-
https://arxiv.org/pdf/2105.01601.pdf
> Convolutional Neural Networks (CNNs) are the go-to model for computer vision. Recently, attention-based networks, such as the Vision Transformer, have also be…
-
when I try to debug lag-llama/train.py, this error occured.
Traceback (most recent call last):
File "/home/xly/anaconda3/envs/c118p310/lib/python3.10/site-packages/numpy/core/getlimits.py", line…
-
### Roadmap
飞桨现有算子已经能较完整地支持 2D，3D 等常见数据维度，我们希望进一步拓展一些算子的高维支持，让飞桨能支持更多应用场景的需求。本方向主要开发：和飞桨专家一起扩展现有算子的功能，开发原有一些算子对处理 3D 及以上高维数据的支持，并解决制约这些高维支持的基础问题。
根据目前的issue发现需要扩展高维支持的算子有：
1. `F.affine_grri…
-
Hi,
this is a question and not an issue: I'm trying to retrain the recognizer on a custom alphabet, so that he is able to recognize chars in an image with a width of 512px and up to 60 chars.
My…
-
Hey, Thanks for uploading the code for this interesting project.
I have questions about the super-resolution capabilities of your approach
- If I'm only interested in super resolution, does the pa…
-
### Your current environment
The output of `python collect_env.py`
```text
WARNING 09-03 01:10:59 _custom_ops.py:14] Failed to import from vllm._C with ImportError('/model/vllm/vllm/_C.abi3.s…
-
# Ask a Question
Whether support will be provided in the future about warp_grid and grid_sample openrates of torch?
### Question
RuntimeError: Exporting the operator affine_grid_generator to ON…
-
Hi, thanks for your code.
I want to plug the STN into a CNN, and after comparing your code with the code in[ pytorch tutorial](https://pytorch.org/tutorials/intermediate/spatial_transformer_tutorial…
-
Hi, I got a problem with STN.
I see that STN's params need target dim as 50.Is that means the outputs of STN are feature maps size of [batch_size, channels, output_height, output_width], and both he…
-
LDM은 먼저 읽자
https://kimjy99.github.io/%EB%85%BC%EB%AC%B8%EB%A6%AC%EB%B7%B0/ldm/
---
https://bytez.com/docs/arxiv/2302.03011/paper
- context와 structure 구분할건데 여기서 structure 보존하는데에 **depth 사용** …