Hello @hahnec,

I couldn't create depth map with your program: depthy v0.3.0 installed via pip3.
When trying with the default test images, I get the following error:

load light-field images
Traceback (most recent call last):
  File "/usr/local/bin/depthy", line 8, in <module>
    sys.exit(main())
  File "/usr/local/lib/python3.7/site-packages/depthy/bin/cli.py", line 113, in main
    lf_img_arr = load_lf_arr(filenames)
  File "/usr/local/lib/python3.7/site-packages/depthy/misc/io_functions.py", line 53, in load_lf_arr
    fnames = sorted(fnames, key=lambda x: int(re.sub("[^0-9]", "", os.path.basename(x).split(".")[0])))
  File "/usr/local/lib/python3.7/site-packages/depthy/misc/io_functions.py", line 53, in <lambda>
    fnames = sorted(fnames, key=lambda x: int(re.sub("[^0-9]", "", os.path.basename(x).split(".")[0])))
ValueError: invalid literal for int() with base 10: ''

When trying with one of my image (a .png), it stops relatively early after ~2s, I get the following:

load light-field images
compute depth from epipolar images
/usr/local/lib/python3.7/site-packages/depthy/lightfield/epi_depth.py:107: RuntimeWarning: invalid value encountered in
true_divide
  disparity = np.mean(disp_arr*reli_arr**2, axis=-1) / confidence
export depth as ply and pfm file
finished

The _epi.pfm =~ 1.3mb

And with another image (a .png), it stops after ~1min and I get:

load light-field images
compute depth from epipolar images
export depth as ply and pfm file
/usr/local/lib/python3.7/site-packages/depthy/misc/pfm_handler.py:62: RuntimeWarning: invalid value encountered in true_divide
  img_arr = (img_arr-np.min(img_arr))/(np.max(img_arr)-np.min(img_arr))
finished

_epi.pfm =~ 100mb

Tried also with a .jpg, I get:

load light-field images
Traceback (most recent call last):
  File "/usr/local/bin/depthy", line 8, in <module>
    sys.exit(main())
  File "/usr/local/lib/python3.7/site-packages/depthy/bin/cli.py", line 113, in main
    lf_img_arr = load_lf_arr(filenames)
  File "/usr/local/lib/python3.7/site-packages/depthy/misc/io_functions.py", line 60, in load_lf_arr
    assert lf_dim % 2 == 1, 'Reshaping image list to light-field array failed due to size %s.' % len(img_list)
AssertionError: Reshaping image list to light-field array failed due to size 0.

Any idea?
It stills generate _epi.ply and _epi.pfm files, but no output image, is it normal or just because it errors out at some point?

I would like to generate depth map using my png file. But it always show error like this. Could you please help in this issue? Many thanks

(depth_map) C:\Workplace\02work>depthy -s D:\PNG\flood

depthy v0.4.0

Using epi method

Load light-field images

Traceback (most recent call last):
File "c:\users\anaconda3\envs\depth_map\lib\runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "c:\users\anaconda3\envs\depth_map\lib\runpy.py", line 85, in run_code
exec(code, run_globals)
File "C:\Users\anaconda3\envs\depth_map\Scripts\depthy.exe_main.py", line 7, in
File "c:\users\anaconda3\envs\depth_map\lib\site-packages\depthy\bin\cli.py", line 138, in main
lf_img_arr = load_lf_arr(filenames)
File "c:\users\anaconda3\envs\depth_map\lib\site-packages\depthy\misc\io_functions.py", line 53, in load_lf_arr
fnames = sorted(fnames, key=lambda x: int(re.sub("[^0-9]", "", os.path.basename(x).split(".")[0])))
File "c:\users\anaconda3\envs\depth_map\lib\site-packages\depthy\misc\io_functions.py", line 53, in
fnames = sorted(fnames, key=lambda x: int(re.sub("[^0-9]", "", os.path.basename(x).split(".")[0])))
ValueError: invalid literal for int() with base 10: ''

Hi, I got that result message while running command:

depthy -s './examples/data/pens/'

Was I using the wrong method?

HI , can you give sample code ideas how to make stereo pair from depthmap in python , I have searched ,but not found that , could you please guide me .
Thanks in advanced .