-
Hello,
I am a PhD student closely following your article on “CoEvoGNN” for link prediction using the Co-AU 2K and Bitcoin datasets. I greatly appreciate you sharing the associated code on GitHub (h…
-
I'm a little confused about the practical difference between `loss` and `metrics`.
I have developed a model for predicting the next item a visitor will click in an e-shop, so I'm primarily interest…
-
**Describe the bug**
Thanks for sharing this wonderful code.
One weird thing I've noticed is that the Persformer in /examples/orbit_5k_pipeline.ipynb is not trainable.
I have changed the Persfo…
-
For the characteristics of the hyperparameters, a kind of global constants, should not be changed after setting. This is the essential difference between a hyperparameter and a variable.
Whether w…
-
Hi,
Thanks for sharing the codes. I have some questions and could help me figure them out?
1. Why using the hyperparameter "freeze_prototypes_niters", is it important for the model performance?
2…
-
Hi IrDIE,
You did a great job for small object detection. I am using your implementation but when I change , slice_height, slice_width, overlap_height_ratio, overlap_width_ratio it does not change an…
-
Hi, when I try to run train.sh on two GPUs (TITAN RTX) with 24GB VRAM, I get the following errors:
> RuntimeError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 1; 23.65 GiB total capacity; 21…
-
We have observed significantly inconsistent training results between specific computers. Investigate and resolve the issue(s). Could be computer-specific problems, or Pytorch bugs, rather than project…
-
I run nosetests under test directory and I got the following error, I'm using python 3.4.3, Theano (0.10.0b1), DIRECT (1.0.1), cma (2.2.0):
..............DIRECT Version 2.0.4
Problem Dimension n…
-
I want to use pix2pix for a medical image generation task, where the control condition is different label images. My hyperparameter settings are as follows:
accelerate launch src/train_pix2pix_turbo.…