def main():
file_path = ".model_weights.hdf5"
callbacks = get_callbacks(filepath=file_path, patience=10)
print("Load data...")
#Load the data.
train = pd.read_json("../data/train.json")
#test = pd.read_json("../data/test.json")
print("Data loading complete")
print("Feed raw data into data pipeline...")
all_X_train = data_pipeline(train)
all_Y_train = train.loc[:, 'is_iceberg']
print("Data pipeline operations should be complete")
print("carve data into train/dev/test sets")
# high iteration training/testing so carve out a final validation block
# which will be scored 10 times max
# keep the seed stable so we're not inadvertently using all of the data/overfitting
X_train_work, X_test, y_train_work, y_test = train_test_split(
all_X_train, all_Y_train, random_state=317, train_size=0.75)
# now do the actual split for the train/dev sets
X_train, X_dev, y_train, y_dev = train_test_split(X_train_work,
y_train_work,
train_size=0.80)
print("data carving completed")
print("attempt to augment data")
X_train, y_train = augment_data(X_train, y_train)
print("data augmentation complete")
# epochs for model
epochs = 150
learning_rate = 0.0001
lr_decay = 0.5e-5
batch_size = 128
drop_out = 0.35
print("create Keras model")
gmodel = getModel(learning_rate=learning_rate,
lr_decay=lr_decay,
drop_out=drop_out)
print("fit Keras NN")
hist = gmodel.fit(X_train,
y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(X_dev, y_dev),
callbacks=callbacks)
print("\n\n\n\nModel fit completed")
print("plot model error/accuracy curves")
plot_hist(hist, epochs, learning_rate, batch_size, drop_out, lr_decay)
print("score model")
score_model(gmodel, file_path, X_train, y_train, X_dev, y_dev)
def main():
_run = True
count = 0
while _run is True:
try:
count += 1
file_path = ".{:}_indigo_model_weights.hdf5".format(count)
callbacks = get_callbacks(filepath=file_path)
print("Load data...")
# Load the data.
train = pd.read_json("../data/train.json")
# test = pd.read_json("../data/test.json")
print("Data loading complete")
print("Feed raw data into data pipeline...")
all_X_pics, standardized_params = data_pipeline(train)
# all_Y_train = train.loc[:,'is_iceberg']
# figure out extra X features from training data
inc_angle = pd.to_numeric(train.loc[:, "inc_angle"],
errors="coerce")
inc_angle[np.isnan(inc_angle)] = inc_angle.mean()
# inc_angle = np.array(inc_angle, dtype=np.float32)
# TODO: enable this?
inc_angle, inc_std_params = standardize(inc_angle)
# because there used to be a column for inc_angle isnan, but that seems
# to cause issues as that only occurs in training data but not test data
# Get labels
all_Y_labels = train.loc[:, "is_iceberg"]
print("Data pipeline operations should be complete")
print("carve data into train/dev/test sets")
# high iteration training/testing so carve out a final validation block
# which will be scored 10 times max
# keep the seed stable so we're not inadvertently using all of the data/overfitting
# keys: "X_images_train", "inc_angle_train", "y_train"
# "X_images_dev", "inc_angle_dev", y_dev"
# "X_images_test", "inc_angle_test", y_test"
data_dict = train_test_dev_split(
(all_X_pics, inc_angle, all_Y_labels))
print("X_images_train shape:", data_dict["X_images_train"].shape)
print("inc_angle_train shape:", data_dict["inc_angle_train"].shape)
print("y_train shape:", data_dict["y_train"].shape)
print("X_images_dev shape:", data_dict["X_images_dev"].shape)
print("inc_angle_dev shape:", data_dict["inc_angle_dev"].shape)
print("y_dev shape:", data_dict["y_dev"].shape)
print("X_images_test shape:", data_dict["X_images_test"].shape)
print("inc_angle_test shape:", data_dict["inc_angle_test"].shape)
print("y_test shape:", data_dict["y_test"].shape)
print("data carving completed")
print("attempt to augment data")
# X_train_pics, X_train_nonpics, y_train = augment_data(X_train_pics, X_train_nonpics, y_train)
data_dict["X_images_train"], data_amp = data_augmentation(
data_dict["X_images_train"], ud=True, rotate90=True)
data_dict["inc_angle_train"] = amplify_data(
data_dict["inc_angle_train"], data_amp)
data_dict["y_train"] = amplify_data(data_dict["y_train"], data_amp)
