and writing object file formats
llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
EsmeYi's Repositories
EsmeYi/UNet-CRF-RNN
Edge-aware U-Net with CRF-RNN layer for Medical Image Segmentation
EsmeYi/time-series-forcasting
Using K-NN, SVM, Bayes, LSTM, and multi-variable LSTM models on time series forecasting
EsmeYi/Caffe-TRT
Import Caffe model into TensorRT using Python
EsmeYi/Zero-Cofig-IoT
security zero configuration IoT smart home system
EsmeYi/taichi-voxel-challenge
EsmeYi/tensorflow-serving-gpu
Serve a pre-trained model (Mask-RCNN, Faster-RCNN, SSD) on Tensorflow:Serving.
EsmeYi/Tensorflow1.14-cuda10.1
This is a general guidance of compiling Tensorflow from source
EsmeYi/EsmeYi
EsmeYi/tensorrt
TensorFlow/TensorRT integration
EsmeYi/TF-TRT
Optimizing a TF model (e.g. frozen graph, SavedModel, ckpt) with TRT
EsmeYi/llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
EsmeYi/API-mashup
Integrate two APIs (translator and news) and implement a web site to show
EsmeYi/count-nails
EsmeYi/deeplab_v3
Tensorflow Implementation of the Semantic Segmentation DeepLab_V3 CNN
EsmeYi/object
A unified interface for reading and writing object file formats
EsmeYi/object-testfiles
Binary files for use in test cases
EsmeYi/rust
Empowering everyone to build reliable and efficient software.
EsmeYi/TensorRT-1
TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.
EsmeYi/TF2.0-Notes