From 67fc250eb6aa84ef9ad19a020e3f8eb4e698feb4 Mon Sep 17 00:00:00 2001 From: Jong Wook Kim Date: Tue, 25 Jan 2022 17:04:00 -0800 Subject: [PATCH] add RN50x64 and ViT-L/14 models --- clip/clip.py | 2 ++ model-card.md | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/clip/clip.py b/clip/clip.py index f79e18b..2c911d0 100644 --- a/clip/clip.py +++ b/clip/clip.py @@ -32,8 +32,10 @@ _MODELS = { "RN101": "https://openaipublic.azureedge.net/clip/models/8fa8567bab74a42d41c5915025a8e4538c3bdbe8804a470a72f30b0d94fab599/RN101.pt", "RN50x4": "https://openaipublic.azureedge.net/clip/models/7e526bd135e493cef0776de27d5f42653e6b4c8bf9e0f653bb11773263205fdd/RN50x4.pt", "RN50x16": "https://openaipublic.azureedge.net/clip/models/52378b407f34354e150460fe41077663dd5b39c54cd0bfd2b27167a4a06ec9aa/RN50x16.pt", + "RN50x64": "https://openaipublic.azureedge.net/clip/models/be1cfb55d75a9666199fb2206c106743da0f6468c9d327f3e0d0a543a9919d9c/RN50x64.pt", "ViT-B/32": "https://openaipublic.azureedge.net/clip/models/40d365715913c9da98579312b702a82c18be219cc2a73407c4526f58eba950af/ViT-B-32.pt", "ViT-B/16": "https://openaipublic.azureedge.net/clip/models/5806e77cd80f8b59890b7e101eabd078d9fb84e6937f9e85e4ecb61988df416f/ViT-B-16.pt", + "ViT-L/14": "https://openaipublic.azureedge.net/clip/models/b8cca3fd41ae0c99ba7e8951adf17d267cdb84cd88be6f7c2e0eca1737a03836/ViT-L-14.pt", } diff --git a/model-card.md b/model-card.md index 2d22e25..126d845 100644 --- a/model-card.md +++ b/model-card.md @@ -18,7 +18,7 @@ The base model uses a ResNet50 with several modifications as an image encoder an Initially, we’ve released one CLIP model based on the Vision Transformer architecture equivalent to ViT-B/32, along with the RN50 model, using the architecture equivalent to ResNet-50. -As part of the staged release process, we have also released the RN101 model, as well as RN50x4, a RN50 scaled up 4x according to the [EfficientNet](https://arxiv.org/abs/1905.11946) scaling rule. In July 2021, we additionally released the RN50x16 and ViT-B/16 models. +As part of the staged release process, we have also released the RN101 model, as well as RN50x4, a RN50 scaled up 4x according to the [EfficientNet](https://arxiv.org/abs/1905.11946) scaling rule. In July 2021, we additionally released the RN50x16 and ViT-B/16 models, and In January 2022, the RN50x64 and ViT-L/14 models were released. Please see the paper linked below for further details about their specification.