# random shuffle the arrays because currently it's first half original
# second half mirror. This might cause some weirdness in training?
p = np.random.permutation(data_dict["X_images_train"].shape[0])
print("shuffle augmented data")
# now shuffly augmented data:
data_dict["X_images_train"][p]
data_dict["inc_angle_train"][p]
data_dict["y_train"][p]
# return double_X_train_images[p], double_X_train_nonimages[p], double_y_train[p]
print("data augmentation complete")
# epochs for model
epochs = 100
# aiming for ~0.001 - 0.0001
_exp = (np.random.uniform(-5.5, -3.0))
learning_rate = 4**_exp
# aiming for ~0.0001 - 0.000001
_exp = (np.random.uniform(-8.5, -6.5))
lr_decay = 4.0**_exp
# learning_rate = 0.0001
# lr_decay = 5e-6
batches = [16, 32, 48, 64, 96, 128]
batch_size = batches[np.random.randint(0, len(batches) - 1)]
drop_out = np.random.uniform(0.05, 0.6)
# batch_size = 32
# drop_out = 0.275
print("create Keras model")
# icy_model = tiny_icy_model((75, 75, 3), drop_out)
_model = gmodel2(learning_rate, drop_out)
mypotim = Adam(lr=learning_rate,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-08,
decay=lr_decay)
_model.compile(loss='binary_crossentropy',
optimizer=mypotim,
metrics=['accuracy'])
# _model.summary()
print("fit Keras NN")
time.sleep(5.0)
print("Launching ~ ~ ~ >>-----<>")
hist = _model.fit(
[data_dict["X_images_train"], data_dict["inc_angle_train"]],
data_dict["y_train"],
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=([
data_dict["X_images_dev"], data_dict["inc_angle_dev"]
], data_dict["y_dev"]),
callbacks=callbacks)
print("\n\n\nModel fit completed")
print("plot model error/accuracy curves")
plot_hist(hist, epochs, learning_rate, batch_size, drop_out,
lr_decay)
print("score model")
score_test = new_score_model(_model, file_path, data_dict)
if score_test is not None:
df_test = pd.read_json('../data/test.json')
test_pics, _ = data_pipeline(df_test, standardized_params)
test_inc_angle = pd.to_numeric(df_test.loc[:, "inc_angle"],
errors="coerce")
test_inc_angle[np.isnan(
test_inc_angle)] = test_inc_angle.mean()
# inc_angle = np.array(inc_angle, dtype=np.float32)
# TODO: enable this?
# has the (mean, std) from standardizing inc_angle earlier
test_inc_angle, _ = standardize(test_inc_angle, inc_std_params)
# because there used to be a column for inc_angle isnan, but that seems
# to cause issues as that only occurs in training data but not test data
pred_test = _model.predict([test_pics, test_inc_angle])
submission = pd.DataFrame({
'id':
df_test["id"],
'is_iceberg':
pred_test.reshape((pred_test.shape[0]))
})
print(submission.head(10))
file_name = '{:1.4f}_cnn.csv'.format(score_test)
submission.to_csv(file_name, index=False)
except ValueError:
print(ValueError)
def main():
file_path = ".model_weights.hdf5"
callbacks = get_callbacks(filepath=file_path, patience=10)
print("Load data...")
