Rope I Vit L14 Pn Aps C1 Pe Core

--- tags: - image-feature-extraction - birder - pytorch library_name: birder license: apache-2.0 base_model: - facebook/PE-Core-L14-336 --- # Model Card for rope_i_vit_l14_pn_aps_c1_pe-core A ViT-L14 image encoder from the PE-Core model by Bolya et al., converted to the Birder format for image feature extraction. This version retains the original model weights and architecture, with the exception of removing the CLIP projection layer to expose raw image embeddings. It is a general-purpose visual backbone. See: <https://huggingface.co/facebook/PE-Core-L14-336> for further details. ## Model Details - **Model Type:** Image classification and detection backbone - **Model Stats:** - Params (M): 316.1 - Input image size: 336 x 336 - **Papers:** - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: <https://arxiv.org/abs/2010.11929> - Rotary Position Embedding for Vision Transformer: <https://arxiv.org/abs/2403.13298> - Perception Encoder: The best visual embeddings are not at the output of the network: <https://arxiv.org/abs/2504.13181> ## Model Usage ### Image Embeddings ```python import birder from birder.inference.classification import infer_image (net, model_info) = birder.load_pretrained_model("rope_i_vit_l14_pn_aps_c1_pe-core", inference=True) # Get the image size the model was trained on size = birder.get_size_from_signature(model_info.signature) # Create an inference transform transform = birder.classification_transform(size, model_info.rgb_stats) image = "path/to/image.jpeg" # or a PIL image (out, embedding) = infer_image(net, image, transform, return_embedding=True) # embedding is a NumPy array with shape of (1, 1024) ``` ### Detection Feature Map ```python from PIL import Image import birder (net, model_info) = birder.load_pretrained_model("rope_i_vit_l14_pn_aps_c1_pe-core", inference=True) # Get the image size the model was trained on size = birder.get_size_from_signature(model_info.signature) # Create an inference transform transform = birder.classification_transform(size, model_info.rgb_stats) image = Image.open("path/to/image.jpeg") features = net.detection_features(transform(image).unsqueeze(0)) # features is a dict (stage name -> torch.Tensor) print([(k, v.size()) for k, v in features.items()]) # Output example: # [('neck', torch.Size([1, 1024, 24, 24]))] ``` ## Citation ```bibtex @misc{dosovits...

Source context: 14 downloads · 0 likes · Pipeline image-feature-extraction · Library birder · Repo birder-project/rope_i_vit_l14_pn_aps_c1_pe-core