-
Updated
Mar 20, 2021 - Python
embeddings
Here are 786 public repositories matching this topic...
-
Updated
Apr 28, 2022 - Python
-
Updated
Sep 1, 2021
Add default parameters for all projection heads
It's helpful to know what the default parameters were in the papers to get started. We should add the default projection head parameters which were used for pre-training on Imagenet to all projection and prediction heads in lightly/models/modules/heads.py.
-
Updated
Feb 23, 2021 - Python
-
Updated
Apr 7, 2019 - Jupyter Notebook
-
Updated
Feb 19, 2022 - Python
-
Updated
Apr 1, 2022 - Python
-
Updated
May 19, 2021 - Python
-
Updated
Apr 12, 2021 - Python
-
Updated
May 9, 2019 - Python
-
Updated
Oct 1, 2021 - Python
-
Updated
Apr 30, 2022 - Python
-
Updated
May 7, 2022 - Python
-
Updated
Mar 28, 2022 - Python
-
Updated
May 11, 2022 - Go
-
Updated
Feb 21, 2020 - Python
-
Updated
Mar 23, 2018 - Python
-
Updated
Apr 29, 2022
-
Updated
Mar 10, 2019 - Python
-
Updated
Apr 10, 2022 - Jupyter Notebook
-
Updated
Feb 12, 2021 - Python
-
Updated
Feb 10, 2022 - Python
-
Updated
May 7, 2022 - Python
Is there an existing issue for this?
- I have searched the existing issues.
Is your feature request related to a problem? Please describe.
Make Api for any object detection pipeline " towhee/img_object_embedding"
Describe the solution you'd like.
An api which return the output similar to the https://towhee.io/towhee/img_object_embedding
Describe an alternate solution.
_N
-
Updated
May 9, 2022 - Python
-
Updated
Mar 11, 2022 - Python
-
Updated
Mar 25, 2018 - Python
Improve this page
Add a description, image, and links to the embeddings topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the embeddings topic, visit your repo's landing page and select "manage topics."
Expected Behavior
I want to convert torch.nn.Linear modules to weight drop linear modules in my model (possibly big), and I want to train my model with multi-GPUs. However, I have RuntimeError in my sample code. First, I have _weight_drop() which drops some part of weights in torch.nn.Linear (see the code below).
Actual Behavior
RuntimeError: arguments are located on different GPUs at /