The way to save the disparity into image

[keishatsai]

Hi,
I follow the demo code and try to save the depth image by using test_kitti_depth.py
Images I saved are not what I expected.......
The original input image:

The predicted depth:

The resized predicted depth:

those predictions I saved don't look like a proper depth map. Is there anything that I misunderstood?
Here is my code:

pred = sfm.inference(inputs, sess, mode='depth')
pred_disp = normalize_depth_for_display(pred['depth'][0,:,:,0])
cv2.imwrite('data/kitti/raw_disp.png', pred_disp)
fh_disp = open('data/kitti/raw_disp.png', 'r')
raw_disp = pil.open(fh_disp)
img_disp = raw_disp.resize((1242, 375), pil.ANTIALIAS)
img_disp.save('data/kitti/disp_resize.png')

Thanks

[keishatsai]

I found that I should use matplotlib to save my instead of using opencv.
Now it is correct.

[WANGYINGYU]

@keishatsai
Hello,
I also have this problem,and I use plt.savefig() instead of using imwrite(),but I found plt.savefig() save image same as using imshow().Actually,I want get depth map and use it in other program and I want to know how to do it,can you give me some suggests?
Thank you.