[Under development]
This repository contains U-Net model implementation (originally proposed in U-Net: Convolutional Networks for Biomedical Image Segmentation) with usage of Tensoflow TPUEstimators API.
Check your current Cloud TPU configuration (in Google Cloud Shell):
ctpu print-configAs a result you should get the similar outcome
ctpu configuration:
name: your-user-name
project: your-project-name
zone: your-zoneTo run CTPU flock, in Google Cloud Shell, execute the following command
ZONE=YOUR-ZONE
TPU_NAME=YOUR-TPU-NAME
ctpu up --zone $ZONE --name $TPU_NAMEOnce the CTPU flock is ready, ssh to your instance
GCP_PROJECT=YOUR-GCP-PROJECT
gcloud compute --project $GCP_PROJECT ssh --zone $ZONE $TPU_NAMEExecute the following commands to create a bucket on your TPU VM instance:
GCP_PROJECT=YOUR-GCP-PROJECT
MODEL_DIR=gs://YOUR-GOOGLE-CLOUD-BUCKET
gsutil mb -p $GCP_PROJECT $MODEL_DIRIn order to train your MNIST image classifier based on U-Net architecture and with the usage of Cloud TPU use u_net_clf_tpu.py script with the following parameters:
# TPU configuration
GCP_PROJECT=YOUR-GCP-PROJECT
TPU_ZONE=YOUR-TPU-ZONE
TPU_NAME=YOUR-TPU-NAME
MODEL_DIR=gs://YOUR-GOOGLE-CLOUD-BUCKET
# problem/model configuration
PROBLEM=MNIST
TRAIN_DIR=PATH-TO-TRAIN-DIR
EVAL_DIR=PATH-TO-EVALUATION-DIR
python u_net_clf_tpu.py \
--train_dir=$TRAIN_DIR \
--eval_dir=$EVAL_DIR \
--problem=$PROBLEM \
--model_dir=$MODEL_DIR \
--tpu_name=$TPU_NAME \
--tpu_zone=$TPU_ZONE \
--gcp_project=$GCP_PROJECTgcloud auth application-default logintensorboard --logdir $MODEL_DIR