|
--- |
|
title: SamGIS - LISA on ZeroGPU |
|
emoji: 🗺️ |
|
colorFrom: red |
|
colorTo: blue |
|
sdk: gradio |
|
sdk_version: 4.40.0 |
|
app_file: app.py |
|
pinned: true |
|
license: mit |
|
--- |
|
|
|
# [LISA](https://github.com/dvlab-research/LISA) + [SamGIS](https://github.com/trincadev/samgis-be) on Zero GPU! |
|
|
|
This project aims to permit use of [LISA](https://github.com/dvlab-research/LISA) (Reasoning Segmentation via Large Language Model) applied to geospatial data thanks to [SamGIS](https://github.com/trincadev/samgis-be). In this space I adapted LISA to HuggingFace [lisa-on-cuda](https://huggingface.co/spaces/aletrn/lisa-on-cuda) ZeroGPU space. |
|
|
|
This [home page project](https://huggingface.co/spaces/aletrn/samgis-lisa-on-zero) is a plane Gradio interface that take a json in input to translate it to a geojson. More information about these API implementation [here]( |
|
https://aletrn-samgis-lisa-on-zero.hf.space/docs). On this [blog page](https://trinca.tornidor.com/projects/lisa-adapted-for-samgis) you can find more details, including some request and response examples with the geojson map representations. |
|
|
|
You can also find the alternative map interface [here](https://aletrn-samgis-lisa-on-zero.hf.space/lisa/) useful to create on the fly the payload requests and to represent the geojson response. |
|
|
|
## Custom environment variables for HuggingFace ZeroGPU Space |
|
|
|
Fundamental environment variables you need are: |
|
|
|
```bash |
|
XDG_CACHE_HOME="/data/.cache" |
|
PROJECT_ROOT_FOLDER="/home/user/app" |
|
WORKDIR="/home/user/app" |
|
``` |
|
|
|
Derived ones: |
|
|
|
```bash |
|
MPLCONFIGDIR="/data/.cache/matplotlib" |
|
TRANSFORMERS_CACHE="/data/.cache/transformers" |
|
PYTORCH_KERNEL_CACHE_PATH="/data/.cache/torch/kernels" |
|
FASTAPI_STATIC="/home/user/app/static" |
|
VIS_OUTPUT="/home/user/app/vis_output" |
|
MODEL_FOLDER="/home/user/app/machine_learning_models" |
|
FOLDERS_MAP='{"WORKDIR":"/home/user/app","XDG_CACHE_HOME":"/data/.cache","PROJECT_ROOT_FOLDER":"/home/user/app","MPLCONFIGDIR":"/data/.cache/matplotlib","TRANSFORMERS_CACHE":"/data/.cache/transformers","PYTORCH_KERNEL_CACHE_PATH":"/data/.cache/torch/kernels","FASTAPI_STATIC":"/home/user/app/static","VIS_OUTPUT":"/home/user/app/vis_output"}' |
|
``` |
|
|
|
The function `build_frontend()` from lisa_on_cuda package create all the folders required for this project using the environment variable `FOLDERS_MAP`. That's useful for cache folders (XDG_CACHE_HOME, MPLCONFIGDIR, TRANSFORMERS_CACHE, PYTORCH_KERNEL_CACHE_PATH) because missing these can slow down the inference process. Also you could keep these folders in a permanent storage disk mounted on a custom path. |
|
|
|
To change the base relative url for custom frontend add the VITE_PREFIX environment variable, e.g.: |
|
|
|
```bash |
|
VITE_INDEX_URL="/custom-url" |
|
``` |
|
|
