Training ShapeMask on Cloud TPU

This document demonstrates how to run the ShapeMask model using Cloud TPU with the COCO dataset.

The instructions below assume you are already familiar with running a model on Cloud TPU. If you are new to Cloud TPU, you can refer to the Quickstart for a basic introduction.

If you plan to train on a TPU Pod slice, review Training on TPU Pods to understand parameter changes required for Pod slices.

Objectives

Create a Cloud Storage bucket to hold your dataset and model output
Prepare the COCO dataset
Set up a Compute Engine VM and Cloud TPU node for training and evaluation
Run training and evaluation on a single Cloud TPU or a Cloud TPU Pod

Costs

This tutorial uses billable components of Google Cloud, including:

Compute Engine
Cloud TPU
Cloud Storage

Use the pricing calculator to generate a cost estimate based on your projected usage. New Google Cloud users might be eligible for a free trial.

Before you begin

Before starting this tutorial, check that your Google Cloud project is correctly set up.

Sign in to your Google Account.
If you don't already have one, sign up for a new account.
In the Cloud Console, on the project selector page, select or create a Cloud project.

Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

Go to the project selector page
Make sure that billing is enabled for your Google Cloud project. Learn how to confirm billing is enabled for your project.

This walkthrough uses billable components of Google Cloud. Check the Cloud TPU pricing page to estimate your costs. Be sure to clean up resources you create when you've finished with them to avoid unnecessary charges.

If you plan to train on a TPU Pod slice, review Training on TPU Pods to understand parameter changes required for Pod slices.

Set up your resources

This section provides information on setting up Cloud Storage, VM, and Cloud TPU resources for this tutorial.

Open a Cloud Shell window.

Open Cloud Shell
Create a variable for your project's ID.
```
export PROJECT_ID=project-id
```
Configure gcloud command-line tool to use the project where you want to create Cloud TPU.
```
gcloud config set project ${PROJECT_ID}
```
The first time you run this command in a new Cloud Shell VM, an Authorize Cloud Shell page is displayed. Click Authorize at the bottom of the page to allow gcloud to make GCP API calls with your credentials.

Create a Service Account for the Cloud TPU project.

gcloud beta services identity create --service tpu.googleapis.com --project $PROJECT_ID

The command returns a Cloud TPU Service Account with following format:

service-PROJECT_NUMBER@cloud-tpu.iam.gserviceaccount.com

Create a Cloud Storage bucket using the following command:

Note: In the following command, replace bucket-name with the name you want to assign to your bucket.
```
gsutil mb -p ${PROJECT_ID} -c standard -l europe-west4 -b on gs://bucket-name
```
This Cloud Storage bucket stores the data you use to train your model and the training results. The ctpu up tool used in this tutorial sets up default permissions for the Cloud TPU Service Account. If you want finer-grain permissions, review the access level permissions.

The bucket location must be in the same region as your virtual machine (VM) and your TPU node. VMs and TPU nodes are located in specific zones, which are subdivisions within a region.
Launch a Compute Engine VM instance.
```
$ ctpu up --project=${PROJECT_ID} \
 --zone=us-central1-a \
 --vm-only \
 --disk-size-gb=300 \
 --machine-type=n1-standard-16 \
 --tf-version=1.15.4 \
 --name=shapemask-tutorial
```
Command flag descriptions

project

Your GCP project ID

zone

The zone where you plan to create your Cloud TPU.

vm-only

Create a VM only. By default the ctpu up command creates a VM and a Cloud TPU.

disk-size-gb

The size of the hard disk in GB of the VM created by the ctpu up command.

machine-type

The machine type of the Compute Engine VM to create.

tf-version

The version of Tensorflow ctpu installs on the VM.

name

The name of the Cloud TPU to create.
The configuration you specified appears. Enter y to approve or n to cancel.
When the ctpu up command has finished executing, verify that your shell prompt has changed from username@projectname to username@vm-name. This change shows that you are now logged into your Compute Engine VM.

