Save detected images error

1 
for i in range(len(boxes)):
        if i in indexes:
            x, y, w, h = boxes[i]
            label = str(classes[class_ids[i]])
            color = colors[class_ids[i]]
            cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
            cv2.putText(img, label, (x, y + 30), font, 3, color, 2)
            crop_img = img[y: y + h, x: x + w]
            if label == 'wearing':
                wearing = wearing+1
                wearing_count = wearing_count+1
                cv2.imwrite(os.path.join(output_crop_wearing,str(x)+'.jpg'),crop_img)
            elif label == 'notwearing':
                notwearing = notwearing+1
                notwearing_count = notwearing_count+1
                cv2.imwrite(os.path.join(output_crop_notwearing,str(x)+'.jpg'),crop_img)

Traceback (most recent call last):
  File "/model/test_yolo_object_detection.py", line 143, in <module>
    cv2.imwrite(os.path.join(output_crop_wearing,str(x)+'.jpg'),crop_img)
cv2.error: OpenCV(4.5.1) /private/var/folders/nz/vv4_9tw56nv9k3tkvyszvwg80000gn/T/pip-req-build-39p1qqfs/opencv/modules/imgcodecs/src/loadsave.cpp:753: error: (-215:Assertion failed) !_img.empty() in function 'imwrite'

I looped through the input images folder and there are some folder that show the error like this

I tried print the value of x,y,w,h
everytime loop stop at when x= -1, y= 193, w= 8, h= 12
I thought that it because the negative x
so I set the condition if any of them is negative I will set that value to 1
but the error still occur as the same

2

please update your question code, then

(and yes, YOLO networks can return out-of-bounds coords, so it’s a good idea to be cautious)

3 
if x < 0:
                    x = 1
                if y < 0:
                    y = 1
                if w < 0:
                    w = 1
                if h < 0:
                    h = 1
                print("x= "+str(x)+" y= "+str(y)+" w= "+str(w)+" h= "+str(h))

I just set things like this in each if condition ‘wearing’ and ‘notwearing’

even the value is no longer negative but it still shown error

x= 1 y= 193 w= 8 h= 12
Traceback (most recent call last):
  File "/Users/khemakorn/Desktop/model/test_yolo_object_detection.py", line 152, in <module>
    cv2.imwrite(os.path.join(output_crop_wearing,str(x)+'.jpg'),crop_img)
cv2.error: OpenCV(4.5.1) /private/var/folders/nz/vv4_9tw56nv9k3tkvyszvwg80000gn/T/pip-req-build-39p1qqfs/opencv/modules/imgcodecs/src/loadsave.cpp:753: error: (-215:Assertion failed) !_img.empty() in function 'imwrite'
4

that’s too late (and no need to duplicate that)
you have to check bounds before cropping the image
please also check, if your crop is valid

5

Oh it works correctly now, Thanks.