EfficientNetV2 implementation using PyTorch

Last update: Dec 29, 2022

Overview

EfficientNetV2-S implementation using PyTorch

Train Steps

Configure imagenet path by changing data_dir in train.py
python main.py --benchmark for model information
python -m torch.distributed.launch --nproc_per_node=$ main.py --train for training model, $ is number of GPUs
python main.py --test for testing

Note

The model achieved 82.7 top-1 after 150 epochs

Number of parameters: 23941296
Time per operator type:
        778.049 ms.    70.6258%. Conv
        255.227 ms.    23.1677%. Sigmoid
          56.91 ms.    5.16589%. Mul
         6.1573 ms.   0.558916%. Add
        4.69289 ms.   0.425987%. ReduceMean
       0.613303 ms.  0.0556713%. FC
        1101.65 ms in Total
FLOP per operator type:
         17.277 GFLOP.    99.7074%. Conv
      0.0419251 GFLOP.   0.241954%. Mul
     0.00519322 GFLOP.  0.0299706%. Add
       0.003585 GFLOP.  0.0206894%. FC
        17.3277 GFLOP in Total
Feature Memory Read per operator type:
        295.875 MB.    50.5134%. Mul
        241.136 MB.     41.168%. Conv
        41.5457 MB.     7.0929%. Add
        7.17917 MB.    1.22567%. FC
        585.737 MB in Total
Feature Memory Written per operator type:
          167.7 MB.    49.2361%. Mul
        152.127 MB.    44.6639%. Conv
        20.7729 MB.    6.09882%. Add
          0.004 MB. 0.00117438%. FC
        340.605 MB in Total
Parameter Memory per operator type:
        87.8034 MB.    92.4486%. Conv
          7.172 MB.    7.55143%. FC
              0 MB.          0%. Add
              0 MB.          0%. Mul
        94.9754 MB in Total

EfficientNetV2 implementation using PyTorch

Related tags

Overview

Train Steps

Note

Owner

Jahongir Yunusov

Robust, modular and efficient implementation of advanced Hamiltonian Monte Carlo algorithms

A unified 3D Transformer Pipeline for visual synthesis

GPU Programming with Julia - course at the Swiss National Supercomputing Centre (CSCS), ETH Zurich

Network Enhancement implementation in pytorch

A highly efficient and modular implementation of Gaussian Processes in PyTorch

This package proposes simplified exporting pytorch models to ONNX and TensorRT, and also gives some base interface for model inference.

Torch implementation of SegNet and deconvolutional network

GT4SD, an open-source library to accelerate hypothesis generation in the scientific discovery process.

🗣️ Microsoft Edge TTS for Home Assistant, no need for app_key

Code for ACL2021 paper Consistency Regularization for Cross-Lingual Fine-Tuning.

Fuzzing tool (TFuzz): a fuzzing tool based on program transformation

This is a tensorflow-based rotation detection benchmark, also called AlphaRotate.

The code for the CVPR 2021 paper Neural Deformation Graphs, a novel approach for globally-consistent deformation tracking and 3D reconstruction of non-rigid objects.

HuSpaCy: industrial-strength Hungarian natural language processing

A Real-World Benchmark for Reinforcement Learning based Recommender System

Compact Bidirectional Transformer for Image Captioning

Human motion synthesis using Unity3D

Continuous Conditional Random Field Convolution for Point Cloud Segmentation

The official PyTorch code for NeurIPS 2021 ML4AD Paper, "Does Thermal data make the detection systems more reliable?"

This is a model made out of Neural Network specifically a Convolutional Neural Network model