Note: The first time you run ctpu up on a project it may take several minutes to perform startup tasks such as SSH key propagation and API turnup. Occasionally, during the SSH key propagation, an error message (ERROR: (gcloud.compute.ssh) [/usr/bin/ssh] exited with return code [255]) is returned. If that happens, run the following command to resolve the problem.
```
gcloud compute ssh shapemask-tutorial --zone=us-central1-a
```
As you continue these instructions, run each command that begins with (vm)$ in your VM session window.
Create an environment variable to store your Cloud Storage bucket location.
```
(vm)$ export STORAGE_BUCKET=gs://bucket-name
```
Create an environment variable for the data directory.
```
(vm)$ export DATA_DIR=${STORAGE_BUCKET}/coco
```

Clone the tpu repository.

(vm)$ git clone -b shapemask https://github.com/tensorflow/tpu/

Install the packages needed to pre-process the data.

(vm)$ sudo apt-get install -y python3-tk && \
  pip3 install --user Cython matplotlib opencv-python-headless pyyaml Pillow && \
  pip3 install --user "git+https://github.com/cocodataset/cocoapi#egg=pycocotools&subdirectory=PythonAPI"

Prepare the COCO dataset

Run the download_and_preprocess_coco.sh script to convert the COCO dataset into a set of TFRecords (*.tfrecord) that the training application expects.

Note: The COCO download and conversion script takes approximately 1 hour to complete.
```
(vm)$ sudo bash /usr/share/tpu/tools/datasets/download_and_preprocess_coco.sh ./data/dir/coco
```
This installs the required libraries and then runs the preprocessing script. It outputs a number of *.tfrecord files in your local data directory.
After you convert the data into TFRecords, copy them from local storage to your Cloud Storage bucket using the gsutil command. You must also copy the annotation files. These files help validate the model's performance:
```
(vm)$ gsutil -m cp ./data/dir/coco/*.tfrecord ${DATA_DIR}
(vm)$ gsutil cp ./data/dir/coco/raw-data/annotations/*.json ${DATA_DIR}
```
Note: If you want to monitor the model's output and performance, follow the guide to setting up TensorBoard.

Set up and start the Cloud TPU

Launch a Cloud TPU resource.

Run the following command to create your Cloud TPU.

(vm)$ ctpu up --project=${PROJECT_ID} \
 --tpu-only \
 --tf-version=1.15.4 \
 --tpu-size=v3-8 \
 --name=shapemask-tutorial

The configuration you specified appears. Enter y to approve or n to cancel.

You will see a message: Operation success; not ssh-ing to Compute Engine VM due to --tpu-only flag. Since you previously completed SSH key propagation, you can ignore this message.
Add an environment variable for your Cloud TPU's name.
```
(vm)$ export TPU_NAME=shapemask-tutorial
```

Run the training and evaluation script

Create the following environment variables:

(vm)$ export MODEL_DIR=${STORAGE_BUCKET}/shapemask_exp
(vm)$ export RESNET_CHECKPOINT=gs://cloud-tpu-checkpoints/shapemask/retinanet/resnet101-checkpoint-2018-02-24
(vm)$ export TRAIN_FILE_PATTERN=${DATA_DIR}/train-*
(vm)$ export EVAL_FILE_PATTERN=${DATA_DIR}/val-*
(vm)$ export VAL_JSON_FILE=${DATA_DIR}/instances_val2017.json
(vm)$ export SHAPE_PRIOR_PATH=gs://cloud-tpu-checkpoints/shapemask/kmeans_class_priors_91x20x32x32.npy
(vm)$ export PYTHONPATH=${PYTHONPATH}:$HOME/tpu/models

Run the following script to perform training.

(vm)$ python3 ~/tpu/models/official/detection/main.py \
--model shapemask \
--use_tpu=True \
--tpu=${TPU_NAME} \
--num_cores=8 \
--model_dir=${MODEL_DIR} \
--mode="train" \
--eval_after_training=False \
--params_override="{train: {iterations_per_loop: 1000, train_batch_size: 64, total_steps: 1000, learning_rate: {total_steps: 1000, warmup_learning_rate: 0.0067, warmup_steps: 500, init_learning_rate: 0.08, learning_rate_levels: [0.008, 0.0008], learning_rate_steps: [30000, 40000]}, checkpoint: { path: ${RESNET_CHECKPOINT}, prefix: resnet101/ }, train_file_pattern: ${TRAIN_FILE_PATTERN} }, resnet: {resnet_depth: 101}, eval: { val_json_file: ${VAL_JSON_FILE}, eval_file_pattern: ${EVAL_FILE_PATTERN}, eval_samples: 5000 }, shapemask_head: {use_category_for_mask: true, shape_prior_path: ${SHAPE_PRIOR_PATH}}, shapemask_parser: {output_size: [1024, 1024]}, }"

Run the script to perform evaluation.

