Image notebook/cli param update (#2435)

* notebook/cli param update * notebook param update * cli param update * notebooks updated to foundational model * vision batch deployment cli and sdk notebook (#2433) * vision batch deployment cli and sdk notebook * black formatting * Comments * comments * updated to take latest version in FT notebooks --------- Co-authored-by: grajguru <grajguru@microsoft.com> * notebook/cli param update * notebook param update * notebook/cli param update * notebook param update * cli param update * notebooks updated to foundational model * notebook/cli param update * notebook param update * notebooks updated to foundational model * notebook/cli param update * notebook param update * notebook/cli param update * notebooks updated to foundational model * cli update * doc update * addressing comments --------- Co-authored-by: Gaurav Rajguru <rajgurugaurav77@gmail.com> Co-authored-by: grajguru <grajguru@microsoft.com>
Azure · Jul 11, 2023 · a739ecf · a739ecf
1 parent b9e9c94
commit a739ecf
Show file tree

Hide file tree

Showing 7 changed files with 74 additions and 65 deletions.
diff --git a/...class-classification/hftransformers-fridgeobjects-multiclass-classification-pipeline.yaml b/...class-classification/hftransformers-fridgeobjects-multiclass-classification-pipeline.yaml
@@ -43,8 +43,8 @@ jobs:
       # Compute
       compute_model_import: ${{parent.inputs.compute_model_import}}
       compute_finetune: ${{parent.inputs.compute_finetune}}
-      number_of_gpu_to_use_finetuning: 1
-      num_nodes_finetune: 1
+      process_count_per_instance: 1
+      instance_count: 1
 
       # model
       task_name: image-classification
@@ -57,10 +57,12 @@ jobs:
       training_data: ${{parent.inputs.training_data}}
       validation_data: ${{parent.inputs.validation_data}}
 
-      image_width: 224
-      image_height: 224
-      number_of_workers: 8
+      auto_hyperparameter_selection: False
+      image_width: -1
+      image_height: -1
+      metric_for_best_model: accuracy
       apply_augmentations: True
+      number_of_workers: 8
       apply_deepspeed: False
       deepspeed_config: ${{parent.inputs.ds_finetune}}
       apply_ort: False
@@ -74,9 +76,9 @@ jobs:
       warmup_steps: 0
       optimizer: adamw_hf
       weight_decay: 0.0
+      extra_optim_args: ""
       gradient_accumulation_step: 1
       precision: 32
-      metric_for_best_model: accuracy
       label_smoothing_factor: 0.0
       random_seed: 42
       evaluation_strategy: epoch

diff --git a/...ation/multiclass-classification/hftransformers-fridgeobjects-multiclass-classification.sh b/...ation/multiclass-classification/hftransformers-fridgeobjects-multiclass-classification.sh
@@ -41,8 +41,8 @@ finetuning_pipeline_component="transformers_image_classification_pipeline"
 number_of_gpu_to_use_finetuning=$gpus_per_node # set to the number of GPUs available in the compute
 
 # 1. Install dependencies
-pip install azure-ai-ml==1.0.0
-pip install azure-identity
+pip install azure-ai-ml==1.8.0
+pip install azure-identity==1.13.0
 pip install datasets==2.3.2
 
 unameOut=$(uname -a)
@@ -127,7 +127,7 @@ then
 fi
 
 # get the latest model version
-model_version=$(az ml model show --name $model_name --label $model_label --registry-name $registry_name --query version --output tsv)
+model_version=$(az ml model show --name $aml_registry_model_name --label $model_label --registry-name $registry_name --query version --output tsv)
 
 # 4. Prepare data
 python prepare_data.py

diff --git a/...label-classification/hftransformers-fridgeobjects-multilabel-classification-pipeline.yaml b/...label-classification/hftransformers-fridgeobjects-multilabel-classification-pipeline.yaml
@@ -44,8 +44,8 @@ jobs:
       # Compute
       compute_model_import: ${{parent.inputs.compute_model_import}}
       compute_finetune: ${{parent.inputs.compute_finetune}}
-      number_of_gpu_to_use_finetuning: 1
-      num_nodes_finetune: 1
+      process_count_per_instance: 1
+      instance_count: 1
 
       # model
       task_name: image-classification-multilabel
@@ -58,10 +58,12 @@ jobs:
       training_data: ${{parent.inputs.training_data}}
       validation_data: ${{parent.inputs.validation_data}}
 
