> ## Documentation Index > Fetch the complete documentation index at: https://arize-ax.mintlify.site/docs/llms.txt > Use this file to discover all available pages before exploring further. # Image Classification > How to log your model schema for image classification models ### Image Classification Model Overview Image classification models take an image as input and return a predicted label for the image. \*all [classification](https://arize.com/docs/ax/sending-data-to-arize/model-types/binary-classification) variant specifications apply to the Image Classification model type, with the addition of embeddings #### Performance Metrics Accuracy, Recall, Precision, FPR, FNR, F1, Sensitivity, Specificity ### Code Example The `EmbeddingColumnNames` class constructs your embedding objects. You can log them into the platform using a dictionary that maps the embedding feature names to the embedding objects. See our [API reference](/ax/machine-learning/machine-learning/how-to-ml/upload-data-to-arize/log-directly-via-sdk-api) for more details. Navigate [here](/ax/machine-learning/machine-learning/integrations-ml/aws-s3-example/aws-s3-example) for step-by-step instructions to view private AWS S3 image links. **Example Row** | image\_vector | image\_link | prediction\_label | actual\_label | prediction\_score | actual\_score | Timestamp | | ------------- | -------------------------------- | ----------------- | ------------- | ----------------- | ------------- | ------------ | | `[1.0, 2, 3]` | `"https://link-to-my-image.png"` | `car` | `bus` | `0.3` | `1` | `1618590882` | ```python theme={null} from arize.pandas.logger import Client, Schema from arize.utils.types import ModelTypes, Environments, EmbeddingColumnNames API_KEY = 'ARIZE_API_KEY' SPACE_ID = 'YOUR SPACE ID' arize_client = Client(space_id=SPACE_ID, api_key=API_KEY) # Declare which columns are the feature columns feature_column_names=[ "MERCHANT_TYPE", "ENTRY_MODE", "STATE", "MEAN_AMOUNT", "STD_AMOUNT", "TX_AMOUNT", ] # feature & tag columns can be optionally defined with typing: tag_columns = TypedColumns( inferred=["name"], to_int=["zip_code", "age"] ) # Declare embedding feature columns embedding_feature_column_names = { # Dictionary keys will be the name of the embedding feature in the app "embedding_display_name": EmbeddingColumnNames( vector_column_name="image_vector", # column name of the vectors, required link_to_data_column_name="image_link", # column name of the link to the images, optional ) } # Defina the Schema, including embedding information schema = Schema( prediction_id_column_name="prediction_id", timestamp_column_name="prediction_ts", prediction_label_column_name="PREDICTION", prediction_score_column_name="PREDICTION_SCORE", actual_label_column_name="ACTUAL", actual_score_column_name="ACTUAL_SCORE", feature_column_names=feature_column_names, embedding_feature_column_names=embedding_feature_column_names, tag_column_names=tag_columns, ) # Log the dataframe with the schema mapping response = arize_client.log( model_id="sample-model-1", model_version= "v1", model_type=ModelTypes.SCORE_CATEGORICAL, environment=Environments.PRODUCTION, dataframe=test_dataframe, schema=schema, ) ``` Google Colaboratory **Image Classification Embedding Features** Arize supports logging the embedding features associated with the image the model is acting on and the image itself using the [`EmbeddingColumnNames`](https://arize.com/docs/ax/api-reference/arize.pandas/embeddingcolumnnames) object. * The `vector_column_name` should be the name of the column where the embedding vectors are stored. The embedding vector is the dense vector representation of the unstructured input. ⚠️ **Note:** embedding features are not sparse vectors. * The `link_to_data_column_name` should be the name of the column where the URL links to the source images, that your model classifies, are stored. ```javascript theme={null} { "embedding_display_name": EmbeddingColumnNames( vector_column_name="image_vector", link_to_data_column_name="image_link" ) } ``` See [here](/ax/machine-learning/computer-vision/how-to-cv/7-troubleshoot-embedding-data/how-to-generate-your-own-embedding) for more information on embeddings and options for generating them. ```py theme={null} from arize.api import Client from arize.utils.types import ModelTypes, Environments, Embedding API_KEY = 'ARIZE_API_KEY' SPACE_ID = 'YOUR SPACE ID' arize_client = Client(space_id=SPACE_ID, api_key=API_KEY) # Example features; features & tags can be optionally defined with typing features = { 'state': 'ca', 'city': 'berkeley', 'merchant_name': 'Peets Coffee', 'pos_approved': TypedValue(value=False, type=ArizeTypes.INT), 'item_count': 10, 'merchant_type': 'coffee shop', 'charge_amount': TypedValue(value=20.11, type=ArizeTypes.FLOAT), } # Example embedding features embedding_features = { "image_embedding": Embedding( vector=np.array([1.0, 2, 3]), link_to_data="https://link-to-my-image.png", ), } # Log data into the Arize platform response = arize.log( model_id='sample-model-1', model_version='v1", model_type=ModelTypes.SCORE_CATEGORICAL, environment=Environments.PRODUCTION, features=features prediction_label="not fraud", prediction_score = 0.3 actual_label="fraud", actual_score = 1 features=features, embedding_features=embedding_features ) ``` **CV Embedding Features** Arize supports logging the embedding features associated with the image the model is acting on and the image itself using the [`Embedding`](https://arize.com/docs/ax/api-reference/arize.log/embedding) object. * The embedding `vector` is the dense vector representation of the unstructured input. ⚠️ **Note:** embedding features are not sparse vectors. * The embedding `link_to_data` is used to pass URL links to the source image your model is classifying. ```cpp theme={null} { "embedding_display_name": Embedding( vector=np.array([1.0, 2, 3]), link_to_data="https://link-to-my-image.png", ) } ``` See [here](/ax/machine-learning/computer-vision/how-to-cv/7-troubleshoot-embedding-data/how-to-generate-your-own-embedding) for more information on embeddings and options for generating them. When configuring an embedding in the **UI using File Import** ```cpp theme={null} "embedding_features": [{ "my_feature": // #required, my_feature is the name of the feature { vector: "vector_col", // #required, vector_col is the column name of the vector raw_data: "raw_data_col", // #optional link_to_data: "link_to_data_col" // #optional } }] ``` Example file schema with embedding features ```json theme={null} { "prediction_id": "prediction_id", "timestamp": "timestamp", "tags": "tag/", "prediction_score": "prediction_score", "prediction_label": "prediction_label", "actual_label": "actual_label", "actual_score": "actual_score", "shap_values": "shap/", "version": "version", // lookup the column "version" in the file "batch_id": "batch_id", "exclude": [ "", "" ], "embedding_features": [ { "embedding_1": { "vector": "vector_column_1" "raw_data": "raw_data_column_1", "link_to_data": "link_to_data_column" } } ] } ``` When configuring an embedding in the **UI using the API** ```json theme={null} "embeddingFeatures": [{ "featureName": "my_feature", "vectorCol": "vector_col", "rawDataCol": "raw_data_col", "linkToDataCol": "link_to_data_col" }] ``` Example file schema with embedding features ```javascript theme={null} prediction_id: prediction_id timestamp: timestamp features: feature/ tags: tag/ prediction_score: prediction_score prediction_label: prediction_label actual_label: actual_label actual_score: actual_score shap_values: shap/ version: version // lookup the column "version" in the file batch_id: batch_id exclude: // leave empty to omit column exclusions embedding_features: // leave empty to omit embeddings ```