(vm)$ python3 ~/tpu/models/official/detection/main.py \
--model shapemask \
--use_tpu=True \
--tpu=${TPU_NAME} \
--num_cores=8 \
--model_dir=${MODEL_DIR} \
--mode="eval" \
--eval_after_training=False \
--params_override="{train: {iterations_per_loop: 1000, train_batch_size: 64, total_steps: 1000, learning_rate: {total_steps: 1000, warmup_learning_rate: 0.0067, warmup_steps: 500, init_learning_rate: 0.08, learning_rate_levels: [0.008, 0.0008], learning_rate_steps: [30000, 40000]}, checkpoint: { path: ${RESNET_CHECKPOINT}, prefix: resnet101/ }, train_file_pattern: ${TRAIN_FILE_PATTERN} }, resnet: {resnet_depth: 101}, eval: {eval_batch_size: 40, val_json_file: ${VAL_JSON_FILE}, eval_file_pattern: ${EVAL_FILE_PATTERN}, eval_samples: 5000 }, shapemask_head: {use_category_for_mask: true, shape_prior_path: ${SHAPE_PRIOR_PATH}}, shapemask_parser: {output_size: [1024, 1024]}, }""

At this point, you can either conclude this tutorial and clean up your GCP resources, or you can further explore running the model on a Cloud TPU Pod.

Scaling your model with Cloud TPU Pods

You can get results faster by scaling your model with Cloud TPU Pods. The fully supported Mask RCNN model can work with the following Pod slices:

v2-32
v3-32

When working with Cloud TPU Pods, you first train the model using a Pod, then use a single Cloud TPU device to evaluate the model.

Training with Cloud TPU Pods

If you have already deleted your Compute Engine instance, create a new one following the steps in Set up your resources.

Delete the Cloud TPU resource you created for training the model on a single Cloud TPU device.

(vm)$ ctpu delete --project=${PROJECT_ID} \
 --tpu-only \
 --zone=us-central1-a \
 --name=shapemask-tutorial

Go to your Cloud Storage bucket and delete the checkpoint file.

Run the ctpu up command, using the tpu-size parameter to specify the Pod slice you want to use. For example, the following command uses a v2-32 Pod slice.

(vm)$ ctpu up --project=${PROJECT_ID} \
  --tpu-only \
  --tpu-size=v2-32 \
  --zone=us-central1-a \
  --tf-version=1.15.4 \
  --name=shapemask-tutorial

Run the following script to train the model on a Pod.

With the given command line the training script takes approximately 45 minutes to run. To run to convergence, set total_steps to 22000.

(vm)$ python3 ~/tpu/models/official/detection/main.py \
--model shapemask \
--use_tpu=True \
--tpu=${TPU_NAME} \
--num_cores=32 \
--model_dir=${MODEL_DIR} \
--mode="train" \
--eval_after_training=False \
--params_override="{train: {iterations_per_loop: 1000, train_batch_size: 256, total_steps: 1000, learning_rate: {total_steps: 1000, warmup_learning_rate: 0.0067, warmup_steps: 500, init_learning_rate: 0.08, learning_rate_levels: [0.008, 0.0008], learning_rate_steps: [15000, 20000]}, checkpoint: { path: ${RESNET_CHECKPOINT}, prefix: resnet101/ }, train_file_pattern: ${TRAIN_FILE_PATTERN} }, resnet: {resnet_depth: 101}, eval: { val_json_file: ${VAL_JSON_FILE}, eval_file_pattern: ${EVAL_FILE_PATTERN}, eval_samples: 5000 }, shapemask_head: {use_category_for_mask: true, shape_prior_path: ${SHAPE_PRIOR_PATH}}, shapemask_parser: {output_size: [1024, 1024]}, }"

The model must be evaluated on a single Cloud TPU device. Delete the Cloud TPU Pod device.

(vm)$ ctpu delete --project=${PROJECT_ID} \
 --zone=us-central1-a \
 --tpu-only \
 --name=shapemask-tutorial

Create a single Cloud TPU resource.

