[Explainer] Detectron2 & COCO Dataset πŸ”₯ β€’ Web Application & Visualizations β€’ End-to-End Baseline & Tensorflow

So, me Shubhamai and I have come up with these 3 things -

COCO Dataset & using Detectron2, MMDetection

YES! I have converted this dataset into COCO Dataset and which we train Mask-RCNN using Detectron2.

There we go boys - Colab Link

More things will be added so like this post RIGHT NOW :smile:

Web Application & Visualisation


But this time, I found that a great preprocessing pipeline can help to model to find accurate features and increasing overall accuracy. But it kinda isn’t that easy as it looks β€”

So I made a Web Application based on that which allows you to play/experiment with many of the image preprocessing functions/methods, changing parameters or writing custom image preprocessing functions to experiment.

And it also contains all the visualizations from the colab notebook .

I hope that it will help you in making the perfect preprocessing pipelines :grin:.

End-to-End Baseline & Tensorflow


I have made a complete colab notebook from Data Exploration to Submitting Predictions. Here are some of the glimpse of the image visualization section!

And this 3D Plot!

1100Γ—600 196 KB

Tables of Content -

  1. Setting our Workspace :briefcase:
  2. Data Exploration :face_with_monocle:
  3. Image Preprocessing Techniqes :broom:
  4. Creating our Dataset :hammer:
  5. Creating our Model :factory:
  6. Training the Model :steam_locomotive:
  7. Evaluating the model :test_tube:
  8. Testing on test Data :100:
  9. Generate More Data + Some tips & tricks :bulb:

The main libraries covered in this notebook is β€”

  • Tensorflow 2.0 & Keras
  • Plotly
  • cv2
    and much more…

The model that i am using is UNet, pretty much standard in image segmentation. More is in the colab notebook!

I hope the colab notebook will help you get started in this competition or learning something new :slightly_smiling_face:. If the notebook did help you, make sure to like the post. lol.


:red_circle: Please like the topic if this helps in any way possible :slight_smile: . I really appreciate that :smiley: