python for segment is not working

[ghost]

this is a crack segment detection for python.

import yolov5
from yolov5.segment import train, val, predict


# load model
model = yolov5.load('weights/wall.pt')
  
# set model parameters
model.conf = 0.25  # NMS confidence threshold
model.iou = 0.45  # NMS IoU threshold
model.agnostic = False  # NMS class-agnostic
model.multi_label = False  # NMS multiple labels per box
model.max_det = 1000  # maximum number of detections per image

# set image
img = 'crack.jpg'

# perform inference
results = model(img)

# inference with larger input size
results = model(img, size=640)

# inference with test time augmentation
results = model(img, augment=True)

# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]



# save results into "results/" folder
results.save(save_dir='AA')

but img result did not show segment polygon, only show bbox.

if i use cli, it will be displayed segment. it is so weird.
(yolov5 segment predict --img 640 --weights weights/wall.pt --source crack.jpg)

can you fix it?