Formatting coordinates.

[coneill65]

I recently came across yolov5 and thought it was very cool, naturally, I started experimenting with implementations, but when it came to a project where I needed the coordinates I could only get complicated numbers instead of pixel coordinates. here is what I got.

tensor([[7.49630e+02, 4.29638e+01, 1.14836e+03, 7.08850e+02, 8.77349e-01, 0.00000e+00],
[4.33616e+02, 4.33966e+02, 5.17898e+02, 7.15169e+02, 6.60622e-01, 2.70000e+01],
[1.13806e+02, 1.96342e+02, 1.09395e+03, 7.10243e+02, 5.93856e-01, 0.00000e+00],
[9.86161e+02, 3.04386e+02, 1.02795e+03, 4.20336e+02, 2.87125e-01, 2.70000e+01]])

I am using python for this and am wondering how I can change the first 4 numbers into pixel coordinates, or if there is another better way of doing this.

Here is my code

import torch

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)

# Image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'  # batched list of images

# Inference
results = model(img)

# Results
results.print()
results.show()  # or .show()

# Data
print(results.xyxy[0])  # print img1 predictions (pixels)
#                   x1           y1           x2           y2   confidence        class
# tensor([[7.50637e+02, 4.37279e+01, 1.15887e+03, 7.08682e+02, 8.18137e-01, 0.00000e+00],
#         [9.33597e+01, 2.07387e+02, 1.04737e+03, 7.10224e+02, 5.78011e-01, 0.00000e+00],
#         [4.24503e+02, 4.29092e+02, 5.16300e+02, 7.16425e+02, 5.68713e-01, 2.70000e+01]])

[coneill65]

I actually found this answer after searching for it for what seems like the 100'th time, so here it is.

print(results.pandas().xyxy[0])

[glenn-jocher]

Your code is from an outdated example. The current YOLOv5 PyTorch Hub Tutorial shows the nice pandas output:

import cv2
import torch
from PIL import Image

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')

# Images
for f in ['zidane.jpg', 'bus.jpg']:
    torch.hub.download_url_to_file('https://ultralytics.com/images/' + f, f)  # download 2 images
img1 = Image.open('zidane.jpg')  # PIL image
img2 = cv2.imread('bus.jpg')[..., ::-1]  # OpenCV image (BGR to RGB)
imgs = [img1, img2]  # batch of images

# Inference
results = model(imgs, size=640)  # includes NMS

# Results
results.print()  
results.save()  # or .show()

results.xyxy[0]  # img1 predictions (tensor)
results.pandas().xyxy[0]  # img1 predictions (pandas)
#      xmin    ymin    xmax   ymax  confidence  class    name
# 0  749.50   43.50  1148.0  704.5    0.874023      0  person
# 1  433.50  433.50   517.5  714.5    0.687988     27     tie
# 2  114.75  195.75  1095.0  708.0    0.624512      0  person
# 3  986.00  304.00  1028.0  420.0    0.286865     27     tie