Interested in parsing any custom object detection dataset format?

I will show you how easy to parse your dataset, and train one of many IceVision models using your own data.

In this post, I walk you through the steps to parse data stored in CSV files by using the Chess dataset
You can apply the same logic to any other format.

• First, both COCO and VOC formats are transparently supported in IceVision.

• The CSV format is different than the COCO and VOC formats. Hence, the custom parsing.

• IceVision auto-generates your parser class skeleton.
• You only need to connect some attributes to their corresponding ones in your CSV file

• Once done, you instantiate your class, and parse your data

• From there, all the subsequent code is common to any other parsed data.

• Parsed data are a collection of record objects
🧊 To train your model, walk through the following steps.

1- Create both train and validation Datasets: IceVision uses a random split (80% and 20%). You can use other splitters
2- Pick any IceVision model

3- Create both train and validation DataLoaders

4- Find an optimal Learning Rate (optional)

5- Train your model using either Fastai or Pytorch-Lightning

6- Do a batch inference (prediction) to visually check your model performance
Those are the common steps: 1 to 6
Choosing one of the IceVision models
Notebook: lnkd.in/em8JGgtt

⭐️ If you are interested in mastering Object Detection (OD), follow @ai_fast_track, and get highly curated content in your feed.

⭐️Please give this thread a quick retweet, and help others discover this content.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with AI Fast Track (40/45)

AI Fast Track (40/45) Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @ai_fast_track

8 Dec
The paradox of "too old" / "too young" to get a job in a new/another field because of lack of experience.

Here is a trick to overcome that archaic rule:

⭐ Set aside the Impostor Syndrome, and focus on your learning and sharing

... Image
📌 Join a friendly/helpful community (e.g., @fastdotai, IceVision, etc.)

⭐ Bond with some members, and build a genuine friendship: Be authentically genuine and thoughtful. People will recognize that.

📌 Work on mini-projects that would interest companies you want to join
⭐ Share those projects on GitHub without fear: Nobody will judge you. People are too busy with their own sh*t

📌 Share your progress with your community (ies), and ask for feedback (community and/or friends)
Read 6 tweets
6 Dec
🎉Part 2- Summary of 10 summaries on:

Tips & Trick & Best Practices in training (not only) object detection models.

Don't miss any of those posts, follow @ai_fast_track to catch them in your feed.

🎁 Summary of summaries: ...
1- Training Object Detection Models Tips & Tricks

2- Pro Tip to fast track your object detection training

Read 12 tweets
5 Dec
Interested in testing several object detection models in one single notebook, in @kaggle Competitions?

Here is a getting started notebook where you could test 5 different models: VFNet, EfficientDet, RetinaNet, Faster-RCNN, and YOLOv5.

🎁 Kaggle NB: kaggle.com/faridone/icevi…
The kaggle notebook is a stripped one. Check out the long version in Colab.

🎁 Colab NB: airctic.com/0.11.0/getting…

That way, you have access to 2 platforms where you get familiar with IceVision
We have a #kaggle dedicated channel in our IceVision forum where kagglers share their knowledge.

• IceVision Forum: discord.gg/JDBeZYK

• IceVision Repo: github.com/airctic/IceVis…
Read 4 tweets
4 Dec
💡 Prop Tip to 🚀 fast track your object detection training

All @fastdotai users use this method for free!

It's fine_tune()

We noticed an important increase in the COCO Metric when we train object detection models using this method even with the simple default values
Fine tuning has 2 phases:

🧊 Phase 1: Freeze your model's backbone and neck. Train your model for a couple of epochs (e.g. 1 to 5)

📈 Phase 2: Unfreeze the whole model. Train for higher number of periods (depending on your dataset, and how hard/easy your data is)
Phase 1 is a kind of warm-up for your model head.

Here is an example showing how to call the fine_tune() method.

In this case, we freeze both the backbone and the neck for 1 epoch in phase 1, and train for 20 epochs in phase 2.
Read 5 tweets
2 Dec
Detecting small object detection is one of the most challenging tasks in object detection.

❓ Want to know an effective way to overcome that❓

Check out the SAHI integration in IceVision🧊
👇
All IceVision models transparently support SAHI (MMDetection, EfficientDet, Torchvision, and YOLOv5). The results are quite impressive!

SAHI is a very cool library that drastically improves detection of small objects.
📌 It is simply used at inference time

📌 It leverages high resolution images.

📌 Your training process remains the same as usual.

🔎 At the high level, this is how SAHI works:

1- It takes a high resolution (e.g.1920 x 1024 px), and divide it in patches (e.g. 128 x 128 px)
Read 7 tweets
30 Nov
🎉🎊🥳Day 30/30: Labeling data and training object detection models are time consuming and expensive.

Here is a Survey of Self-Supervised and Few-Shot Object Detection (FSOD). Those technique aim at alleviating those issues.
The authors have categorized, reviewed, and compared several few-shot and self-supervised object detection methods

📌 FSOD is about training a model on novel (unseen) object classes with little data. It still requires prior training on many labeled data of base (seen) classes
📌 Self-Supervised Learning (SSL) methods aim at learning representations from unlabeled data which transfer well to downstream tasks such as object detection

📌 Combining few-shot and self-supervised object detection is a promising research direction
Read 8 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

:(