Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 12 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -104,10 +104,19 @@ $ conda activate thingsvision
```
Then, activate the environment and simply install `thingsvision` via running the following `pip` command in your terminal.
```bash
$ pip install --upgrade thingsvision[full]
$ pip install --upgrade thingsvision
$ pip install git+https://github.com/openai/CLIP.git
```

The package automatically installs the [Harmonization](https://github.com/serre-lab/harmonization) and [DreamSim](https://github.com/ssundaram21/dreamsim) repositories. See the documentation for available [harmonized models](https://vicco-group.github.io/thingsvision/AvailableModels.html#harmonization) and [DreamSim models](https://vicco-group.github.io/thingsvision/AvailableModels.html#dreamsim) in `thingsvision`.
If you want to extract features for [harmonized models](https://vicco-group.github.io/thingsvision/AvailableModels.html#harmonization) from the [Harmonization repo](https://github.com/serre-lab/harmonization), you have to additionally run the following `pip` command in your `thingsvision` environment,
```bash
$ pip install "keras-cv-attention-models>=1.3.5" "vit-keras==0.1.2"
$ pip install git+https://github.com/serre-lab/Harmonization.git
```
If you want to extract features for [DreamSim](https://dreamsim-nights.github.io/) from the [DreamSim repo](https://github.com/ssundaram21/dreamsim), you have to additionally run the following `pip` command in your `thingsvision` environment,
```bash
$ pip install dreamsim==0.1.3
```
See the [docs](https://vicco-group.github.io/thingsvision/AvailableModels.html#dreamsim) for which `DreamSim` models are available in `thingsvision`.

#### Google Colab
Alternatively, you can use Google Colab to play around with `thingsvision` by uploading your image data to Google Drive (via directory mounting).
Expand Down
4 changes: 2 additions & 2 deletions requirements.txt
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@
ftfy
h5py
keras-cv-attention-models>=1.3.5
matplotlib
numba
numpy<2
Expand All @@ -20,6 +19,7 @@ tqdm
transformers==4.40.1
pytest
git+https://github.com/openai/CLIP.git
dreamsim==0.1.3
keras-cv-attention-models>=1.3.5
vit-keras==0.1.2
git+https://github.com/serre-lab/Harmonization.git
dreamsim==0.1.3
8 changes: 1 addition & 7 deletions setup.py
Original file line number Diff line number Diff line change
Expand Up @@ -49,11 +49,5 @@
"Operating System :: OS Independent",
],
entry_points={"console_scripts": ["thingsvision = thingsvision.thingsvision:main"]},
python_requires=">=3.10",
extras_require={
"clip": ["CLIP @ git+https://github.com/openai/CLIP.git"],
"dreamsim": ["dreamsim==0.1.3"],
"harmonization": ["keras-cv-attention-models>=1.3.5", "vit-keras==0.1.2","Harmonization @ git+https://github.com/serre-lab/Harmonization.git"],
"full":["CLIP @ git+https://github.com/openai/CLIP.git", "dreamsim==0.1.3", "keras-cv-attention-models>=1.3.5", "vit-keras==0.1.2","Harmonization @ git+https://github.com/serre-lab/Harmonization.git" ],
}
python_requires=">=3.10"
)
Loading