Se Resnext 50 Arabian Peninsula

--- tags: - image-classification - birder - pytorch library_name: birder license: apache-2.0 --- # Model Card for se_resnext_50_arabian-peninsula A SE ResNeXt image classification model. This model was trained on the `arabian-peninsula` dataset (all the relevant bird species found in the Arabian peninsula inc. rarities). The species list is derived from data available at <https://avibase.bsc-eoc.org/checklist.jsp?region=ARA>. ## Model Details - **Model Type:** Image classification and detection backbone - **Model Stats:** - Params (M): 27.0 - Input image size: 256 x 256 - **Dataset:** arabian-peninsula (735 classes) - **Papers:** - Aggregated Residual Transformations for Deep Neural Networks: <https://arxiv.org/abs/1611.05431> - Squeeze-and-Excitation Networks: <https://arxiv.org/abs/1709.01507> ## Model Usage ### Image Classification ```python import birder from birder.inference.classification import infer_image # Option 1: manual setup (more control over preprocessing) net, model_info = birder.load_pretrained_model("se_resnext_50_arabian-peninsula", 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) # Option 2: helper (quick start with default preprocessing) net, model_info, transform = birder.load_pretrained_model_and_transform("se_resnext_50_arabian-peninsula", inference=True) image = "path/to/image.jpeg" # or a PIL image, must be loaded in RGB format out, _ = infer_image(net, image, transform) # out is a NumPy array with shape of (1, 735), representing class probabilities. ``` ### Image Embeddings ```python import birder from birder.inference.classification import infer_image # Option 1: manual setup (more control over preprocessing) net, model_info = birder.load_pretrained_model("se_resnext_50_arabian-peninsula", 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) # Option 2: helper (quick start with default preprocessing) net, model_info, transform = birder.load_pretrained_model_and_transform("se_resnext_50_arabian-peninsula", inference=True) image = "path/to/image.jpeg" # or a PIL...

Source context: 4 downloads · 0 likes · Pipeline image-classification · Library birder · Repo birder-project/se_resnext_50_arabian-peninsula