Vision Datasets location Update (#3289)

* adding continue_on_step_failure False and force_rerun True for vision pipelines

* adding continue_on_step_failure False and force_rerun True for vision pipelines

* adding continue_on_step_failure False and force_rerun True for vision pipelines

* update datasets location

* Replace remaining references to multiclass classification data.

* Replace remaining references to multilabel classification data.

* Replace remaining references to object detection data.

* Replace remaining references to instance segmentation data.

* Patch .zip url.

* Install numpy version compatible with scikit-image==0.19.3.

* Use different names for data sources to prevent job failures due to same name being used at the same time.

---------

Co-authored-by: Radu-Mihai Dondera <rdondera@microsoft.com>

cli/foundation-models/system/finetune/image-classification/multiclass-classification/prepare_data.py

@@ -105,7 +105,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
 
     # Download data
     print("Downloading data.")
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/fridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-classification/fridgeObjects.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -132,7 +132,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images",
-        name="fridge-items-images-2",
+        name="fridge-items-images-mc-ft",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)

cli/foundation-models/system/finetune/image-classification/multilabel-classification/prepare_data.py

@@ -108,7 +108,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
 
     # Download data
     print("Downloading data.")
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/multilabelFridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-classification/multilabelFridgeObjects.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -135,7 +135,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images",
-        name="fridge-items-images-2",
+        name="fridge-items-images-ml-ft",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)

cli/foundation-models/system/finetune/image-instance-segmentation/prepare_data.py

@@ -157,7 +157,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
     os.makedirs(dataset_parent_dir, exist_ok=True)
 
     # Download data
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjectsMask.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-instance-segmentation/odFridgeObjectsMask.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -184,7 +184,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images instance segmentation",
-        name="fridge-items-images-instance-segmentation",
+        name="fridge-items-images-is-ft",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)
@@ -198,6 +198,8 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
     subprocess.check_call(
         [sys.executable, "-m", "pip", "install", "scikit-image==0.19.3"]
     )
+    # Install numpy version compatible with scikit-image==0.19.3.
+    subprocess.check_call([sys.executable, "-m", "pip", "install", "numpy==1.26.4"])
     subprocess.check_call([sys.executable, "-m", "pip", "install", "simplification"])
     print("done")
 

cli/foundation-models/system/finetune/image-object-detection/prepare_data.py

@@ -160,7 +160,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
     os.makedirs(dataset_parent_dir, exist_ok=True)
 
     # download data
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-object-detection/odFridgeObjects.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -187,7 +187,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images Object detection",
-        name="fridge-items-images-object-detection",
+        name="fridge-items-images-od-ft",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)

cli/foundation-models/system/inference/image-classification/prepare_data.py

@@ -21,9 +21,9 @@ def download_and_unzip(dataset_parent_dir: str, is_multilabel_dataset: int) -> N
 
     # download data
     if is_multilabel_dataset == 0:
-        download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/fridgeObjects.zip"
+        download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-classification/fridgeObjects.zip"
     else:
-        download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/multilabelFridgeObjects.zip"
+        download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-classification/multilabelFridgeObjects.zip"
     print(f"Downloading data from {download_url}")
 
     # Extract current dataset name from dataset url

cli/foundation-models/system/inference/image-embeddings/prepare_data.py

@@ -20,7 +20,7 @@ def download_and_unzip(dataset_parent_dir: str) -> None:
     os.makedirs(dataset_parent_dir, exist_ok=True)
 
     # download data
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/fridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-classification/fridgeObjects.zip"
     print(f"Downloading data from {download_url}")
 
     # Extract current dataset name from dataset url

cli/foundation-models/system/inference/image-instance-segmentation/prepare_data.py

@@ -19,7 +19,7 @@ def download_and_unzip(dataset_parent_dir: str) -> None:
 
     # download data
 
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjectsMask.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-instance-segmentation/odFridgeObjectsMask.zip"
     print(f"Downloading data from {download_url}")
 
     # Extract current dataset name from dataset url

cli/foundation-models/system/inference/image-object-detection/prepare_data.py

@@ -19,7 +19,7 @@ def download_and_unzip(dataset_parent_dir: str) -> None:
 
     # download data
 
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-object-detection/odFridgeObjects.zip"
     print(f"Downloading data from {download_url}")
 
     # Extract current dataset name from dataset url

cli/foundation-models/system/inference/image-text-embeddings/prepare_data.py

@@ -20,7 +20,7 @@ def download_and_unzip(dataset_parent_dir: str) -> None:
     os.makedirs(dataset_parent_dir, exist_ok=True)
 
