holywu / vs-midas Goto Github PK

# Imports
import vapoursynth as vs
# getting Vapoursynth core
import sys
import ctypes
import os
import site
core = vs.core
# Import scripts folder
scriptPath = 'F:/Hybrid/64bit/vsscripts'
sys.path.insert(0, os.path.abspath(scriptPath))
# Adding torch dependencies to PATH
path = site.getsitepackages()[0]+'/torch_dependencies/bin/'
ctypes.windll.kernel32.SetDllDirectoryW(path)
path = path.replace('\\', '/')
os.environ["PATH"] = path + os.pathsep + os.environ["PATH"]
# Loading Plugins
core.std.LoadPlugin(path="F:/Hybrid/64bit/vsfilters/SourceFilter/LSmashSource/vslsmashsource.dll")
# source: 'G:\TestClips&Co\files\test.avi'
# current color space: YUV420P8, bit depth: 8, resolution: 640x352, fps: 25, color matrix: 470bg, yuv luminance scale: limited, scanorder: progressive
# Loading G:\TestClips&Co\files\test.avi using LWLibavSource
clip = core.lsmas.LWLibavSource(source="G:/TestClips&Co/files/test.avi", format="YUV420P8", stream_index=0, cache=0, prefer_hw=0)
# Setting detected color matrix (470bg).
clip = core.std.SetFrameProps(clip, _Matrix=5)
# Setting color transfer info (470bg), when it is not set
clip = clip if not core.text.FrameProps(clip,'_Transfer') else core.std.SetFrameProps(clip, _Transfer=5)
# Setting color primaries info (), when it is not set
clip = clip if not core.text.FrameProps(clip,'_Primaries') else core.std.SetFrameProps(clip, _Primaries=5)
# Setting color range to TV (limited) range.
clip = core.std.SetFrameProp(clip=clip, prop="_ColorRange", intval=1)
# making sure frame rate is set to 25
clip = core.std.AssumeFPS(clip=clip, fpsnum=25, fpsden=1)
clip = core.std.SetFrameProp(clip=clip, prop="_FieldBased", intval=0) # progressive
from vsmidas import midas as MiDaS
# adjusting color space from YUV420P8 to RGBH for MiDaS
clip = core.resize.Bicubic(clip=clip, format=vs.RGBH, matrix_in_s="470bg", range_s="limited")
# Depth estimation using MiDaS
clip = MiDaS(clip=clip, model=2, device_index=0)
# adjusting output color from: RGBH to YUV420P10 for x265Model
clip = core.resize.Bicubic(clip=clip, format=vs.YUV420P10, matrix_s="470bg", range_s="limited", dither_type="error_diffusion")
# set output frame rate to 25fps (progressive)
clip = core.std.AssumeFPS(clip=clip, fpsnum=25, fpsden=1)
# Output
clip.set_output()

2023-12-14 16:30:42.755 Failed to evaluate the script:Python exception: Error(s) in loading state_dict for DPTDepthModel:Missing key(s) in state_dict: "pretrained.model.layers.3.downsample.reduction.weight", "pretrained.model.layers.3.downsample.norm.weight", "pretrained.model.layers.3.downsample.norm.bias", "pretrained.model.head.fc.weight", "pretrained.model.head.fc.bias". Unexpected key(s) in state_dict: "pretrained.model.layers.0.downsample.reduction.weight", "pretrained.model.layers.0.downsample.norm.weight", "pretrained.model.layers.0.downsample.norm.bias", "pretrained.model.layers.0.blocks.1.attn_mask", "pretrained.model.layers.1.blocks.1.attn_mask", "pretrained.model.head.weight", "pretrained.model.head.bias". size mismatch for pretrained.model.layers.1.downsample.reduction.weight: copying a param with shape torch.Size([768, 1536]) from checkpoint, the shape in current model is torch.Size([384, 768]).size mismatch for pretrained.model.layers.1.downsample.norm.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([384]).size mismatch for pretrained.model.layers.1.downsample.norm.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([384]).size mismatch for pretrained.model.layers.2.downsample.reduction.weight: copying a param with shape torch.Size([1536, 3072]) from checkpoint, the shape in current model is torch.Size([768, 1536]).size mismatch for pretrained.model.layers.2.downsample.norm.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([768]).size mismatch for pretrained.model.layers.2.downsample.norm.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([768]).Traceback (most recent call last):File "src\cython\vapoursynth.pyx", line 3115, in vapoursynth._vpy_evaluateFile "src\cython\vapoursynth.pyx", line 3116, in vapoursynth._vpy_evaluateFile "C:\Users\Selur\Desktop\Testing.vpy", line 38, in clip = MiDaS(clip=clip, model=2, device_index=0)^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_contextreturn func(*args, **kwargs)^^^^^^^^^^^^^^^^^^^^^File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\vsmidas\__init__.py", line 108, in midasmodule.load_state_dict(parameters)File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\torch\nn\modules\module.py", line 2152, in load_state_dictraise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(RuntimeError: Error(s) in loading state_dict for DPTDepthModel:Missing key(s) in state_dict: "pretrained.model.layers.3.downsample.reduction.weight", "pretrained.model.layers.3.downsample.norm.weight", "pretrained.model.layers.3.downsample.norm.bias", "pretrained.model.head.fc.weight", "pretrained.model.head.fc.bias". Unexpected key(s) in state_dict: "pretrained.model.layers.0.downsample.reduction.weight", "pretrained.model.layers.0.downsample.norm.weight", "pretrained.model.layers.0.downsample.norm.bias", "pretrained.model.layers.0.blocks.1.attn_mask", "pretrained.model.layers.1.blocks.1.attn_mask", "pretrained.model.head.weight", "pretrained.model.head.bias". size mismatch for pretrained.model.layers.1.downsample.reduction.weight: copying a param with shape torch.Size([768, 1536]) from checkpoint, the shape in current model is torch.Size([384, 768]).size mismatch for pretrained.model.layers.1.downsample.norm.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([384]).size mismatch for pretrained.model.layers.1.downsample.norm.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([384]).size mismatch for pretrained.model.layers.2.downsample.reduction.weight: copying a param with shape torch.Size([1536, 3072]) from checkpoint, the shape in current model is torch.Size([768, 1536]).size mismatch for pretrained.model.layers.2.downsample.norm.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([768]).size mismatch for pretrained.model.layers.2.downsample.norm.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([768]).
--