-
### Description
This Issue aims to address and refactor the `cstr` model to fix benchmark issues as outlined in [Issue #60](https://github.com/SECQUOIA/gdplib/issues/60).
Solution strategy causing…
-
### Description
This Issue aims to address and refactor the `batch_processing` model to fix benchmark issues as outlined in [Issue #60](https://github.com/SECQUOIA/gdplib/issues/60).
Solution stra…
-
Hi, thanks again for the nice paper!
The best reference model is GPT-J-6B, and from the code I see you set it to float16 precision (both revision and torch_dtype). If I initialize the model with fu…
-
This operator reverses the order of the input tensor along specified axes. There are some pytorch models using [`flip`](https://pytorch.org/docs/stable/generated/torch.flip.html) operator. When they t…
-
I saw that there is a significant performance difference between clip-ViT-L-14 and clip-ViT-B-32 on ImageNet. What's the difference between those models (vector length, model size,.., couldn't find an…
-
I have a COLMAP model with more than 100 images, can I use the COLMAP model as a fixed prior to get dense point cloud? I used to try with dust3r, but with too many images the performance degenerates, …
-
**Is your feature request related to a problem? Please describe.**
on low performance pc's it can be time consuming having to wait for the gcode generation to complete, when you just want to slice a …
-
Hello,
I am working on training AdaBLDM with my custom dataset, which uses binary masks rather than the triple masks used in the original implementation. I would like to understand:
1. Which par…
-
**Environment**
device : inf1.xlarge
torch 1.3.1
torch-neuron 1.13.1.2.9.17.0
**Problem**
I compared the performance of convolution on different resolutions on different devices (inf1.xlarge, C…
-
Hi
I tried to reproduce the experimental results using the given pre-trained model, but the model could not even achieve a similar performance.
Can you explain why? or can you provide the model …