models microsoft beit base patch16 224 pt22k ft22k
Description: The BEiT is a vision transformer that is similar to the BERT model, but is also capable of image analysis. The model is pre-trained on a large collection of images, and uses patches to analyze images. It uses relative position embeddings and mean-pooling to classify images, and can be used to extract image features for downstream tasks by placing a linear layer on top of the pre-trained encoder. You can place a linear layer on top of the [CLS] token or mean-pool the final hidden states of the patch embeddings, depending on the specifics of your task. > The above summary was generated using ChatGPT. Review the original-model-card to understand the data used to train the model, evaluation metrics, license, intended uses, limitations and bias before using the model. ### Inference samples Inference type|Python sample (Notebook)|CLI with YAML |--|--|--| Real time|image-classification-online-endpoint.ipynb|image-classification-online-endpoint.sh Batch |image-classification-batch-endpoint.ipynb|image-classification-batch-endpoint.sh ### Finetuning samples Task|Use case|Dataset|Python sample (Notebook)|CLI with YAML |---|--|--|--|--| Image Multi-class classification|Image Multi-class classification|fridgeObjects|fridgeobjects-multiclass-classification.ipynb|fridgeobjects-multiclass-classification.sh Image Multi-label classification|Image Multi-label classification|multilabel fridgeObjects|fridgeobjects-multilabel-classification.ipynb|fridgeobjects-multilabel-classification.sh ### Model Evaluation |Task|Use case|Dataset|Python sample (Notebook)| |---|--|--|--| |Image Multi-class classification|Image Multi-class classification|fridgeObjects|image-multiclass-classification.ipynb| |Image Multi-label classification|Image Multi-label classification|multilabel fridgeObjects|image-multilabel-classification.ipynb| ### Sample inputs and outputs (for real-time inference) #### Sample input json { "input_data": { "columns": [ "image" ], "index": [0, 1], "data": ["image1", "image2"] } } Note: "image1" and "image2" string should be in base64 format or publicly accessible urls. #### Sample output json [ { "probs": [0.91, 0.09], "labels": ["can", "carton"] }, { "probs": [0.1, 0.9], "labels": ["can", "carton"] } ] #### Model inference - visualization for a sample image
/plot_microsoft-beit-base-patch16-224-pt22k-ft22k_MC.png)
Version: 10
Preview license : apache-2.0 model_specific_defaults : ordereddict([('apply_deepspeed', 'true'), ('apply_ort', 'true')]) task : image-classification
View in Studio: https://ml.azure.com/registries/azureml/models/microsoft-beit-base-patch16-224-pt22k-ft22k/version/10
License: apache-2.0
SHA: 9da301148150e37e533abef672062fa49f6bda4f
datasets: imagenet, imagenet-21k
evaluation-min-sku-spec: 4|1|28|176
evaluation-recommended-sku: Standard_NC6s_v3
finetune-min-sku-spec: 4|1|28|176
finetune-recommended-sku: Standard_NC6s_v3
finetuning-tasks: image-classification
inference-min-sku-spec: 4|0|14|28
inference-recommended-sku: Standard_DS3_v2, Standard_D4a_v4, Standard_D4as_v4, Standard_DS4_v2, Standard_D8a_v4, Standard_D8as_v4, Standard_DS5_v2, Standard_D16a_v4, Standard_D16as_v4, Standard_D32a_v4, Standard_D32as_v4, Standard_D48a_v4, Standard_D48as_v4, Standard_D64a_v4, Standard_D64as_v4, Standard_D96a_v4, Standard_D96as_v4, Standard_FX4mds, Standard_F8s_v2, Standard_FX12mds, Standard_F16s_v2, Standard_F32s_v2, Standard_F48s_v2, Standard_F64s_v2, Standard_F72s_v2, Standard_FX24mds, Standard_FX36mds, Standard_FX48mds, Standard_E4s_v3, Standard_E8s_v3, Standard_E16s_v3, Standard_E32s_v3, Standard_E48s_v3, Standard_E64s_v3, Standard_NC4as_T4_v3, Standard_NC6s_v3, Standard_NC8as_T4_v3, Standard_NC12s_v3, Standard_NC16as_T4_v3, Standard_NC24s_v3, Standard_NC64as_T4_v3, Standard_NC24ads_A100_v4, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4, Standard_ND40rs_v2
model_id: microsoft/beit-base-patch16-224-pt22k-ft22k