Project Name | Stars | Downloads | Repos Using This | Packages Using This | Most Recent Commit | Total Releases | Latest Release | Open Issues | License | Language |
---|---|---|---|---|---|---|---|---|---|---|
Batchgenerators | 1,013 | 6 | 22 | 4 months ago | 16 | March 16, 2023 | 40 | apache-2.0 | Jupyter Notebook | |
A framework for data augmentation for 2D and 3D image classification and segmentation | ||||||||||
All About The Gan | 602 | 6 years ago | 1 | mit | Python | |||||
All About the GANs(Generative Adversarial Networks) - Summarized lists for GAN | ||||||||||
Unet In Tensorflow | 157 | 6 years ago | 10 | mit | Jupyter Notebook | |||||
U-Net implementation in Tensorflow | ||||||||||
Cloud Volume | 120 | 13 | 23 | 5 months ago | 319 | October 19, 2023 | 83 | bsd-3-clause | Python | |
Read and write Neuroglancer datasets programmatically. | ||||||||||
Freespace_segmentation_ _ford_otosan_intern | 51 | 3 years ago | Python | |||||||
Determination of drivable area in highway images with semantic segmentation. | ||||||||||
Simple Tensor | 17 | a year ago | 2 | mit | Python | |||||
A simplification of Tensorflow Tensor Operations | ||||||||||
Keras Imagedatagenerator | 11 | 5 years ago | 1 | Python | ||||||
A customized real-time ImageDataGenerator for Keras | ||||||||||
Tensormask Review | 10 | 5 years ago | gpl-3.0 | |||||||
Sliding-window object detectors that generate boundingbox object predictions over a dense, regular grid have advanced rapidly and proven popular. In contrast, modern instance segmentation approaches are dominated by methods that first detect object bounding boxes, and then crop and segment these regions, as popularized by Mask R-CNN. In this work, we investigate the paradigm of dense slidingwindow instance segmentation, which is surprisingly underexplored. Our core observation is that this task is fundamentally different than other dense prediction tasks such as semantic segmentation or bounding-box object detection, as the output at every spatial location is itself a geometric structure with its own spatial dimensions. To formalize this, we treat dense instance segmentation as a prediction task over 4D tensors and present a general framework called TensorMask that explicitly captures this geometry and enables novel operators on 4D tensors. We demonstrate that the tensor view leads to large gains over baselines that ignore this structure, and leads to results comparable to Mask R-CNN. These promising results suggest that TensorMask can serve as a foundation for novel advances in dense mask prediction and a more complete understanding of the task. Code will be made available. |