     # download data
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/fridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-classification/fridgeObjects.zip"
     print(f"Downloading data from {download_url}")
 
     # Extract current dataset name from dataset url

cli/foundation-models/system/inference/image-to-text/prepare_data.py

@@ -18,7 +18,7 @@ def download_and_unzip(dataset_parent_dir: str) -> None:
     os.makedirs(dataset_parent_dir, exist_ok=True)
 
     # download data
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-object-detection/odFridgeObjects.zip"
     print(f"Downloading data from {download_url}")
 
     # Extract current dataset name from dataset url

cli/foundation-models/system/inference/mask-generation/prepare_data.py

@@ -19,7 +19,7 @@ def download_and_unzip(dataset_parent_dir: str) -> None:
 
     # download data
 
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-object-detection/odFridgeObjects.zip"
     print(f"Downloading data from {download_url}")
 
     # Extract current dataset name from dataset url

cli/foundation-models/system/inference/visual-question-answering/prepare_data.py

@@ -18,7 +18,7 @@ def download_and_unzip(dataset_parent_dir: str) -> None:
     os.makedirs(dataset_parent_dir, exist_ok=True)
 
     # download data
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-object-detection/odFridgeObjects.zip"
     print(f"Downloading data from {download_url}")
 
     # Extract current dataset name from dataset url

cli/foundation-models/system/inference/zero-shot-image-classification/prepare_data.py

@@ -21,7 +21,7 @@ def download_and_unzip(dataset_parent_dir: str) -> None:
     os.makedirs(dataset_parent_dir, exist_ok=True)
 
     # download data
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/fridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-classification/fridgeObjects.zip"
     print(f"Downloading data from {download_url}")
 
     # Extract current dataset name from dataset url

cli/jobs/automl-standalone-jobs/cli-automl-image-classification-multiclass-task-fridge-items/prepare_data.py

@@ -105,7 +105,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
 
     # download data
     print("Downloading data.")
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/fridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-classification/fridgeObjects.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -132,7 +132,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images",
-        name="fridge-items-images-2",
+        name="fridge-items-images-mc",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)

cli/jobs/automl-standalone-jobs/cli-automl-image-classification-multilabel-task-fridge-items/prepare_data.py

@@ -108,7 +108,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
 
     # download data
     print("Downloading data.")
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/multilabelFridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-classification/multilabelFridgeObjects.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -135,7 +135,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images",
-        name="fridge-items-images-2",
+        name="fridge-items-images-ml",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)

cli/jobs/automl-standalone-jobs/cli-automl-image-instance-segmentation-task-fridge-items/prepare_data.py

@@ -40,7 +40,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
     os.makedirs(dataset_parent_dir, exist_ok=True)
 
     # download data
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjectsMask.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-instance-segmentation/odFridgeObjectsMask.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -67,7 +67,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images instance segmentation",
-        name="fridge-items-images-instance-segmentation",
+        name="fridge-items-images-is",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)
@@ -81,6 +81,8 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
     subprocess.check_call(
         [sys.executable, "-m", "pip", "install", "scikit-image==0.19.3"]
     )
+    # Install numpy version compatible with scikit-image==0.19.3.
+    subprocess.check_call([sys.executable, "-m", "pip", "install", "numpy==1.26.4"])
     subprocess.check_call([sys.executable, "-m", "pip", "install", "simplification"])
     print("done")
 

cli/jobs/automl-standalone-jobs/cli-automl-image-object-detection-task-fridge-items/prepare_data.py

@@ -143,7 +143,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
     os.makedirs(dataset_parent_dir, exist_ok=True)
 
     # download data
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-object-detection/odFridgeObjects.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -170,7 +170,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images Object detection",
-        name="fridge-items-images-object-detection",
+        name="fridge-items-images-od",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)

cli/jobs/pipelines/automl/image-instance-segmentation-task-fridge-items-pipeline/prepare_data.py

@@ -40,7 +40,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
     os.makedirs(dataset_parent_dir, exist_ok=True)
 
     # download data
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjectsMask.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-instance-segmentation/odFridgeObjectsMask.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -67,7 +67,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images instance segmentation",
-        name="fridge-items-images-instance-segmentation",
+        name="fridge-items-images-is-p",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)
@@ -81,6 +81,8 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
     subprocess.check_call(
         [sys.executable, "-m", "pip", "install", "scikit-image==0.19.3"]
     )
+    # Install numpy version compatible with scikit-image==0.19.3.
+    subprocess.check_call([sys.executable, "-m", "pip", "install", "numpy==1.26.4"])
     subprocess.check_call([sys.executable, "-m", "pip", "install", "simplification"])
     print("done")
 

cli/jobs/pipelines/automl/image-multiclass-classification-fridge-items-pipeline/prepare_data.py

