Get live statistics and analysis of Marco Franzon's profile on X / Twitter

This is the power of YOLO, trained on a laptop for ~1 hour, with a Kaggle dataset. Oh, and just ~100 lines of Python. I can make a startup on this and it took me literally a couple of hours.

I am setting up a GitHub repo, let me write down the steps to reproduce it, some docs and I'll let you train your YOLO 😆

The DIY Pothole Detection System is becoming real. - Dash cam captures real-time road footage - Raspberry Pi runs inference and processes data - GPS module gets coordinates of detected potholes It is a low-cost solution and literally everybody can do it.

Calculating pothole volume from a 2D image is challenging but possible: > Assign each pothole an ID to avoid duplication. > Use basic trigonometry to convert pixels to real-world meters. > Apply a novel algorithm to estimate depth using road engineering data.

Consider taking this Robotics Course from HuggingFace. The syllabus is impressive, covering topics from robotics foundations to reinforcement learning. It's an excellent way to start with robotics and build your first robot.

Don't buy GPUs, buy MCUs. Start with a simple microPython application, more approachable than C. Add sensors, install a webserver, and control remotely. AI? Use models from Arduino App Lab, then distill your custom models. Build your own robot.

It is almost done. As many of you have asked me to make a reproducible notebook, I have decided to put a little bit more effort and making a GitHub repo. In it I add a notebook easily adaptable for many different use cases. So a little bit of patience and I'll make it public😁

I will clean up woods and forests with Python: > Automatically label images with GroundingDINO. > Use the dataset to train a YOLO model. > Recognize litter in forests. I just need a drone with a harvesting tool to make forests great again.

Today something crazy happened to me. I would never have thought to reach 1 million of you. Learn Python today, it will change your life.

The GitHub repository with a template to reproduce this and many more image recognition tasks is public. I made it as simple as possible so everybody can play with it . If you run out of ideas, I also leave a list of cool Kaggle datasets to play with. Check the first comment!

I received a lot of DMs about my last CV post for pothole recognition. A lot of you want to see the code, don't worry I am going to publish a notebook for that soon. Some of you also wrote me other ideas like a bacteria counter, or a car counter. Let's do it together!

8 views on Youtube. Such a great success🚀🤣

Making the GUI for real so now everybody can: > create a labeled dataset > train a YOLO model > use it for inference on images or videos No code needed. Just a bunch of images and a cool idea.

This is the power of YOLO, trained on a laptop for ~1 hour, with a Kaggle dataset. Oh, and just ~100 lines of Python. I can make a startup on this and it took me literally a couple of hours.

I am setting up a GitHub repo, let me write down the steps to reproduce it, some docs and I'll let you train your YOLO 😆

8 views on Youtube. Such a great success🚀🤣

The DIY Pothole Detection System is becoming real. - Dash cam captures real-time road footage - Raspberry Pi runs inference and processes data - GPS module gets coordinates of detected potholes It is a low-cost solution and literally everybody can do it.

Calculating pothole volume from a 2D image is challenging but possible: > Assign each pothole an ID to avoid duplication. > Use basic trigonometry to convert pixels to real-world meters. > Apply a novel algorithm to estimate depth using road engineering data.

I will clean up woods and forests with Python: > Automatically label images with GroundingDINO. > Use the dataset to train a YOLO model. > Recognize litter in forests. I just need a drone with a harvesting tool to make forests great again.

Today something crazy happened to me. I would never have thought to reach 1 million of you. Learn Python today, it will change your life.

Don't buy GPUs, buy MCUs. Start with a simple microPython application, more approachable than C. Add sensors, install a webserver, and control remotely. AI? Use models from Arduino App Lab, then distill your custom models. Build your own robot.

This is something unbelievable. I have never seen a growth like that. In a single day, my account goes from 2k to 6k followers and over 3M of impressions. Thank you so much!! I hope you will enjoy my content😁

It is almost done. As many of you have asked me to make a reproducible notebook, I have decided to put a little bit more effort and making a GitHub repo. In it I add a notebook easily adaptable for many different use cases. So a little bit of patience and I'll make it public😁

Consider taking this Robotics Course from HuggingFace. The syllabus is impressive, covering topics from robotics foundations to reinforcement learning. It's an excellent way to start with robotics and build your first robot.

What is your experience with github actions? Are you using frequently or never heard about them?

I received a lot of DMs about my last CV post for pothole recognition. A lot of you want to see the code, don't worry I am going to publish a notebook for that soon. Some of you also wrote me other ideas like a bacteria counter, or a car counter. Let's do it together!

Computer vision is changing my life. I need more gpus.