Computer vision
Computer vision is an interdisciplinary field that deals with how computers can be made to gain high-level understanding of digital images and videos.
Here are 14,810 public repositories matching this topic...
-
Updated
Oct 3, 2021 - Python
-
Updated
Sep 10, 2021
-
Updated
Sep 25, 2021 - C++
-
Updated
Sep 30, 2021 - C
-
Updated
Oct 1, 2021
-
Updated
Sep 30, 2021 - Python
-
Updated
Sep 28, 2021 - Jupyter Notebook
I figured out a way to get the (x,y,z) data points for each frame from one hand previously. but im not sure how to do that for the new holistic model that they released. I am trying to get the all landmark data points for both hands as well as parts of the chest and face. does anyone know how to extract the holistic landmark data/print it to a text file? or at least give me some directions as to h
Change tensor.data to tensor.detach() due to
pytorch/pytorch#6990 (comment)
tensor.detach() is more robust than tensor.data.
-
Updated
May 2, 2021
-
Updated
Oct 3, 2021 - C++
-
Updated
Aug 25, 2021 - Python
Describe the bug
A harmless but distracting warning is raised when prefetch is passed as argument to the Flow.
Reproduce
from jina import Flow, Document
f = Flow(prefetch=10).add()
with f:
f.index(inputs=Document())-
Updated
Oct 2, 2021 - Python
-
Updated
Aug 3, 2020 - Lua
-
Updated
Oct 3, 2021 - C++
-
Updated
Oct 3, 2021 - Python
🐛 Describe the bug
Steps to reproduce:
import torchvision
from PIL import Image
img = Image.open("test/assets/encode_jpeg/grace_hopper_517x606.jpg")
torchvision.transforms.functional.pil_to_tensor(img)Raises:
./vision/torchvision/transforms/functional.py:177: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tenso
-
Updated
Jul 26, 2021 - Go
-
Updated
Sep 18, 2021 - HTML
-
Updated
Apr 24, 2021 - Python
-
Updated
Jun 6, 2021 - Lua
-
Updated
Oct 1, 2021 - C++
-
Updated
Sep 28, 2021 - Jupyter Notebook
-
Updated
Oct 3, 2021 - Python
-
Updated
Aug 23, 2021
-
Updated
Oct 3, 2021 - Python
-
Updated
Sep 29, 2021 - Python
System information (version)
Detailed description
When running cv2.seamlessClone() the error is a bit misleading when the incorrect image path is supplied. It doesn't make it obvious that the problem is in the path
Steps to reproduce