Golbstein / Keras Segmentation Deeplab V3.1
An awesome semantic segmentation model that runs in real time
Stars: ✭ 156
Projects that are alternatives of or similar to Keras Segmentation Deeplab V3.1
Deeplabv3 Plus
Tensorflow 2.3.0 implementation of DeepLabV3-Plus
Stars: ✭ 32 (-79.49%)
Mutual labels: jupyter-notebook, segmentation, semantic-segmentation
Cascaded Fcn
Source code for the MICCAI 2016 Paper "Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional NeuralNetworks and 3D Conditional Random Fields"
Stars: ✭ 296 (+89.74%)
Mutual labels: jupyter-notebook, segmentation, semantic-segmentation
3dunet abdomen cascade
Stars: ✭ 91 (-41.67%)
Mutual labels: jupyter-notebook, segmentation, semantic-segmentation
Multiclass Semantic Segmentation Camvid
Tensorflow 2 implementation of complete pipeline for multiclass image semantic segmentation using UNet, SegNet and FCN32 architectures on Cambridge-driving Labeled Video Database (CamVid) dataset.
Stars: ✭ 67 (-57.05%)
Mutual labels: jupyter-notebook, segmentation, semantic-segmentation
Setr Pytorch
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Stars: ✭ 96 (-38.46%)
Mutual labels: segmentation, semantic-segmentation
Spacenet building detection
Project to train/test convolutional neural networks to extract buildings from SpaceNet satellite imageries.
Stars: ✭ 83 (-46.79%)
Mutual labels: jupyter-notebook, semantic-segmentation
Deep Residual Unet
ResUNet, a semantic segmentation model inspired by the deep residual learning and UNet. An architecture that take advantages from both(Residual and UNet) models.
Stars: ✭ 97 (-37.82%)
Mutual labels: jupyter-notebook, semantic-segmentation
Crfasrnn pytorch
CRF-RNN PyTorch version http://crfasrnn.torr.vision
Stars: ✭ 102 (-34.62%)
Mutual labels: segmentation, semantic-segmentation
Deep Segmentation
CNNs for semantic segmentation using Keras library
Stars: ✭ 69 (-55.77%)
Mutual labels: segmentation, semantic-segmentation
Unet
Generic U-Net Tensorflow 2 implementation for semantic segmentation
Stars: ✭ 100 (-35.9%)
Mutual labels: jupyter-notebook, semantic-segmentation
Dstl unet
Dstl Satellite Imagery Feature Detection
Stars: ✭ 117 (-25%)
Mutual labels: jupyter-notebook, segmentation
Unet Tgs
Applying UNET Model on TGS Salt Identification Challenge hosted on Kaggle
Stars: ✭ 81 (-48.08%)
Mutual labels: jupyter-notebook, semantic-segmentation
Fcn.tensorflow
Tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation (http://fcn.berkeleyvision.org)
Stars: ✭ 1,230 (+688.46%)
Mutual labels: jupyter-notebook, segmentation
Mit Deep Learning
Tutorials, assignments, and competitions for MIT Deep Learning related courses.
Stars: ✭ 8,912 (+5612.82%)
Mutual labels: jupyter-notebook, segmentation
Dilation Tensorflow
A native Tensorflow implementation of semantic segmentation according to Multi-Scale Context Aggregation by Dilated Convolutions (2016). Optionally uses the pretrained weights by the authors.
Stars: ✭ 134 (-14.1%)
Mutual labels: segmentation, semantic-segmentation
Segmentation
Tensorflow implementation : U-net and FCN with global convolution
Stars: ✭ 101 (-35.26%)
Mutual labels: segmentation, semantic-segmentation
Vision4j Collection
Collection of computer vision models, ready to be included in a JVM project
Stars: ✭ 132 (-15.38%)
Mutual labels: segmentation, semantic-segmentation
Fcn For Semantic Segmentation
Implemention of FCN-8 and FCN-16 with Keras and uses CRF as post processing
Stars: ✭ 155 (-0.64%)
Mutual labels: jupyter-notebook, semantic-segmentation
Relaynet pytorch
Pytorch Implementation of retinal OCT Layer Segmentation (with trained models)
Stars: ✭ 63 (-59.62%)
Mutual labels: jupyter-notebook, segmentation
Multi Task Refinenet
Multi-Task (Joint Segmentation / Depth / Surface Normas) Real-Time Light-Weight RefineNet
Stars: ✭ 139 (-10.9%)
Mutual labels: jupyter-notebook, semantic-segmentation
Keras DeepLab V3.1+
DeepLab V3+ for Semantic Image Segmentation With Subpixel Upsampling Layer Implementation in Keras
Added Tensorflow 2 support - Nov 2019
DeepLab is a state-of-art deep learning model for semantic image segmentation. Original DeepLabV3 can be reviewed here: DeepLab Paper with the original model implementation.
Features
- Conditional Random Fields (CRF) implementation as post-processing step to aquire better contour that is correlated with nearby pixels and their color. See here: Fully-Connected CRF
- Custom image generator for semantic segmentation with large augmentation capabilities.
New Features That Are Not Included In The Paper
- Keras Subpixel (Pixel-Shuffle layer) from: Keras-Subpixel for efficient upsampling and more accurate segmentation
- ICNR Initializer for subpixel layer (removing checkerboard artifact) ICNR
- Comparisson of the original Deeplab model with my Deeplab+subpixel+CRF
- Fast training - transfer learning from paper's proposed model to a better model within ~1 hour with 1-1080Ti GPU
- Jaccard (mIOU) monitoring during training process for multi-class segmentation tasks.
- Adaptive pixel weights.
Results
I've compared the segmentation visual results and the IOU score between paper's model and mine, as well as the outcome of applying CRF as a post-processing step.
Below depicted few examples:
And the IOU score amid the classes:
I didn't receive a significant improvement of the IOU scores, perhaps due to low number of epochs. However I believe this method can eventually outperform the original model for a bigger dataset and more epochs.
Dependencies
- Python 3.6
- Keras>2.2.x
- pydensecrf
- tensorflow > 1.11
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].