---

=== Help ===
usage: inference_video.py [-h] [--video VIDEO] [--output OUTPUT] [--img IMG]
                          [--montage] [--model MODELDIR] [--fp16] [--UHD]
                          [--scale SCALE] [--skip] [--fps FPS] [--png]
                          [--ext EXT] [--exp EXP] [--multi MULTI]

Interpolation for a pair of images

options:
  -h, --help        show this help message and exit
  --video VIDEO
  --output OUTPUT
  --img IMG
  --montage         montage origin video
  --model MODELDIR  directory with trained model files
  --fp16            fp16 mode for faster and more lightweight inference on
                    cards with Tensor Cores
  --UHD             support 4k video
  --scale SCALE     Try scale=0.5 for 4k video
  --skip            whether to remove static frames before processing
  --fps FPS
  --png             whether to vid_out png format vid_outs
  --ext EXT         vid_out video extension
  --exp EXP
  --multi MULTI

STDERR: 

=== Запуск с полным выводом ===
STDOUT:
Loaded 3.x/4.x HD model.


STDERR:
Traceback (most recent call last):
  File "/content/Practical-RIFE/inference_video.py", line 112, in <module>
    lastframe = next(videogen)
                ^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/skvideo/io/io.py", line 251, in vreader
    reader = FFmpegReader(fname, inputdict=inputdict, outputdict=outputdict, verbosity=verbosity)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/skvideo/io/ffmpeg.py", line 103, in __init__
    self.inputfps = np.float(parts[0])/np.float(parts[1])
                    ^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/numpy/__init__.py", line 394, in __getattr__
    raise AttributeError(__former_attrs__[attr])
AttributeError: module 'numpy' has no attribute 'float'.
`np.float` was a deprecated alias for the builtin `float`. To avoid this error in existing code, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
    https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations. Did you mean: 'float16'?


Код: 1