segmentation_models VS ultralytics

Also, I’d suggest considering switching to the segmentation-models library - it provides U-Net models with a variety of pretrained backbones of as encoders. The author also put out a PyTorch version. https://github.com/qubvel/segmentation_models.pytorch https://github.com/qubvel/segmentation_models

I used segmentation-models (https://github.com/qubvel/segmentation_models) to create a deeplabv3+ model. I havent used it in the last 2 months and now i comeback to the same code and cant use it. Getting ModuleNotFoundError: No module named 'segmentation_models_pytorch.deeplabv3'

I'm building some semantic segmentation models off of low-moderate volumes of biomedical images (~500 - 1k images). So far I've done some hyperparameter sweeping (learning rate, transfer learning, architectures, dropout layers) using the Segmentation Models package from qubvel https://github.com/qubvel/segmentation_models but I'm only seeing moderate performance and minimal differences between tested parameters.

So, image segmentation (especially for satellite images) is a known problem. Search for semantic segmentation and unet (a model used for semantic segmentation). Also, if you use tensorflow there is this library which I found useful segmentation models.

I am doing an image segmentation project using https://github.com/qubvel/segmentation_models as the baseline. I was wondering if any of you have tried the latest segmentation models from cvpr papers. If yes, which ones you found to be interesting or actually improve miou. And how difficult/easy it is to implement those?

That is just U-net from this repo, anything aside is slicing images to fit into window and predict call. I measure time of predict() and it is the same as profiler numbers, so definitely my other operations are beyond profiler. C API code is just creating tensors and calling TF_SessionRun plus slice operations with opencv. Can't post code, sorry.

I'm trying to train image segmentation model with transfer learning using https://github.com/qubvel/segmentation_models/.

Yep, I noticed this a while ago. It posts easily identifiable ChatGPT responses. It also posts garbage wrong answers which makes it worse than useless. Totally disrespectful to the userbase.

https://github.com/ultralytics/ultralytics/issues/5748#issue...

There are obvious places it is being used that I have noticed organically. For instance, check out the answers in this repo:

https://github.com/ultralytics/ultralytics/issues/5748#issue...

If you read the answers there, the style of answering is always to repeat the question in a very specific way. Once you see it you can’t in-see it.

When browsing the state-of-the-art in object detection on Papers with Code, I found the YOLO model to be one of the most popular, accurate, and fastest. That being said, I would recommend having a look at Ultralytics, which provides the tools to evaluate, predict, and export the latest versions of YOLO models with only a few lines of code.

YOLOv8 (You Only Look Once) is an open-source Computer Vision AI model released on January 10th, 2023. It’s called YOLO because it detects everything inside an image in a single pass. The new version can perform image detection, classification, instance segmentation, tracking, and pose estimation tasks.

Next, I needed to figure out, how can I access the stream, recognize an animal, then let Max know? There are tons of examples of recognizing an object via camera frames, but I ultimately found this python library called ultralytics that supports RTSP streams and classifying objects in the video frames using pre-built models. The docs looked like it would be pretty low effort, so after some experimentation, I was successful in having the ultralytics library recognize objects from my cheap camera!

I have created an issue in their Github as well but so far not much help has been recieved. You can check that here

And the target models include: * YOLOv8 (You Only Look Once) * YOLO-NAS * YOLOv5 * and DETR