How to specify where to save the file in model.predict()?

Question

Here is my code:

from ultralytics import YOLO
model = YOLO('best.pt')
results = model.predict(
    source = '/Users/sereentaleb/Desktop/download.jpg',
    save=True,
    conf=0.25
)

This script will save my file in runs/detect/predict. However, I don't want it saved there. Is there a way to tell the function to save the file somewhere else? And is there a way to give the file (the file that I did the detection on) a name of my choosing?

I searched the ultralytics documentation for an answer and I couldn't find anything that helped.

SpareL · Accepted Answer · 2024-07-11 03:21:58Z

0

If you only need to save a small number of test results, you can try using the following method to save them to your desired location.

import cv2
import numpy as np
import matplotlib.pyplot as plt
from ultralytics import YOLO

# # Load the YOLOv8 model
model = YOLO('yolov8n.pt')
image_data = 'pic.png'

# read your image
img = cv2.imread(image_data)
# predict return result
result = model(img)[0].plot()
# save path
file_path = r'./save/save_img.jpg'
cv2.imwrite(file_path,result)

# show result
res = cv2.cvtColor(result, cv2.COLOR_BGR2RGB)
plt.imshow(res)
plt.axis('off')
plt.show()

# Note: This program originates from my own work. To meet the requirements of the problem,
# I utilized AI assistance in some parts. After successful implementation and reviewing the rules,
# I am publishing it.

edited Jul 11, 2024 at 3:21

answered Jul 11, 2024 at 2:58

SpareL

11 bronze badge

Sign up to request clarification or add additional context in comments.

1 Comment

Sereen Taleb Over a year ago

Ok, I got it. Thank you!!

Collectives™ on Stack Overflow

How to specify where to save the file in model.predict()?

1 Answer 1

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related