-      image_width: 224
-      image_height: 224
-      number_of_workers: 8
+      auto_hyperparameter_selection: False
+      image_width: -1
+      image_height: -1
+      metric_for_best_model: iou
       apply_augmentations: True
+      number_of_workers: 8
       apply_deepspeed: False
       deepspeed_config: ${{parent.inputs.ds_finetune}}
       apply_ort: False
@@ -75,9 +77,9 @@ jobs:
       warmup_steps: 0
       optimizer: adamw_hf
       weight_decay: 0.0
+      extra_optim_args: ""
       gradient_accumulation_step: 1
       precision: 32
-      metric_for_best_model: accuracy
       label_smoothing_factor: 0.0
       random_seed: 42
       evaluation_strategy: epoch

diff --git a/...ation/multilabel-classification/hftransformers-fridgeobjects-multilabel-classification.sh b/...ation/multilabel-classification/hftransformers-fridgeobjects-multilabel-classification.sh
@@ -41,8 +41,8 @@ finetuning_pipeline_component="transformers_image_classification_pipeline"
 number_of_gpu_to_use_finetuning=$gpus_per_node # set to the number of GPUs available in the compute
 
 # 1. Install dependencies
-pip install azure-ai-ml==1.0.0
-pip install azure-identity
+pip install azure-ai-ml==1.8.0
+pip install azure-identity==1.13.0
 pip install datasets==2.3.2
 
 unameOut=$(uname -a)
@@ -126,7 +126,7 @@ then
 fi
 
 # get the latest model version
-model_version=$(az ml model show --name $model_name --label $model_label --registry-name $registry_name --query version --output tsv)
+model_version=$(az ml model show --name $aml_registry_model_name --label $model_label --registry-name $registry_name --query version --output tsv)
 
 # 4. Prepare data
 python prepare_data.py

diff --git a/...ls/system/docs/component_docs/image_finetune/transformers_finetune_component.md b/...ls/system/docs/component_docs/image_finetune/transformers_finetune_component.md
@@ -21,17 +21,26 @@ The components can be seen here ![as shown in the figure](../../images/image_cla
 
 5. _image_height_ (int, optional)
 
-    Final Image height after augmentation that is input to the network. The default value is 224.
+    Final Image height after augmentation that is input to the network. Default value is -1 which means it would be overwritten by default image height in Hugging Face feature extractor. If either image_width or image_height is set to -1, default value would be used for both width and height.
 
 6. _image_width_ (int, optional)
 
-    Final Image width after augmentation that is input to the network. The default value is 224.
+    Final Image width after augmentation that is input to the network. Default value is -1 which means it would be overwritten by default image width in Hugging Face feature extractor. If either image_width or image_height is set to -1, default value would be used for both width and height.
 
 7. _task_name_ (string, required)
 
     Which task the model is solving.
     It could be one of [`image-classification`, `image-classification-multilabel`].
 
+7. _metric_for_best_model_ (string, optional)
+
+    Specify the metric to use to compare two different models. The default value is accuracy. It could be one of
+    [`loss`, `f1_score_macro`, 
+     `accuracy`, `precision_score_macro`, 
+     `recall_score_macro`, `iou`, 
+     `iou_macro`, `iou_micro`, 
+     `iou_weighted`]
+
 8. _apply_augmentations_ (bool, optional)
 
     If set to true, will enable data augmentations for training and validation.
@@ -81,7 +90,7 @@ The components can be seen here ![as shown in the figure](../../images/image_cla
 
 19. _learning_rate_scheduler_ (string, optional)
 
-    The learning rate scheduler to use. The default value is warmup_linear.
+    The learning rate scheduler to use.
     It could be one of [`warmup_linear`, `warmup_cosine`, `warmup_cosine_with_restarts`, `warmup_polynomial`,
     `constant`, `warmup_constant`]
 
@@ -91,13 +100,19 @@ The components can be seen here ![as shown in the figure](../../images/image_cla
 
 21. _optimizer_ (string, optional)
 
-    Optimizer to be used while training. The default value is adamw_hf.
+    Optimizer to be used while training.
     It could be one of [`adamw_hf`, `adamw`, `sgd`, `adafactor`, `adagrad`]
 
 22. _weight_decay_ (float, optional)
 
     The weight decay to apply (if not zero) to all layers except all bias and LayerNorm weights in AdamW optimizer. The default value is 0.
 
+23. _extra_optim_args_: (string, optional)
+
+    Optional additional arguments that are supplied to SGD Optimizer. The arguments should be semi-colon separated key value pairs and should be enclosed in double quotes. For example, "momentum=0.5; nesterov=True" for sgd. Please make sure to use a valid parameter names for the chosen optimizer. For exact parameter
+    names, please refer https://pytorch.org/docs/1.13/generated/torch.optim.SGD.html#torch.optim.SGD for SGD. Parameters supplied in extra_optim_args will take precedence over the parameter supplied via other arguments such as weight_decay. If weight_decay is provided via "weight_decay"
+    parameter and via extra_optim_args both, values specified in extra_optim_args will be used.
+
 23. _gradient_accumulation_step_ (int, optional)
 
     Number of updates steps to accumulate the gradients for, before performing a backward/update pass. The default value is 1.
@@ -107,9 +122,6 @@ The components can be seen here ![as shown in the figure](../../images/image_cla
     Apply mixed precision training. This can reduce memory footprint by performing operations in half-precision. The default value is 32.
     It could one of [`16`, `32`]
 
-25. _metric_for_best_model_ (string, optional)
-
-    Specify the metric to use to compare two different models. The default value is accuracy.
 
