signatrix / Regnet
Licence: mit
Pytorch implementation of network design paradigm described in the paper "Designing Network Design Spaces"
Stars: ✭ 129
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Regnet
Imgclsmob
Sandbox for training deep learning networks
Stars: ✭ 2,405 (+1764.34%)
Mutual labels: classification, image-classification, imagenet
Efficientnet
Implementation of EfficientNet model. Keras and TensorFlow Keras.
Stars: ✭ 1,920 (+1388.37%)
Mutual labels: classification, image-classification, imagenet
Awesome Project Ideas
Curated list of Machine Learning, NLP, Vision, Recommender Systems Project Ideas
Stars: ✭ 6,114 (+4639.53%)
Mutual labels: classification, image-classification
Orange3 Imageanalytics
🍊 🎑 Orange3 add-on for dealing with image related tasks
Stars: ✭ 24 (-81.4%)
Mutual labels: image-classification, imagenet
Labelbox
Labelbox is the fastest way to annotate data to build and ship computer vision applications.
Stars: ✭ 1,588 (+1131.01%)
Mutual labels: image-classification, imagenet
Label Studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Stars: ✭ 7,264 (+5531.01%)
Mutual labels: image-classification, imagenet
Pytorch Mobilenet V3
MobileNetV3 in pytorch and ImageNet pretrained models
Stars: ✭ 616 (+377.52%)
Mutual labels: classification, 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 (-58.14%)
Mutual labels: image-classification, imagenet
Tensorflow object tracking video
Object Tracking in Tensorflow ( Localization Detection Classification ) developed to partecipate to ImageNET VID competition
Stars: ✭ 491 (+280.62%)
Mutual labels: classification, imagenet
Tf Mobilenet V2
Mobilenet V2(Inverted Residual) Implementation & Trained Weights Using Tensorflow
Stars: ✭ 85 (-34.11%)
Mutual labels: image-classification, imagenet
Caffe Model
Caffe models (including classification, detection and segmentation) and deploy files for famouse networks
Stars: ✭ 1,258 (+875.19%)
Mutual labels: classification, imagenet
Pytorch Classification
Classification with PyTorch.
Stars: ✭ 1,268 (+882.95%)
Mutual labels: classification, imagenet
Cvat
Powerful and efficient Computer Vision Annotation Tool (CVAT)
Stars: ✭ 6,557 (+4982.95%)
Mutual labels: image-classification, imagenet
Mmclassification
OpenMMLab Image Classification Toolbox and Benchmark
Stars: ✭ 532 (+312.4%)
Mutual labels: image-classification, imagenet
Hrnet Image Classification
Train the HRNet model on ImageNet
Stars: ✭ 633 (+390.7%)
Mutual labels: image-classification, imagenet
Fishnet
Implementation code of the paper: FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction, NeurIPS 2018
Stars: ✭ 533 (+313.18%)
Mutual labels: image-classification, imagenet
Constrained attention filter
(ECCV 2020) Tensorflow implementation of A Generic Visualization Approach for Convolutional Neural Networks
Stars: ✭ 36 (-72.09%)
Mutual labels: classification, imagenet
Petridishnn
Code for the neural architecture search methods contained in the paper Efficient Forward Neural Architecture Search
Stars: ✭ 112 (-13.18%)
Mutual labels: image-classification, imagenet
Computer Vision
Programming Assignments and Lectures for Stanford's CS 231: Convolutional Neural Networks for Visual Recognition
Stars: ✭ 408 (+216.28%)
Mutual labels: image-classification, imagenet
Neural Backed Decision Trees
Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
Stars: ✭ 411 (+218.6%)
Mutual labels: image-classification, imagenet
Regnet
Introduction
Here is our pytorch pytorch implementation of network design paradigm described in the paper "Designing Network Design Spaces"
Comparison
P: Paper's. O: Our
Model | [P/O] gflops | [P/O] params | [P/O] top-1 error |
---|---|---|---|
RerNetY-200MF | 0.2/0.22 | 3.2/3.27 | 29.6/updating... |
RerNetY-400MF | 0.4/0.42 | 4.3/4.45 | 25.9/updating... |
RerNetY-600MF | 0.6/0.60 | 6.1/5.66 | 24.5/updating... |
RerNetY-800MF | 0.8/0.82 | 6.3/6.26 | 23.7/updating... |
Best models
Datasets
We use Imagenet (ILSVRC2012) for all experiments, as stated in the paper.
Create a data folder under this repository,
cd {repo_root}
mkdir data
-
ImageNet:
Download the ImageNet dataset and put the files as the following structure:
Of course you could change this path to whatever you want based on your own preference, or mount it to a folder when using docker.data ├── train │ ├── n01440764 │ └── n01443537 │ └── ... │── val │ ├── n01440764 │ └── n01443537 │ └── ...
How to use our code
With our code, you can:
- Train your model with default arguments by running python train.py -d path/to/image/root/folder
- We also provide shell scripts which could be used to run training for first RegnetY models at ./scripts/. For example, if you want to train RegNetY 800MF, you could simply run ./scripts/RegnetY_800MF.sh
Requirements
- python 3.7
- pytorch 1.4
- opencv (cv2)
- pthflops
- torchsummary
Updating (21/04/2020)
Complete all networks and training script. We are training RegnetY models and will update result soon.
References
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].