Mohammed Innat

Results 89 issues of Mohammed Innat

**Short Description** AKA, You Only Look Once. A strong object detection model, described in the following paper. **Papers** https://arxiv.org/abs/1804.02767?fbclid=IwAR3A2nyK8EPa-JcoGp_N6tNqVkKOmy2J1ip5AYcEki5FzkZ62E3z6tbNSy0 Published on: 2018 Cited by 14236 (until) **Existing Implementations** Here is...

**Short Description** A two stage object detection model, strongly well-known for its detection and instance-wise simultaneous output. **Papers** https://arxiv.org/abs/1703.06870 Publish date: 2017 Cited by **20059** (until now) **Existing Implementations** A...

models
roadmap
type:feature
high-priority

If you open a GitHub issue, here is our policy: It must be a bug, a feature request, or a significant problem with the documentation (for small docs fixes please...

contribution-welcome
type:feature

Close https://github.com/keras-team/keras-cv/issues/296 ![image](https://user-images.githubusercontent.com/17668390/165566477-fc0a81d6-848e-4ad3-af03-20211a22964c.png) Ps. Tested on actual training, works fine so far for 2D and 3D cases; now needs some polish.

review-needed

Mosaic augmentation for object detection is used in Yolo-V4 literature, [FR](https://github.com/keras-team/keras-cv/issues/21). I'm not sure if it's used for classification tasks there. I was wondering if it's possible to do so...

contribution-welcome
preprocessing

This type of augmentation is mostly sued in 2D and 3D image augmentation, especially in medical imaging. - [Source](https://albumentations.ai/docs/api_reference/augmentations/geometric/transforms/#albumentations.augmentations.geometric.transforms.ElasticTransform). TensorFlow (DeepMind): [How to use the On-the-Fly Elastic Deformation for TensorFlow](https://github.com/deepmind/multidim-image-augmentation/blob/master/doc/elastic_deformation_colab.md...

stat:contributions welcome
preprocessing
type:feature
stale

**Short Description** **RetinaNet**, an object detection as described in the following paper. **Papers** https://arxiv.org/abs/1708.02002 publish date: 2017 Cited by 14612 (until) **Existing Implementations** Here is one well known and strong...

**Short Description** This function computes Cohen’s kappa, a score that expresses the level of agreement between two annotators on a classification problem. It is defined as ![image](https://user-images.githubusercontent.com/17668390/169282603-96865edb-8ac9-430b-a31c-128e6b0ff34c.png) where `p_0` is...

**System information**. TensorFlow version (you are using): 2.8 Are you willing to contribute it (Yes/No) : No (but willing to provide starter if required.) **Describe the feature and the current...

contribution-welcome
losses
type:feature

## Describe the feature Run-Length-Encoding or **RLE** is one of the encoded annotation formats mostly for the segmentation task. It would be nice to have a **utility** function to **encode**...