def train_mnist(config):
# https://github.com/tensorflow/tensorflow/issues/32159
import tensorflow as tf
print('Is cuda available:', tf.test.is_gpu_available())
batch_size = 128
num_classes = 10
epochs = 12
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(config["hidden"], activation="relu"),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(num_classes, activation="softmax")
])
model.compile(loss="sparse_categorical_crossentropy",
optimizer=tf.keras.optimizers.SGD(
lr=config["lr"], momentum=config["momentum"]),
metrics=["accuracy"])
model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
verbose=0,
validation_data=(x_test, y_test),
callbacks=[TuneReportCallback({"mean_accuracy": "accuracy"})])
def train_mnist(config):
# https://github.com/tensorflow/tensorflow/issues/32159
import tensorflow as tf
print('Is cuda available for trainer:', tf.test.is_gpu_available())
batch_size = 128
num_classes = 10
epochs = 200
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
# define model
inputs = tf.keras.layers.Input(shape=(28, 28))
x = tf.keras.layers.Flatten()(inputs)
# x=tf.keras.layers.LayerNormalization()(x)
for i in range(config["layers"]):
x = tf.keras.layers.Dense(units=config["hidden"],
activation=config["activation"])(x)
x = tf.keras.layers.Dropout(config["dropout"])(x)
outputs = tf.keras.layers.Dense(units=num_classes, activation="softmax")(x)
model = tf.keras.Model(inputs=inputs, outputs=outputs, name="mnist_model")
model.compile(loss="sparse_categorical_crossentropy",
optimizer=tf.keras.optimizers.Adam(lr=config["lr"]),
metrics=["accuracy"])
model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
verbose=0,
validation_data=(x_test, y_test),
callbacks=[TuneReportCallback({"mean_accuracy": "accuracy"})])
def train_unet(config,
train_dataloader=None,
val_dataloader=None,
loss=None,
metrics=None,
checkpoint_dir=None):
epochs = 15
batch_size = 1
model = get_model(backbone='vvg16',
encoder_freeze=config["encoder_freeze"],
n_classes=1,
activation='sigmoid',
dropout=config["dropout"])
model.compile(optimizer=config["optimizer"](config["learning_rate"]),
loss=loss,
metrics=metrics)
history = model.fit(train_dataloader,
steps_per_epoch=len(train_dataloader),
epochs=epochs,
verbose=0,
batch_size=batch_size,
validation_data=val_dataloader,
validation_steps=len(val_dataloader),
callbacks=[
TuneReportCallback(
{
"loss": "loss",
"iou_score": "iou_score",
"val_loss": "val_loss",
"val_iou_score": "val_iou_score",
},
on="epoch_end"),
TqdmCallback(verbose=2),
])
# save best model of the trial
with tune.checkpoint_dir(step=1) as checkpoint_dir:
checkpoint_dir = os.path.dirname(
os.path.dirname(checkpoint_dir)) # go up two directories
score_file_path = os.path.join(checkpoint_dir, 'score')
score_file_exists = os.path.isfile(score_file_path)
new_val_iou_score = history.history['val_iou_score'][0]
best_model_file_path = os.path.join(checkpoint_dir, 'best_model.h5')
if score_file_exists:
old_val_iou_score = 0
with open(score_file_path) as f:
old_val_iou_score = float(f.read())
if new_val_iou_score > old_val_iou_score:
# we have a new best model
with open(score_file_path, 'w') as f:
f.write(str(new_val_iou_score))
model.save(best_model_file_path)
else:
# first model of the trial
with open(score_file_path, 'w') as f:
f.write(str(new_val_iou_score))
model.save(best_model_file_path)
print(history.history.keys())
def train_mnist(config):
# https://github.com/tensorflow/tensorflow/issues/32159
import tensorflow as tf
import numpy as np
print('Is cuda available:', tf.test.is_gpu_available())
batch_size = config['batch_s']
num_classes = 10
epochs = 200
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
x_train = np.expand_dims(x_train, axis=3)
x_test = np.expand_dims(x_test, axis=3)
#define model
inputs = tf.keras.layers.Input(shape=(28, 28,
1)) #changed size shape=(28, 28)
x = tf.keras.layers.BatchNormalization()(inputs)
#1st conv layer
x = tf.keras.layers.Conv2D(filters=config["c1_f"],
kernel_size=config["c1_ks"],
kernel_initializer=config["init"],
activation=config["act_f1"])(x)
x = tf.keras.layers.MaxPool2D((2, 2))(x)
x = tf.keras.layers.BatchNormalization()(x)
#2nd conv layer
x = tf.keras.layers.Conv2D(filters=config["c2_f"],
kernel_size=config["c2_ks"],
kernel_initializer=config["init"],
activation=config["act_f1"])(x)
x = tf.keras.layers.MaxPool2D((2, 2))(x)
x = tf.keras.layers.BatchNormalization()(x)
x = tf.keras.layers.Flatten()(x)
x = tf.keras.layers.Dense(units=config["hidden"],
kernel_initializer=config["init"],
activation=config["act_f2"])(x)
x = tf.keras.layers.Dropout(config["drop"])(x)
x = tf.keras.layers.BatchNormalization()(x)
outputs = tf.keras.layers.Dense(units=num_classes,
kernel_initializer=config["init"],
activation="softmax")(x)
model = tf.keras.Model(inputs=inputs,
outputs=outputs,
name="mnist_conv_model")
model.compile(loss="sparse_categorical_crossentropy",
optimizer=tf.keras.optimizers.Adam(lr=config["lr"]),
metrics=["accuracy"])
model.fit(
x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
verbose=0,
validation_data=(x_test, y_test),
callbacks=[
TuneReportCallback({
"mean_accuracy":
"val_accuracy" #optional values ['loss', 'accuracy', 'val_loss', 'val_accuracy']
})
])