import tensorflow as tf
tf.version.VERSION

'2.6.0'

! pip install -q tensorflow-cloud

import tensorflow_cloud as tfc
tfc.__version__

import sys

# Set Google Cloud Specific parameters

# TODO: Please set GCP_PROJECT_ID to your own Google Cloud project ID.
GCP_PROJECT_ID = 'YOUR_PROJECT_ID'

# TODO: set GCS_BUCKET to your own Google Cloud Storage (GCS) bucket.
GCS_BUCKET = 'YOUR_GCS_BUCKET_NAME'

# DO NOT CHANGE: Currently only the 'us-central1' region is supported.
REGION = 'us-central1'

# OPTIONAL: You can change the job name to any string.
JOB_NAME = 'nasnet'

# Setting location were training logs and checkpoints will be stored
GCS_BASE_PATH = f'gs://{GCS_BUCKET}/{JOB_NAME}'
TENSORBOARD_LOGS_DIR = os.path.join(GCS_BASE_PATH,"logs")
MODEL_CHECKPOINT_DIR = os.path.join(GCS_BASE_PATH,"checkpoints")
SAVED_MODEL_DIR = os.path.join(GCS_BASE_PATH,"saved_model")

# Using tfc.remote() to ensure this code only runs in notebook
if not tfc.remote():

    # Authentication for Kaggle Notebooks
    if "kaggle_secrets" in sys.modules:
        from kaggle_secrets import UserSecretsClient
        UserSecretsClient().set_gcloud_credentials(project=GCP_PROJECT_ID)

    # Authentication for Colab Notebooks
    if "google.colab" in sys.modules:
        from google.colab import auth
        auth.authenticate_user()
        os.environ["GOOGLE_CLOUD_PROJECT"] = GCP_PROJECT_ID

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()

# Setting input specific parameters
# The model expects input of dimension (INPUT_IMG_SIZE, INPUT_IMG_SIZE, 3)
INPUT_IMG_SIZE = 32
NUM_CLASSES = 10

from tensorflow.keras.layers.experimental import preprocessing
from tensorflow.keras.models import Sequential


img_augmentation = Sequential(
    [
        # Resizing input to better match ImageNet size
        preprocessing.Resizing(256, 256),
        preprocessing.RandomRotation(factor=0.15),
        preprocessing.RandomFlip(),
        preprocessing.RandomContrast(factor=0.1),
    ],
    name="img_augmentation",
)

from tensorflow.keras import layers

def build_model(num_classes, input_image_size):
    inputs = layers.Input(shape=(input_image_size, input_image_size, 3))
    x = img_augmentation(inputs)

    model = tf.keras.applications.NASNetMobile(
        input_shape=None,
        include_top=False,
        weights="imagenet",
        input_tensor=x,
        pooling=None,
        classes=num_classes,
    )

    # Freeze the pretrained weights
    model.trainable = False

    # We unfreeze the top 20 layers while leaving BatchNorm layers frozen
    for layer in model.layers[-20:]:
        if not isinstance(layer, layers.BatchNormalization):
            layer.trainable = True

    # Rebuild top
    x = layers.GlobalAveragePooling2D(name="avg_pool")(model.output)
    x = layers.BatchNormalization()(x)

    x = layers.Dense(128, activation="relu")(x)
    x = layers.Dense(64, activation="relu")(x)
    outputs = layers.Dense(num_classes, activation="softmax", name="pred")(x)

    # Compile
    model = tf.keras.Model(inputs, outputs, name="NASNetMobile")
    optimizer = tf.keras.optimizers.Adam(learning_rate=3e-4)
    model.compile(
        optimizer=optimizer,
        loss="sparse_categorical_crossentropy",
        metrics=["accuracy"]
    )
    return model

model = build_model(NUM_CLASSES, INPUT_IMG_SIZE)

if tfc.remote():
    # Configure Tensorboard logs
    callbacks=[
        tf.keras.callbacks.TensorBoard(log_dir=TENSORBOARD_LOGS_DIR),
        tf.keras.callbacks.ModelCheckpoint(
            MODEL_CHECKPOINT_DIR,
            save_best_only=True),
        tf.keras.callbacks.EarlyStopping(
            monitor='loss',
            min_delta =0.001,
            patience=3)]

    model.fit(x=x_train, y=y_train, epochs=100,
              validation_split=0.2, callbacks=callbacks)

    model.save(SAVED_MODEL_DIR)

else:
    # Run the training for 1 epoch and a small subset of the data to validate setup
    model.fit(x=x_train[:100], y=y_train[:100], validation_split=0.2, epochs=1)

# If you are using a custom image you can install modules via requirements
# txt file.
with open('requirements.txt','w') as f:
    f.write('tensorflow-cloud\n')

# Optional: Some recommended base images. If you provide none the system
# will choose one for you.
TF_GPU_IMAGE= "tensorflow/tensorflow:latest-gpu"
TF_CPU_IMAGE= "tensorflow/tensorflow:latest"

# Submit a distributed training job using GPUs.
tfc.run(
    distribution_strategy='auto',
    requirements_txt='requirements.txt',
    docker_config=tfc.DockerConfig(
        parent_image=TF_GPU_IMAGE,
        image_build_bucket=GCS_BUCKET
        ),
    chief_config=tfc.COMMON_MACHINE_CONFIGS['K80_1X'],
      worker_config=tfc.COMMON_MACHINE_CONFIGS['K80_1X'],
      worker_count=3,
    job_labels={'job': JOB_NAME}
)

%load_ext tensorboard
%tensorboard --logdir $TENSORBOARD_LOGS_DIR

trained_model = tf.keras.models.load_model(SAVED_MODEL_DIR)
trained_model.summary()