foamliu / Mobile Image Matting
Licence: mit
a lightweight image matting model
Stars: ✭ 61
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Mobile Image Matting
Classification models
Classification models trained on ImageNet. Keras.
Stars: ✭ 938 (+1437.7%)
Mutual labels: resnet
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 (-19.67%)
Mutual labels: resnet
Bmw Tensorflow Training Gui
This repository allows you to get started with a gui based training a State-of-the-art Deep Learning model with little to no configuration needed! NoCode training with TensorFlow has never been so easy.
Stars: ✭ 736 (+1106.56%)
Mutual labels: resnet
Autodl
Automated Deep Learning without ANY human intervention. 1'st Solution for AutoDL [email protected]
Stars: ✭ 854 (+1300%)
Mutual labels: resnet
Video Classification
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
Stars: ✭ 543 (+790.16%)
Mutual labels: resnet
Pytorch Image Models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
Stars: ✭ 15,232 (+24870.49%)
Mutual labels: resnet
Retinanet
Keras implementation of RetinaNet for object detection and visual relationship identification
Stars: ✭ 24 (-60.66%)
Mutual labels: resnet
Imagenet resnet tensorflow2.0
Train ResNet on ImageNet in Tensorflow 2.0; ResNet 在ImageNet上完整训练代码
Stars: ✭ 42 (-31.15%)
Mutual labels: resnet
Deep Ctr Prediction
CTR prediction models based on deep learning(基于深度学习的广告推荐CTR预估模型)
Stars: ✭ 628 (+929.51%)
Mutual labels: resnet
Keras Idiomatic Programmer
Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software Engineers and Data Scientists wanting to learn the TF.Keras Machine Learning framework
Stars: ✭ 720 (+1080.33%)
Mutual labels: resnet
Cifar Zoo
PyTorch implementation of CNNs for CIFAR benchmark
Stars: ✭ 584 (+857.38%)
Mutual labels: resnet
Pretrained Models.pytorch
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
Stars: ✭ 8,318 (+13536.07%)
Mutual labels: resnet
Medicalzoopytorch
A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation
Stars: ✭ 546 (+795.08%)
Mutual labels: resnet
Vgg16 Pytorch
VGG16 Net implementation from PyTorch Examples scripts for ImageNet dataset
Stars: ✭ 26 (-57.38%)
Mutual labels: resnet
Cyclegan Qp
Official PyTorch implementation of "Artist Style Transfer Via Quadratic Potential"
Stars: ✭ 59 (-3.28%)
Mutual labels: resnet
Jacinto Ai Devkit
Training & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models
Stars: ✭ 49 (-19.67%)
Mutual labels: resnet
Tensornets
High level network definitions with pre-trained weights in TensorFlow
Stars: ✭ 982 (+1509.84%)
Mutual labels: resnet
Deep Mobile Matting
This is a lightweight image matting model in PyTorch.
Features
- MobileNetV2 as backbone.
- DeepLabv3 heads.
- Small model (size: 23.5MB, FLOPs: 11.39GB, total params: 7.62 millions)
Performance
- The Composition-1k testing dataset.
- Evaluate with whole image.
- SAD normalized by 1000.
- Input image is normalized with mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225].
- Both erode and dialte to generate trimap.
Models | SAD | MSE | Download |
---|---|---|---|
paper-stage0 | 59.6 | 0.019 | |
paper-stage1 | 54.6 | 0.017 | |
paper-stage3 | 50.4 | 0.014 | |
my-stage0 | 127.4 | 0.068 | Link |
Dependencies
- Python 3.6.8
- PyTorch 1.3
Dataset
Adobe Deep Image Matting Dataset
Follow the instruction to contact author for the dataset.
MSCOCO
Go to MSCOCO to download:
PASCAL VOC
Go to PASCAL VOC to download:
- VOC challenge 2008 training/validation data
- The test data for the VOC2008 challenge
Usage
Data Pre-processing
Extract training images:
$ python pre_process.py
# python data_gen.py
Train
$ python train.py
If you want to visualize during training, run in your terminal:
$ tensorboard --logdir runs
Experimental results
The Composition-1k testing dataset
- Test:
$ python test.py
It prints out average SAD and MSE errors when finished.
Demo
Download pre-trained Deep Image Matting Link then run:
$ python demo.py
Image/Trimap | Output/GT | New BG/Compose |
---|---|---|
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].