Detect module is running twice about ultralytics HOT 4 OPEN

👋 Hello @RUPESH-KUMAR01, thank you for your interest in Ultralytics YOLOv8 🚀! We recommend a visit to the Docs for new users where you can find many Python and CLI usage examples and where many of the most common questions may already be answered.

If this is a 🐛 Bug Report, please provide a minimum reproducible example to help us debug it.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.

Join the vibrant Ultralytics Discord 🎧 community for real-time conversations and collaborations. This platform offers a perfect space to inquire, showcase your work, and connect with fellow Ultralytics users.

Install

Pip install the ultralytics package including all requirements in a Python>=3.8 environment with PyTorch>=1.8.

pip install ultralytics

Environments

YOLOv8 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all Ultralytics CI tests are currently passing. CI tests verify correct operation of all YOLOv8 Modes and Tasks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

from ultralytics.

Hi @RUPESH-KUMAR01,

Thank you for reaching out and providing a detailed description of your issue! It sounds like you've done some great investigative work already. Let's see if we can get to the bottom of this.

Firstly, could you please provide a minimum reproducible code example? This will help us better understand the context and reproduce the issue on our end. You can find guidelines for creating a minimum reproducible example here. This step is crucial for us to investigate and resolve the issue effectively.

Additionally, please ensure that you are using the latest versions of torch and ultralytics. You can upgrade your packages using the following commands:

pip install --upgrade torch
pip install --upgrade ultralytics

Regarding the warmup run you mentioned, it's indeed a feature designed to optimize performance. However, seeing the output shapes three times is unusual and suggests that the forward pass might be executed more than expected. Once we have your reproducible code, we can delve deeper into this behavior.

Looking forward to your response so we can assist you further! 😊

from ultralytics.

These are the changes I have made in the detect module in head.py in the code.

Input for prediction by using the import YOLO and model.predict() written in a a.py file.

Here, I used a terminal-based approach for prediction. The first output on the top of the image is related to the a.py file (used in
first try) and the second one is through the terminal based approach.

from ultralytics.

Hi @RUPESH-KUMAR01,

Thank you for providing the detailed screenshots and explanation! It’s great to see your proactive approach in understanding the tensor inputs and strides in the detect module. 😊

To help us investigate this issue further, could you please provide a minimum reproducible code example? This will allow us to replicate the behavior on our end and pinpoint the cause. You can find guidelines for creating a minimum reproducible example here. This step is crucial for us to effectively diagnose and resolve the issue.

Additionally, please ensure that you are using the latest versions of torch and ultralytics. You can upgrade your packages using the following commands:

pip install --upgrade torch
pip install --upgrade ultralytics

From your description, it seems like the forward pass might be executed more than expected. This could be due to the warmup run or other internal mechanisms. Once we have your reproducible code, we can delve deeper into this behavior.

Looking forward to your response so we can assist you further! 😊

from ultralytics.