stigma0617 / Vovnet.pytorch
A pytorch implementation of VoVNet
Stars: ✭ 101
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Vovnet.pytorch
Big transfer
Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.
Stars: ✭ 1,096 (+985.15%)
Mutual labels: imagenet
Mobilenet Caffe
Caffe Implementation of Google's MobileNets (v1 and v2)
Stars: ✭ 1,217 (+1104.95%)
Mutual labels: imagenet
Imagenet resnet tensorflow2.0
Train ResNet on ImageNet in Tensorflow 2.0; ResNet 在ImageNet上完整训练代码
Stars: ✭ 42 (-58.42%)
Mutual labels: imagenet
Imagenet
Trial on kaggle imagenet object localization by yolo v3 in google cloud
Stars: ✭ 56 (-44.55%)
Mutual labels: imagenet
Tf Hrnet
tensorflow implementation for "High-Resolution Representations for Labeling Pixels and Regions"
Stars: ✭ 61 (-39.6%)
Mutual labels: imagenet
Orange3 Imageanalytics
🍊 🎑 Orange3 add-on for dealing with image related tasks
Stars: ✭ 24 (-76.24%)
Mutual labels: imagenet
Pytorch Classification
Classification with PyTorch.
Stars: ✭ 1,268 (+1155.45%)
Mutual labels: imagenet
Segmentationcpp
A c++ trainable semantic segmentation library based on libtorch (pytorch c++). Backbone: ResNet, ResNext. Architecture: FPN, U-Net, PAN, LinkNet, PSPNet, DeepLab-V3, DeepLab-V3+ by now.
Stars: ✭ 49 (-51.49%)
Mutual labels: imagenet
Divide And Co Training
[Paper 2020] Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training. Plus, an image classification toolbox includes ResNet, Wide-ResNet, ResNeXt, ResNeSt, ResNeXSt, SENet, Shake-Shake, DenseNet, PyramidNet, and EfficientNet.
Stars: ✭ 54 (-46.53%)
Mutual labels: imagenet
Pneumonia Detection From Chest X Ray Images With Deep Learning
Detecting Pneumonia in Chest X-ray Images using Convolutional Neural Network and Pretrained Models
Stars: ✭ 64 (-36.63%)
Mutual labels: imagenet
Constrained attention filter
(ECCV 2020) Tensorflow implementation of A Generic Visualization Approach for Convolutional Neural Networks
Stars: ✭ 36 (-64.36%)
Mutual labels: imagenet
Caffe Model
Caffe models (including classification, detection and segmentation) and deploy files for famouse networks
Stars: ✭ 1,258 (+1145.54%)
Mutual labels: imagenet
Classification models
Classification models trained on ImageNet. Keras.
Stars: ✭ 938 (+828.71%)
Mutual labels: imagenet
One Pixel Attack Keras
Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet
Stars: ✭ 1,097 (+986.14%)
Mutual labels: imagenet
Hbonet
[ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions
Stars: ✭ 94 (-6.93%)
Mutual labels: imagenet
Tf Mobilenet V2
Mobilenet V2(Inverted Residual) Implementation & Trained Weights Using Tensorflow
Stars: ✭ 85 (-15.84%)
Mutual labels: imagenet
Artos
Adaptive Real-Time Object Detection System with HOG and CNN Features
Stars: ✭ 64 (-36.63%)
Mutual labels: imagenet
A pytorch Implementation of VoVNet Backbone Networks
This is a pytorch implementation of VoVNet backbone networks as described in the paper An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection. This is implemented through pytorch/vision style.
What does this repo provide?
This repo provides VoVNet-39/57 models trained on ImageNet classification dataset with same training protocols as pytorch/examples/imagenet (e.g., 128 batch size, 90 epoch, data augmentations, lr_policy, etc) and compares to ResNet and DenseNet.
ImageNet results
Notes:
- For fair comparison, same training protocols used as pytorch/examples/imagenet
- 90 epoch
- step learning rate schedule (learning rate decayed at every 30 epoch)
- 256 batch size
- default augmentations (e.g., crop, flip, same mean/std normalization)
- @224x224 training/validation
- Inference time is measured on TITAN X PASCAL GPU
- CUDA v9.2, cuDNN v7.3, pytorch 1.0
Model | Top-1 | Top-5 | Inference time |
---|---|---|---|
ResNet-50 | 23.85% | 7.13% | 12 ms |
DenseNet-201 | 22.80% | 6.43% | 39 ms |
VoVNet-39 | 23.23% | 6.57% | 10 ms |
ResNet-101 | 22.63% | 6.44% | 20 ms |
DenseNet-161 | 22.35% | 6.20% | 27 ms |
VoVNet-57 | 22.27% | 6.28% | 13 ms |
Pretrained models
Training & Inferecne
Installation
- python 3.6
- Install pytorch > 0.4
git clone https://github.com/stigma0617/VoVNet.pytorch.git
- install depenecies :
pip install -r requirements.txt
Imagenet data preparation
You can follow the instruction of pytorch/examples/imagenet
Train
run main.py
specifying data path, the desired model name--arch
, and save-directory--savedir
.
python main.py [imagenet-folder with train and val folders] --arch vovnet39 --savedir VoVNet39
Related projects
VoVNet-Detectron VoVNet-DeepLabV3
TO DO
- [ ] VoVNet-27-slim
- [ ] VoVNet-27-slim-depthwise
- [ ] VoVNet-99
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].