ViTST
ViTST copied to clipboard
Leezekun
[NeurIPS 2023] The official repo for the paper: "Time Series as Images: Vision Transformer for Irregularly Sampled Time Series"."
Thank you so much for releasing the code. I am trying to reproduce the results for regular time series dataset. I wonder if you could provide the batch size and...
I pip installed the configs package. But it has errors. ``` Traceback (most recent call last): File ".../ViTST/dataset/TSRAdata/process_scripts/ConstructDataset.py", line 16, in from configs import color_detailed_description ImportError: cannot import name 'color_detailed_description'...
Hi team, great work first of all. I would like to use your framework for the domain of sports. I have a time series data of players in regards to...
Can't run the script"run_VisionTextCLS.py",and this is my error:"ModuleNotFoundError: No module named 'models'"
The tokenizer is just for analyzing the length of static features. It is not necessary. You can remove the code related to the tokenizer if you have trouble loading it....
When I follow the steps of 'ReadMe'. When I run ConstructImage.py. The error comes. it comes from row 209: tokenizer = AutoTokenizer.from_pretrained("allenai/longformer-base-4096") how to solve this? Thank you.
Regarding the code for Vision Transformer and Swin Transformer, did you implement it yourself or use Google's source code? Are there any performance differences compared to the source code released...
I want to try converting data into images myself. I downloaded data from https://physionet.org/content/challenge-2012/1.0.0/, and it seems like ConstructImage.py uses .npy files. However, the data I downloaded from the website...