 26. _label_smoothing_factor_ (float, optional)
 

diff --git a/...on/multiclass-classification/hftransformers-fridgeobjects-multiclass-classification.ipynb b/...on/multiclass-classification/hftransformers-fridgeobjects-multiclass-classification.ipynb
@@ -43,8 +43,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install azure-ai-ml==1.0.0\n",
-    "! pip install azure-identity\n",
+    "! pip install azure-ai-ml==1.8.0\n",
+    "! pip install azure-identity==1.13.0\n",
     "! pip install datasets==2.3.2"
    ]
   },
@@ -499,9 +499,10 @@
     "    # \"model_name\": huggingface_model_name,\n",
     "    # finetune_args\n",
     "    \"auto_hyperparameter_selection\": False,\n",
-    "    \"image_width\": 224,\n",
-    "    \"image_height\": 224,\n",
+    "    \"image_width\": -1,\n",
+    "    \"image_height\": -1,\n",
     "    \"task_name\": \"image-classification\",\n",
+    "    \"metric_for_best_model\": \"accuracy\",\n",
     "    \"apply_augmentations\": True,\n",
     "    \"number_of_workers\": 8,\n",
     "    \"apply_deepspeed\": False,\n",
@@ -517,9 +518,9 @@
     "    \"warmup_steps\": 0,\n",
     "    \"optimizer\": \"adamw_hf\",\n",
     "    \"weight_decay\": 0.0,\n",
+    "    \"extra_optim_args\": \"\",\n",
     "    \"gradient_accumulation_step\": 1,\n",
     "    \"precision\": \"32\",\n",
-    "    \"metric_for_best_model\": \"accuracy\",\n",
     "    \"label_smoothing_factor\": 0.0,\n",
     "    \"random_seed\": 42,\n",
     "    \"evaluation_strategy\": \"epoch\",\n",
@@ -535,8 +536,8 @@
     "    \"resume_from_checkpoint\": False,\n",
     "    \"save_as_mlflow_model\": True,\n",
     "}\n",
-    "number_of_gpu_to_use_finetuning = 1\n",
-    "num_nodes_finetune = 1\n",
+    "process_count_per_instance = 1\n",
+    "instance_count = 1\n",
     "\n",
     "# Ensure that the user provides only one of mlflow_model or model_name\n",
     "if pipeline_component_args.get(\"mlflow_model\") is None and pipeline_component_args.get(\"model_name\") is None:\n",
@@ -579,8 +580,8 @@
     "        compute_finetune=finetune_cluster_name,\n",
     "        training_data=Input(type=AssetTypes.MLTABLE, path=training_mltable_path),\n",
     "        validation_data=Input(type=AssetTypes.MLTABLE, path=validation_mltable_path),\n",
-    "        number_of_gpu_to_use_finetuning=number_of_gpu_to_use_finetuning,\n",
-    "        num_nodes_finetune=num_nodes_finetune,\n",
+    "        instance_count=instance_count,\n",
+    "        process_count_per_instance=process_count_per_instance,\n",
     "        **pipeline_component_args,\n",
     "    )\n",
     "    return {\n",
@@ -858,14 +859,14 @@
     "        success_threshold=1,\n",
     "        timeout=10,\n",
     "        period=10,\n",
-    "        initial_delay=10,\n",
+    "        initial_delay=2000,\n",
     "    ),\n",
     "    readiness_probe=ProbeSettings(\n",
     "        failure_threshold=10,\n",
     "        success_threshold=1,\n",
     "        timeout=10,\n",
     "        period=10,\n",
-    "        initial_delay=10,\n",
+    "        initial_delay=2000,\n",
     "    ),\n",
     ")\n",
     "workspace_ml_client.online_deployments.begin_create_or_update(demo_deployment).wait()\n",
@@ -923,8 +924,9 @@
     "\n",
     "\n",
     "request_json = {\n",
-    "    \"inputs\": {\n",
-    "        \"image\": [base64.encodebytes(read_image(sample_image)).decode(\"utf-8\")],\n",
+    "    \"input_data\": {\n",
+    "        \"columns\": [\"image\"],\n",
+    "        \"data\": [base64.encodebytes(read_image(sample_image)).decode(\"utf-8\")],\n",
     "    }\n",
     "}\n",
     "\n",
@@ -972,13 +974,6 @@
    "source": [
     "workspace_ml_client.online_endpoints.begin_delete(name=online_endpoint_name).wait()"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

