Tencent / PocketFlow
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
☆2,816Updated last year
Alternatives and similar repositories for PocketFlow:
Users that are interested in PocketFlow are comparing it to the libraries listed below
- Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distille…☆4,376Updated last year
- Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators☆1,538Updated 5 years ago
- MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Co…☆5,810Updated 9 months ago
- Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet☆3,063Updated 2 years ago
- The convertor/conversion of deep learning models for different deep learning frameworks/softwares.☆3,245Updated last year
- Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)☆1,516Updated 4 years ago
- Fast and flexible AutoML with learning guarantees.☆3,461Updated last year
- FeatherCNN is a high performance inference engine for convolutional neural networks.☆1,217Updated 5 years ago
- [ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware☆1,433Updated 6 months ago
- A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility☆6,307Updated last year
- Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)☆1,083Updated 10 months ago
- An optimizer that trains as fast as Adam and as good as SGD.☆2,910Updated last year
- TensorFlow Code for paper "Efficient Neural Architecture Search via Parameter Sharing"☆1,579Updated 5 years ago
- Bolt is a deep learning library with high performance and heterogeneous flexibility.☆940Updated 7 months ago
- PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"☆2,710Updated last year
- Code for: "And the bit goes down: Revisiting the quantization of neural networks"☆634Updated 4 years ago
- Memory consumption and FLOP count estimates for convnets☆918Updated 6 years ago
- MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.☆4,999Updated 9 months ago
- A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.☆1,526Updated last month
- Fast & Simple Resource-Constrained Learning of Deep Network Structure☆1,028Updated last month
- ☆668Updated 3 years ago
- Tutorials for creating and using ONNX models☆3,469Updated 8 months ago
- A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.☆2,821Updated 5 years ago
- Tensorflow Backend for ONNX☆1,296Updated 11 months ago
- Deep Compression on AlexNet☆667Updated 3 years ago
- On the Variance of the Adaptive Learning Rate and Beyond☆2,546Updated 3 years ago
- Collection of recent methods on (deep) neural network compression and acceleration.☆939Updated 3 months ago
- A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures,…☆852Updated 3 years ago
- Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.☆9,335Updated 2 years ago
- A curated list of awesome architecture search resources☆1,186Updated 4 years ago