nasirkhalid24 / clip-mesh-smplx Goto Github PK
View Code? Open in Web Editor NEWCLIP + Mesh + SMPL-X
License: MIT License
CLIP + Mesh + SMPL-X
License: MIT License
I ran into this Error in both terminal and colab, sigma is a list, not a tuple:
TypeError Traceback (most recent call last)
in
19 set_seed(cfg['seed'])
20
---> 21 single_loop(cfg)
2 frames
/content/CLIPMesh-SMPLX/loops/single.py in single_loop(config)
129 # low pass filter for textures
130 ready_texture = texture.Texture2D(
--> 131 kornia.filters.gaussian_blur2d(
132 kd_map_opt.data.permute(0, 3, 1, 2),
133 kernel_size=config["kernel_size"],
/usr/local/lib/python3.9/dist-packages/kornia/filters/gaussian.py in gaussian_blur2d(input, kernel_size, sigma, border_type, separable)
56 sigma = tensor([sigma], device=input.device, dtype=input.dtype)
57 else:
---> 58 KORNIA_CHECK_IS_TENSOR(sigma)
59 sigma = sigma.to(device=input.device, dtype=input.dtype)
60
/usr/local/lib/python3.9/dist-packages/kornia/core/check.py in KORNIA_CHECK_IS_TENSOR(x, msg)
133 """
134 if not isinstance(x, Tensor):
--> 135 raise TypeError(f"Not a Tensor type. Got: {type(x)}.\n{msg}")
136
137
TypeError: Not a Tensor type. Got: <class 'list'>.
None
I tried changing kernel_size=config["kernel_size"]; sigma=config["blur_sigma"] to kernel_size= tuple(config["kernel_size"]); sigma=tuple(config["blur_sigma"]). Then a new ERROR is obtained:
0%| | 0/1000 [00:00<?, ?it/s]IMAGEIO FFMPEG_WRITER WARNING: input image is not divisible by macro_block_size=16, resizing from (518, 260) to (528, 272) to ensure video compatibility with most codecs and players. To prevent resizing, make your input image divisible by the macro_block_size or set the macro_block_size to 1 (risking incompatibility).
[swscaler @ 0000029e84943fc0] Warning: data is not aligned! This can lead to a speed loss
0%| | 0/1000 [00:04<?, ?it/s]
Traceback (most recent call last):
File "C:\Users...\CLIPMesh-SMPLX\main.py", line 83, in
single_loop(cfg)
File "C:\Users..\CLIPMesh-SMPLX\loops\single.py", line 423, in single_loop
log_str = "CLIP Loss = %.3f | TVL Tex = %.3f" % (clip_loss.item(), t_l.item())
ValueError: only one element tensors can be converted to Python scalars
How do I fix it?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.