diff --git a/...on/multilabel-classification/hftransformers-fridgeobjects-multilabel-classification.ipynb b/...on/multilabel-classification/hftransformers-fridgeobjects-multilabel-classification.ipynb
@@ -43,8 +43,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install azure-ai-ml==1.0.0\n",
-    "! pip install azure-identity\n",
+    "! pip install azure-ai-ml==1.8.0\n",
+    "! pip install azure-identity==1.13.0\n",
     "! pip install datasets==2.3.2"
    ]
   },
@@ -95,7 +95,10 @@
     "    subscription_id = \"SUBSCRIPTION_ID\"\n",
     "    resource_group = \"RESOURCE_GROUP\"\n",
     "    workspace_name = \"AML_WORKSPACE_NAME\"\n",
-    "    workspace_ml_client = MLClient(credential, subscription_id, resource_group, workspace_name)\n",
+    "\n",
+    "workspace_ml_client = MLClient(\n",
+    "    credential, subscription_id, resource_group, workspace_name\n",
+    ")\n",
     "\n",
     "registry_ml_client = MLClient(\n",
     "    credential,\n",
@@ -499,9 +502,10 @@
     "    # \"model_name\": huggingface_model_name,\n",
     "    # finetune_args\n",
     "    \"auto_hyperparameter_selection\": False,\n",
-    "    \"image_width\": 224,\n",
-    "    \"image_height\": 224,\n",
+    "    \"image_width\": -1,\n",
+    "    \"image_height\": -1,\n",
     "    \"task_name\": \"image-classification-multilabel\",\n",
+    "    \"metric_for_best_model\": \"iou\",\n",
     "    \"apply_augmentations\": True,\n",
     "    \"number_of_workers\": 8,\n",
     "    \"apply_deepspeed\": False,\n",
@@ -517,9 +521,9 @@
     "    \"warmup_steps\": 0,\n",
     "    \"optimizer\": \"adamw_hf\",\n",
     "    \"weight_decay\": 0.0,\n",
+    "    \"extra_optim_args\": \"\",\n",
     "    \"gradient_accumulation_step\": 1,\n",
     "    \"precision\": \"32\",\n",
-    "    \"metric_for_best_model\": \"accuracy\",\n",
     "    \"label_smoothing_factor\": 0.0,\n",
     "    \"random_seed\": 42,\n",
     "    \"evaluation_strategy\": \"epoch\",\n",
@@ -535,8 +539,8 @@
     "    \"resume_from_checkpoint\": False,\n",
     "    \"save_as_mlflow_model\": True,\n",
     "}\n",
-    "number_of_gpu_to_use_finetuning = 1\n",
-    "num_nodes_finetune = 1\n",
+    "process_count_per_instance = 1\n",
+    "instance_count = 1\n",
     "\n",
     "# Ensure that the user provides only one of mlflow_model or model_name\n",
     "if pipeline_component_args.get(\"mlflow_model\") is None and pipeline_component_args.get(\"model_name\") is None:\n",
@@ -579,8 +583,8 @@
     "        compute_finetune=finetune_cluster_name,\n",
     "        training_data=Input(type=AssetTypes.MLTABLE, path=training_mltable_path),\n",
     "        validation_data=Input(type=AssetTypes.MLTABLE, path=validation_mltable_path),\n",
-    "        number_of_gpu_to_use_finetuning=number_of_gpu_to_use_finetuning,\n",
-    "        num_nodes_finetune=num_nodes_finetune,\n",
+    "        instance_count=instance_count,\n",
+    "        process_count_per_instance=process_count_per_instance,\n",
     "        **pipeline_component_args,\n",
     "    )\n",
     "    return {\n",
@@ -625,7 +629,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "workspace_ml_client.jobs.stream(transformers_pipeline_run.name)"
+    "workspace_ml_client.jobs.stream(transformers_pipeline_run.name)\n"
    ]
   },
   {
@@ -919,8 +923,9 @@
     "\n",
     "\n",
     "request_json = {\n",
-    "    \"inputs\": {\n",
-    "        \"image\": [base64.encodebytes(read_image(sample_image)).decode(\"utf-8\")],\n",
+    "    \"input_data\": {\n",
+    "        \"columns\": [\"image\"],\n",
+    "        \"data\": [base64.encodebytes(read_image(sample_image)).decode(\"utf-8\")],\n",
     "    }\n",
     "}\n",
     "\n",
@@ -968,13 +973,6 @@
    "source": [
     "workspace_ml_client.online_endpoints.begin_delete(name=online_endpoint_name).wait()"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {