A problem about the inference of gray image(8 bit image)

[DsLipku]

When I try to restore 00017_gray.png this image(a gray, 8-bit image) ,

using command "python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs --face_enhance --fp32",

the following problem occured:

Traceback (most recent call last): File "C:/Users/qingfeng/Desktop/Real-ESRGAN/inferencerealesrgan.py", line 145, in main , _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True) File "D:\Anaconda3\envs\Real-ESRGAN\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context return func(*args, kwargs) File "D:\Anaconda3\envs\Real-ESRGAN\lib\site-packages\gfpgan\utils.py", line 145, in enhance restored_img = self.face_helper.paste_faces_to_input_image(upsample_img=bg_img) File "D:\Anaconda3\envs\Real-ESRGAN\lib\site-packages\facexlib\utils\face_restoration_helper.py", line 355, in paste_faces_to_input_image upsample_img = inv_soft_mask pasted_face + (1 - inv_soft_mask) upsample_img ValueError: operands could not be broadcast together with shapes (1404,2000,1) (1404,2000)**

In this statement "upsample_img = inv_soft_mask pasted_face + (1 - inv_soft_mask) upsample_img", the shape of inv_soft_mask is (1404,2000,1), the shape of pasted_face is (1404,2000,3) and the shape of upsample_img is (1404,2000).

[Dalaoyel]

我也遇到这个问题了，你有好的解决办法吗

[DsLipku]

我也遇到这个问题了，你有好的解决办法吗

预处理一下灰度图，将灰度图的单通道复制成三通道，代码如下

[Dalaoyel]

我也遇到这个问题了，你有好的解决办法吗

预处理一下灰度图，将灰度图的单通道复制成三通道，代码如下

这非常管用，谢谢你

[jackecust]

我也遇到这个问题了，你有好的解决办法吗

预处理一下灰度图，将灰度图的单通道复制成三通道，代码如下

it is very good, really thanks