-
# Transformer 在视觉方面的应用
## Reference
- 2021-01 A Survey on Visual Transformer [[Paper](https://arxiv.org/pdf/2012.12556.pdf)] [[Note](https://github.com/junxnone/tech-io/issues/926)]
- 2021-01 Tr…
-
### 🐛 Describe the bug
Following #80212, the docker build command failed again today on a freshly cloned repo:
```sh
$ git clone --recursive https://github.com/pytorch/pytorch
$ cd pytorch
$ DO…
-
# 30분 만에 만드는 과일 품질 분류 CNN 모델 | Seungwon Projects
Pytorch CNN Fruit Classification using ResNet18
[https://ethanseok.github.io/projects/2022/08/20/cnn_post/](https://ethanseok.github.io/projects/2022…
-
### Your current environment
Collecting environment information...
PyTorch version: 2.3.0
Is debug build: False
CUDA used to build PyTorch: 12.2
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.0…
-
### Description & Motivation
I've experienced with pytorch XLA using multitple NVIDIA A100 GPU and I observed that in most cases training is faster. So it would be really nice to have the option to…
-
i download checkpoint.zip :
wget https://cloud.mlcommons.org/index.php/s/QAZ2oM94MkFtbQx/download --output-document checkpoint.zip
but with error pytorch checkpoint file cannot load
when i unzip ch…
-
hi, eric-yyjau
why need to crop to the same length?
# crop to the same length
shuffle = True
if not shuffle: print("shuffle: ", shuffle)
choice = crop_or_pad_choice(uv_b_matches.sha…
-
### 🐛 Describe the bug
In the following code we add a backend-specific autograd kernel(e.g. AutogradCUDA) for aten builtin operator "tanh". Originally, it does not have a kernel for "AutogradCUDA",…
-
### 🐛 Describe the bug
When trying to implement a custom `autograd.Function` wrapping a custom CUDA Extensions, I ran into what I believe is a bug or a poorly documented interaction.
A minimal e…
-
### 🐛 Describe the bug
The sparse BSR tensor is something like the CSR tensor but with blocks instead of fine-grained elements. Using `is_sparse()` on a BSR object returns `False`, which should inste…
v0dro updated
1 month ago