pytorch hub and detect.py gives different results

[kzyadaking]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

im using win32 instead of pill or mss for screengrab because this way its way faster than those two.
but the problem is sometimes it doesnt detect well compared to using detect.py. i have no idea where to look at.
does anyone have an idea?

import torch
import numpy as np
import win32gui
import win32ui
import win32con



w = 800 # set this
h = 600 # set this
bmpfilenamename = "color.bmp" #set this
windowname = 'put windowname'


def screenshot():
    hwnd = win32gui.FindWindow(None, windowname)
    wDC = win32gui.GetWindowDC(hwnd)
    dcObj=win32ui.CreateDCFromHandle(wDC)
    cDC=dcObj.CreateCompatibleDC()
    dataBitMap = win32ui.CreateBitmap()
    dataBitMap.CreateCompatibleBitmap(dcObj, w, h)
    cDC.SelectObject(dataBitMap)
    cDC.BitBlt((0,0),(w, h) , dcObj, (0,0), win32con.SRCCOPY)

#save the screenshot
#dataBitMap.SaveBitmapFile(cDC, bmpfilenamename)

signedIntsArray = dataBitMap.GetBitmapBits(True)
img = np.frombuffer(signedIntsArray, dtype='uint8')
img.shape = (h,w,4)

# Free Resources
dcObj.DeleteDC()
cDC.DeleteDC()
win32gui.ReleaseDC(hwnd, wDC)
win32gui.DeleteObject(dataBitMap.GetHandle())

#img = img[..., ::-1]
#img = np.ascontiguousarray(img)

return img

#load
model = torch.hub.load('./', 'custom', path='yolov5s.pt', source='local')


#inference
test = screenshot()
results = model(test)
boxes = results.pandas().xyxy[0]
print (boxes)

Additional

No response

[github-actions]

👋 Hello @kzyadaking, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://ultralytics.com or email support@ultralytics.com.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Google Colab and Kaggle 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 YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), validation (val.py), inference (detect.py) and export (export.py) on macOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@kzyadaking we don't assist in debugging custom code, but obviously I'd recommend you compare whatever the image your code is producing with the official screenshot inference example in our PyTorch Hub tutorial:

YOLOv5 Tutorials

• Train Custom Data  🚀 RECOMMENDED
• Tips for Best Training Results  ☘️ RECOMMENDED
• Weights & Biases Logging  🌟 NEW
• Roboflow for Datasets, Labeling, and Active Learning  🌟 NEW
• Multi-GPU Training
• PyTorch Hub  ⭐ NEW
• TFLite, ONNX, CoreML, TensorRT Export 🚀
• Test-Time Augmentation (TTA)
• Model Ensembling
• Model Pruning/Sparsity
• Hyperparameter Evolution
• Transfer Learning with Frozen Layers  ⭐ NEW
• Architecture Summary  ⭐ NEW

Good luck 🍀 and let us know if you have any other questions!

[kzyadaking]

@glenn-jocher thanx for the reply. i found a solution! for those who might be interested,

#change this 
results = model(test) 

#to this
results = model(cv.cvtColor(test, cv.COLOR_BGR2RGB))

[github-actions]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!

[glenn-jocher]

Glad to hear you found a solution, @kzyadaking! Thanks for sharing it with the community. Your contribution is valuable 💪. Let us know if you need further assistance or have any more tips to share!