Revert to using image_url for image classification tasks.

Azure · Oct 24, 2024 · bc1aeb6 · bc1aeb6
1 parent 86b6c21
commit bc1aeb6
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 4 deletions.
diff --git a/assets/training/finetune_acft_image/components/pipeline_components/classification/spec.yaml b/assets/training/finetune_acft_image/components/pipeline_components/classification/spec.yaml
@@ -263,7 +263,7 @@ jobs:
       compute_model_import: ${{parent.inputs.compute_model_import}}
       compute_finetune: ${{parent.inputs.compute_finetune}}
       task_name: ${{parent.inputs.task_type}}
-      user_column_names: image,label
+      user_column_names: image_url, label
       task_specific_extra_params: '"model_family=HuggingFaceImage;model_name=${{parent.inputs.model_name}};metric_for_best_model=${{parent.inputs.primary_metric}};number_of_epochs=${{parent.inputs.number_of_epochs}}"'
 
   framework_selector:

diff --git a/...s/training/finetune_acft_image/components/pipeline_components/hf_classification/spec.yaml b/...s/training/finetune_acft_image/components/pipeline_components/hf_classification/spec.yaml
@@ -363,7 +363,7 @@ inputs:
 
   input_column_names:
     type: string
-    default: image
+    default: image_url
     optional: true
     description: Input column names in provided test dataset, for example column1. Add comma delimited values in case of multiple input columns, for example column1,column2.
 

diff --git a/assets/training/model_evaluation/tests/test_image_dataset.py b/assets/training/model_evaluation/tests/test_image_dataset.py
@@ -150,7 +150,7 @@ def get_mock_run_context():
 
 
 @pytest.mark.parametrize("task_type,input_column_names,label_column_name", [
-    (TASK.IMAGE_CLASSIFICATION, ["image"], "label"),
+    (TASK.IMAGE_CLASSIFICATION, ["image_url"], "label"),
     (TASK.IMAGE_OBJECT_DETECTION, ["image", "image_meta_info", "text_prompt"], "label"),
     (TASK.IMAGE_GENERATION, ["prompt"], "label"),
 ])
@@ -192,7 +192,7 @@ def test_image_dataset(task_type, input_column_names, label_column_name):
         # Compare the loaded dataset with the original.
         if task_type == TASK.IMAGE_CLASSIFICATION:
             loaded_dataset = [
-                {k: row[k] for k in ["image", "label"]} for _, row in df.iterrows()
+                {k: row[k] for k in ["image_url", "label"]} for _, row in df.iterrows()
             ]
 
             for r1, r2 in zip(dataset, loaded_dataset):