代码错误

[kx-kexi]

in_coordinate, out_coordinate = det(image, "icon", groundingdino_model)
这里返回两个值，但是方法只返回了一个值，是不是有错误啊，代码在Mobile-Agent/run.py 的149行
def det(input_image_path, caption, groundingdino_model, box_threshold=0.05, text_threshold=0.5):
image = Image.open(input_image_path)
size = image.size

caption = caption.lower()
caption = caption.strip()
if not caption.endswith('.'):
    caption = caption + '.'

inputs = {
    'IMAGE_PATH': input_image_path,
    'TEXT_PROMPT': caption,
    'BOX_TRESHOLD': box_threshold,
    'TEXT_TRESHOLD': text_threshold
}

result = groundingdino_model(inputs)
print(result)
boxes_filt = result['boxes']

H, W = size[1], size[0]
for i in range(boxes_filt.size(0)):
    boxes_filt[i] = boxes_filt[i] * torch.Tensor([W, H, W, H])
    boxes_filt[i][:2] -= boxes_filt[i][2:] / 2
    boxes_filt[i][2:] += boxes_filt[i][:2]

boxes_filt = boxes_filt.cpu().int().tolist()
filtered_boxes = remove_boxes(boxes_filt, size)  # [:9]
coordinates = []
for box in filtered_boxes:
    coordinates.append([box[0], box[1], box[2], box[3]])

return coordinates

[junyangwang0410]

in_coordinate, out_coordinate = det(image, "icon", groundingdino_model) 这里返回两个值，但是方法只返回了一个值，是不是有错误啊，代码在Mobile-Agent/run.py 的149行 def det(input_image_path, caption, groundingdino_model, box_threshold=0.05, text_threshold=0.5): image = Image.open(input_image_path) size = image.size

caption = caption.lower()
caption = caption.strip()
if not caption.endswith('.'):
    caption = caption + '.'

inputs = {
    'IMAGE_PATH': input_image_path,
    'TEXT_PROMPT': caption,
    'BOX_TRESHOLD': box_threshold,
    'TEXT_TRESHOLD': text_threshold
}

result = groundingdino_model(inputs)
print(result)
boxes_filt = result['boxes']

H, W = size[1], size[0]
for i in range(boxes_filt.size(0)):
    boxes_filt[i] = boxes_filt[i] * torch.Tensor([W, H, W, H])
    boxes_filt[i][:2] -= boxes_filt[i][2:] / 2
    boxes_filt[i][2:] += boxes_filt[i][:2]

boxes_filt = boxes_filt.cpu().int().tolist()
filtered_boxes = remove_boxes(boxes_filt, size)  # [:9]
coordinates = []
for box in filtered_boxes:
    coordinates.append([box[0], box[1], box[2], box[3]])

return coordinates

感谢纠正，我们不小心混淆了v1和v2的图标检测流程，现在已经修复。