(vm)$ ctpu up --project=${PROJECT_ID} \
 --tpu-only  \
 --tpu-size=v3-8 \
 --zone us-central1-a \
 --tf-version=1.15.4 \
 --name=shapemask-tutorial

Run the script to perform evaluation.

(vm)$ python3 ~/tpu/models/official/detection/main.py \
--model shapemask \
--use_tpu=True \
--tpu=${TPU_NAME} \
--num_cores=8 \
--model_dir="${MODEL_DIR} \
--mode="eval" \
--eval_after_training=False \
--params_override="{train: {iterations_per_loop: 1000, train_batch_size: 256, total_steps: 1000, learning_rate: {total_steps: 1000, warmup_learning_rate: 0.0067, warmup_steps: 500, init_learning_rate: 0.08, learning_rate_levels: [0.008, 0.0008], learning_rate_steps: [15000,20000]}, checkpoint: { path: ${RESNET_CHECKPOINT}, prefix: resnet101/ }, train_file_pattern: ${TRAIN_FILE_PATTERN} }, resnet: {resnet_depth: 101}, eval: { val_json_file: ${VAL_JSON_FILE}, eval_file_pattern: ${EVAL_FILE_PATTERN}, eval_samples: 5000 }, shapemask_head: {use_category_for_mask: true, shape_prior_path: ${SHAPE_PRIOR_PATH}}, shapemask_parser: {output_size: [1024, 1024]}, }"

Cleaning up

To avoid incurring charges to your Google Cloud Platform account for the resources used in this tutorial:

Disconnect from the Compute Engine instance, if you have not already done so:
```
(vm)$ exit
```
Your prompt should now be username@projectname, showing you are in the Cloud Shell.
In your Cloud Shell, run ctpu delete with the --zone flag you used when you set up the Cloud TPU to delete your Compute Engine VM and your Cloud TPU:
```
$ ctpu delete --project=${PROJECT_ID} \
 --zone=us-central1-a \
 --name=shapemask-tutorial
```
Important: If you set the TPU resources name when you ran ctpu up, you must specify that name with the --name flag when you run ctpu delete in order to shut down your TPU resources.
Run the following command to verify the Compute Engine VM and Cloud TPU have been shut down:
```
$ ctpu status --project=${PROJECT_ID} \
  --zone=us-central1-a \
  --name=shapemask-tutorial
```
The deletion might take several minutes. A response like the one below indicates there are no more allocated instances:
```
2018/04/28 16:16:23 WARNING: Setting zone to "us-central1-a"
No instances currently exist.
   Compute Engine VM:     --
   Cloud TPU:             --
```
Caution: All training data will be lost when you delete your bucket, so only do this step when you are finished running the tutorial.
Run gsutil as shown, replacing bucket-name with the name of the Cloud Storage bucket you created for this tutorial:
```
$ gsutil rm -r gs://bucket-name
```

What's next

In this tutorial you have trained the ShapeMask model using a sample dataset. The results of this training are (in most cases) not usable for inference. To use a model for inference you can train the data on a publicly available dataset or your own data set. Models trained on Cloud TPUs require datasets to be in TFRecord format.

You can use the dataset conversion tool sample to convert an image classification dataset into TFRecord format. If you are not using an image classification model, you will have to convert your dataset to TFRecord format yourself. For more information, see TFRecord and tf.Example

Hyperparameter tuning

To improve the model's performance with your dataset, you can tune the model's hyperparameters. You can find information about hyperparameters common to all TPU supported models on GitHub. Information about model-specific hyperparameters can be found in the source code for each model. For more information on hyperparameter tuning, see Overview of hyperparameter tuning, Using the Hyperparameter tuning service and Tune hyperparameters.

Inference

Once you have trained your model you can use it for inference (also called prediction). AI Platform is a cloud-based solution for developing, training, and deploying machine learning models. Once a model is deployed, you can use the AI Platform Prediction service.

Train with different image sizes

You can try using a larger neural network (for example, ResNet-101 instead of ResNet-50). A larger input image and a more powerful neural network will yield a slower but more precise model.

Use a different basis

Alternatively, you can explore pre-training a ResNet model on your own dataset and using it as a basis for your ShapeMask model. With some more work, you can also swap in an alternative neural network in place of ResNet. Finally, if you are interested in implementing your own object detection models, this network may be a good basis for further experimentation.