关于预测时的问题

[HouseWay]

Model loaded successfully from 'sam_model/VAE.pth'
第1张图: 1.bmp
prepare to cut DM from the image...
Traceback (most recent call last):
File "D:\JetBrains\PyCharm 2021.1.3\plugins\python\helpers\pydev\pydevd.py", line 1483, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "D:\JetBrains\PyCharm 2021.1.3\plugins\python\helpers\pydev_pydev_imps_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "F:/Halcon/DeepLearning/Unsupervised-Defect-Detection-Project-Based-on-VAE-GAN-Architecture-master/main.py", line 205, in
score, diff_bin = defection_detection(os.path.join(input_dir, filename), VAE_model=VAE_model,
File "F:/Halcon/DeepLearning/Unsupervised-Defect-Detection-Project-Based-on-VAE-GAN-Architecture-master/main.py", line 84, in defection_detection
mask_image, coordinates, mask, info = cut_target_from_image(image, reason_mode=reason_mode)
File "F:\Halcon\DeepLearning\Unsupervised-Defect-Detection-Project-Based-on-VAE-GAN-Architecture-master\CutTarget.py", line 217, in cut_target_from_image
masked_image_cut, cropped_mask = apply_mask(cropped_image, cropped_mask)
File "F:\Halcon\DeepLearning\Unsupervised-Defect-Detection-Project-Based-on-VAE-GAN-Architecture-master\CutTarget.py", line 113, in apply_mask
alpha[mask] = 255 # 兴趣地方标记为1,且为白色
IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed

出现了这个报错

[DEVILENMO]

apply_mask 这个函数应该就是把图像基于SAM分割的结果做一下去除外围，你看一下是不是SAM分割出来的mask是空的了？因为分割的时候基于那个辨别器去判断分割出来的是不是真实结果了，你可以修改一下判断的逻辑