[FEATURE] Add important tutorials to hub docs

[istranic]

🚨🚨 Feature Request

• [ ] Related to an existing Issue
• [ ] A new implementation (Improvement, Extension)

Is your feature request related to a problem?

Hub docs are missing the following tutorials in order of priority:

• Training an object detection model in Pytorch
• Training a segmentation model in Pytorch
• Training a classification model in TensorFlow
• Training an object detection model in TensorFlow
• Training a segmentation model in TensorFlow

Tips for completing the task

• All of these tutorials can use the COCO dataset, because it contains all of the data types that are required above.
• When training the models, only the tensors that contain the relevant data should be loaded for training.
• The tutorials should be written in Gitbook and Colab
• The tutorials should use a similar style to the existing classification tutorial
• The focus of the tutorials is the data and data pre-processing. The model and training process should be as simple as possible.

If your feature will improve HUB

It will provide users helpful starter-code for training different types of models

[istranic]

@Manas2030

[Manas2030]

Hey @istranic, I'll work on the tutorials. 🙂

[istranic]

Hey @Manas2030 Just making sure that you're still working on this? How is progress so far? Do you need any assistance?

[jaivanti]

Is this issue still open? I would love to work on it?

[istranic]

Hi @jaivanti The PyTorch components are complete, but the TensorFlow ones are not. Are you interested in those?

[jaivanti]

Yes! I would go for it

[istranic]

Hi @jaivanti Great. I think the best approach would be to implement the tutorial below using hub's TensorFlow integration.

https://docs.activeloop.ai/hub-tutorials/training-an-object-detection-and-segmentation-model-in-pytorch

Let me know if you have any questions.

[jaivanti]

Thanks @istranic So just want to confirm....I just have to build a similar pipeline as that mentioned in the link but i gotta do it in Tensorflow?