ftian1

Follow

Tian, Feng ftian1

Follow

Deep Learning Framework Developer, focusing on model optimization with quantization, distillation, and pruning

21 followers · 3 following

Intel
Shanghai
03:22 (UTC +08:00)

Achievements

BetaSend feedback

Achievements

BetaSend feedback

Organizations

Block or Report

Block or report ftian1

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned

intelcaffe_weight_to_bvlc Public

This is used to convert intelcaffe weight file to be compatible with bvlc caffe

Python 5
CaffeDeepSpeech2 Public

The caffe implementation of DeepSpeech2

Cuda
dlrm Public

Forked from facebookresearch/dlrm

An implementation of a deep learning recommendation model (DLRM)

Python
pytorch/pytorch Public

Tensors and Dynamic neural networks in Python with strong GPU acceleration

C++ 61.2k 17k
intel/caffe Public archive

This fork of BVLC/Caffe is dedicated to improving performance of this deep learning framework when running on CPU, in particular Intel® Xeon processors.

C++ 838 499

71 contributions in the last year

Learn how we count contributions

Less More

Contribution activity

December 2022

Reviewed 42 pull requests in 2 repositories

intel/neural-compressor 25 pull requests

Reconstructing pruning API derived from Component.py. Dec 19
Fix onnxrt numpy round bug Dec 16
refine torchvision examples Dec 16
Export Qlinear to QDQ Dec 12
Pruning/Integrate new-developed pruning API with old one Dec 12
Update spr-base version number Dec 12
Pruning/Integrate new-developed pruning API with old one. Dec 12
Integrate new-developed pruning API with old one. Dec 9
Fixed pruning and distillation bug and remove invalid code Dec 9
Add mse_v2 tuning strategy Dec 9
add keras-in/keras-out to INC Dec 9
Update DyNAS interface Dec 9
Enable Transformer LT search space for Dynamic Neural Architecture Search Toolkit Dec 9
Fixed the UTs of sigopt strategy for the new API Dec 9
Remove data, metric and common to neural_compressor Dec 9
Support different backends for adaptors Dec 9
Fix Windows multi-instance bug Dec 8
Fix ITEX OOB model benchmark issue Dec 8
Refine TF NLP models with INC User NewAPI Dec 8
add warning when meets unsupported config Dec 8
INC New API TF oob, wide_deep_large_ds, 3dunet-mlperf examples Dec 8
Modify NAS n_worker as a variable Dec 8
Enhance ITEX benchmark UT check Dec 8
Disable inserting QDQ for DepthwiseConv2dNative in ITEX mode Dec 8
Refine Keras Examples for INC New API Dec 7
Some pull request reviews not shown.

huggingface/optimum-intel 1 pull request

Refactorization intel neural compressor Dec 16