From fd902f3894eac13b933fc73ef722398e0c51a1fe Mon Sep 17 00:00:00 2001 From: Lukas Muttenthaler Date: Sat, 5 Aug 2023 09:14:44 +0200 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index e7b7b65..452c92e 100644 --- a/README.md +++ b/README.md @@ -79,7 +79,7 @@ Neural networks come from different sources. With `thingsvision`, you can extrac - both original [CLIP](https://github.com/openai/CLIP) variants (`ViT-B/32` and `RN50`) - a few custom models (Alexnet, VGG-16, Resnet50, and Inception_v3) trained on [Ecoset](https://www.pnas.org/doi/10.1073/pnas.2011417118) rather than ImageNet and one Alexnet pretrained on ImageNet and fine-tuned on [SalObjSub](https://cs-people.bu.edu/jmzhang/sos.html) - each of the many [CORnet](https://github.com/dicarlolab/CORnet) versions -- [Harmonization](https://arxiv.org/abs/2211.04533) models from the official [Harmonization repo](https://github.com/serre-lab/harmonization). The default variant is `ViT_B16`. However, the following encoders are additionally available: `ResNet50`, `VGG16`, `EfficientNetB0`, `tiny_ConvNeXT`, `tiny_MaxViT`, `LeViT_small`
+- [Harmonization](https://arxiv.org/abs/2211.04533) models from the official [Harmonization repo](https://github.com/serre-lab/harmonization). The default variant is `ViT_B16`. Other available models are `ResNet50`, `VGG16`, `EfficientNetB0`, `tiny_ConvNeXT`, `tiny_MaxViT`, `LeViT_small`
- [DreamSim](https://dreamsim-nights.github.io/) models from the official [DreamSim repo](https://github.com/ssundaram21/dreamsim). The default variant is `open_clip_vitb32`. Other available models are `clip_vitb32`. See the [docs](https://vicco-group.github.io/thingsvision/AvailableModels.html) for more information.

(back to top)