-
Hi all!
Recently I've been running experiments with Merlin and tried to speed-up the learning process by utilizing GPU. Unfortunatelly I could only achieve about 50% increase in learning time, which …
-
KTLG reference https://github.com/ktlg/tickets-integration/issues/687
Tenant reference https://github.com/ken9ross/ktlg-trng/issues/212
Testing Supply feedback command
-
# Open Grant Proposal: Proposal for Implementing Blockchain Explorer Tracking System
*Exploring tracking system:**
**Other:** Choose one of `Developer and data tooling`, `Applications`, `Integra…
-
Name of project:
XFX Academy
Grant Category
Educational material
Description
Problem Statement
Target Audience:
Aspiring blockchain developers
Enthusiasts and professionals looking to tr…
-
- PyTorch-Forecasting version: latest
- PyTorch version:
- Python version:3.7
- Operating System: Google Colab
### Expected behavior
i'm trying to apply the sample tutorial code
https://pytor…
-
We need to finalise the proposed budget lines. There was some discussion on whether we should remain high level (so it is more relatable) or low level (so it is more informative). @fretchen Ronald doe…
-
Fondant currently supports execution across cores on a single machine, which enables workflows using millions of images, but becomes a bottleneck when scaling to tens or hundreds of millions of images…
-
Hi,
I want to train a fasterrcnn_resnet50_fpn_v2 model on a custom dataset. I want to start from COCO pre-trained weights. Is that the default behavior?
or Do I need to supply a weights file thru…
-
## Question about applying fully unsupervised pre-training with VISSL
I have a dataset of images, split into two classes. My directory structure looks like:
```
data/
├── train/
│ ├── class0/…
-
@tkipf I'm trying slot attention with higher level features.
Hard K-means variant trains very fast, while the full attention variant with `slots = updates` is prone to gradient blow-up (probably be…