@@ -105,7 +105,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
 
     # download data
     print("Downloading data.")
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/fridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-classification/fridgeObjects.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -132,7 +132,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images",
-        name="fridge-items-images-2",
+        name="fridge-items-images-mc-p",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)

cli/jobs/pipelines/automl/image-multilabel-classification-fridge-items-pipeline/prepare_data.py

@@ -108,7 +108,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
 
     # download data
     print("Downloading data.")
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/multilabelFridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-classification/multilabelFridgeObjects.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -135,7 +135,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images",
-        name="fridge-items-images-2",
+        name="fridge-items-images-ml-p",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)

cli/jobs/pipelines/automl/image-object-detection-task-fridge-items-pipeline/prepare_data.py

@@ -143,7 +143,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
     os.makedirs(dataset_parent_dir, exist_ok=True)
 
     # download data
-    download_url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjects.zip"
+    download_url = "https://automlsamplenotebookdata.blob.core.windows.net/image-object-detection/odFridgeObjects.zip"
 
     # Extract current dataset name from dataset url
     dataset_name = os.path.basename(download_url).split(".")[0]
@@ -170,7 +170,7 @@ def upload_data_and_create_jsonl_mltable_files(ml_client, dataset_parent_dir):
         path=dataset_dir,
         type=AssetTypes.URI_FOLDER,
         description="Fridge-items images Object detection",
-        name="fridge-items-images-object-detection",
+        name="fridge-items-images-od-p",
     )
 
     uri_folder_data_asset = ml_client.data.create_or_update(my_data)

sdk/python/foundation-models/system/evaluation/image-classification/multiclass-classification/image-multiclass-classification.ipynb

@@ -10,7 +10,7 @@
     "This sample shows how use the evaluate a group of models against a given set of metrics for the `image-classification` task. \n",
     "\n",
     "### Evaluation dataset\n",
-    "We will use the [fridgeObjects](https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/fridgeObjects.zip) dataset.\n",
+    "We will use the [fridgeObjects](https://automlsamplenotebookdata.blob.core.windows.net/image-classification/fridgeObjects.zip) dataset.\n",
     "\n",
     "### Model\n",
     "The goal of evaluating models is to compare their performance on a variety of metrics. `image-classification` is a generic task type. As such, the models you pick to compare must be finetuned for the same scenario. Given that we have the dataset, we would like to look for models finetuned for this specific scenario. We will compare `microsoft-beit-base-patch16-224-pt22k-ft22k` and `microsoft-swinv2-base-patch4-window12-192-22k` in this sample, which are available in the `azureml` system registry.\n",
@@ -258,7 +258,7 @@
    "source": [
     "### 4. Prepare the dataset for fine-tuning the model\n",
     "\n",
-    "We will use the [fridgeObjects](https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/fridgeObjects.zip) dataset. The fridge object dataset is stored in a directory. There are four different folders inside:\n",
+    "We will use the [fridgeObjects](https://automlsamplenotebookdata.blob.core.windows.net/image-classification/fridgeObjects.zip) dataset. The fridge object dataset is stored in a directory. There are four different folders inside:\n",
     "- /water_bottle\n",
     "- /milk_bottle\n",
     "- /carton\n",
@@ -288,7 +288,7 @@
     "os.makedirs(dataset_parent_dir, exist_ok=True)\n",
     "\n",
     "# download data\n",
-    "download_url = \"https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/fridgeObjects.zip\"\n",
+    "download_url = \"https://automlsamplenotebookdata.blob.core.windows.net/image-classification/fridgeObjects.zip\"\n",
     "\n",
     "# Extract current dataset name from dataset url\n",
     "dataset_name = os.path.split(download_url)[-1].split(\".\")[0]\n",

sdk/python/foundation-models/system/evaluation/image-classification/multilabel-classification/image-multilabel-classification.ipynb

@@ -285,7 +285,7 @@
     "os.makedirs(dataset_parent_dir, exist_ok=True)\n",
     "\n",
     "# download data\n",
-    "download_url = \"https://cvbp-secondary.z19.web.core.windows.net/datasets/image_classification/multilabelFridgeObjects.zip\"\n",
+    "download_url = \"https://automlsamplenotebookdata.blob.core.windows.net/image-classification/multilabelFridgeObjects.zip\"\n",
     "\n",
     "# Extract current dataset name from dataset url\n",
     "dataset_name = os.path.split(download_url)[-1].split(\".\")[0]\n",