# Load the data.
train = pd.read_json("../data/train.json")
# test = pd.read_json("../data/test.json")
print("Data loading complete")
print("Feed raw data into data pipeline...")
all_X_pics = data_pipeline(train)
# all_Y_train = train.loc[:,'is_iceberg']
# figure out extra X features from training data
inc_angle = pd.to_numeric(train.loc[:, "inc_angle"], errors="coerce")
inc_angle[np.isnan(inc_angle)] = inc_angle.mean()
# inc_angle = np.array(inc_angle, dtype=np.float32)
# inc_angle = standardize(inc_angle)
# print("inc_angle type: ", type(inc_angle))
# #
# inc_angle = tf.convert_to_tensor(inc_angle, np.float32)
# because there used to be a column for inc_angle isnan, but that seems
# to cause issues as that only occurs in training data but not test data
all_X_nonpics = inc_angle
# Get labels
all_Y_labels = train.loc[:, "is_iceberg"]
# make X data linspace so that we can use train_test_split on that and then use
# indices to get the slices that we need
x_indices = np.arange(all_X_pics.shape[0])
print("all x pics shape:", all_X_pics.shape)
print("all x nonpics shape:", all_X_nonpics.shape)
print("shape of x_indices:", x_indices.shape)
print("shape of y labels:", all_Y_labels.shape)
print("Data pipeline operations should be complete")
print("carve data into train/dev/test sets")
# high iteration training/testing so carve out a final validation block
# which will be scored 10 times max
# keep the seed stable so we're not inadvertently using all of the data/overfitting
X_train_work_indices, X_test_indices, y_train_work, y_test = train_test_split(x_indices, all_Y_labels, random_state=317, train_size=0.85)
# figure out what the train slices are
# these slices are work in progress as they will be sliced again
X_train_work_pics = all_X_pics[X_train_work_indices]
X_train_work_nonpics = all_X_nonpics[X_train_work_indices]
# figure out the test holdout slices
X_test_pics = all_X_pics[X_test_indices]
X_test_nonpics = all_X_nonpics[X_test_indices]
# make new linspace to get sliced
x_indices = np.arange(X_train_work_pics.shape[0])
# now do the actual split for the train/dev sets
X_train_indices, X_dev_indices, y_train, y_dev = train_test_split(x_indices, y_train_work, train_size=0.80, random_state=12018)
X_train_pics = X_train_work_pics[X_train_indices]
X_train_nonpics = X_train_work_nonpics[X_train_indices]
X_dev_pics = X_train_work_pics[X_dev_indices]
X_dev_nonpics = X_train_work_nonpics[X_dev_indices]
print("X_train_images shape:", X_train_pics.shape)
print("X_train_non_images shape:", X_train_nonpics.shape)
print("y_Train shape:", y_train.shape)
print("data carving completed")
print("attempt to augment data")
X_train_pics, X_train_nonpics, y_train = augment_data(X_train_pics, X_train_nonpics, y_train)
print("data augmentation complete")
# epochs for model
epochs = 50
learning_rate = 0.001
lr_decay = 1e-6
batch_size = 32
drop_out = 0.20
print("create Keras model")
# icy_model = tiny_icy_model((75, 75, 3), drop_out)
_model = gmodel2(learning_rate, lr_decay, drop_out)
mypotim = Adam(lr=learning_rate,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-08,
decay=lr_decay)
_model.compile(loss='binary_crossentropy',
optimizer=mypotim,
metrics=['accuracy'])
# optimo = Adam(lr=learning_rate, decay=lr_decay)
#
# _model.compile(optimizer=optimo, loss="binary_crossentropy", metrics=["accuracy"])
_model.summary()
# gmodel = getModel(learning_rate=learning_rate, lr_decay=lr_decay, drop_out=drop_out)
print("fit Keras NN")
# hist = icy_model.fit([X_train_pics, X_train_nonpics], y_train,
# batch_size=batch_size,
# epochs=epochs,
# verbose=1,
# validation_data=([X_dev_pics, X_dev_nonpics], y_dev),
# callbacks=callbacks)
# hist = gmodel.fit(X_train, y_train,
# batch_size=batch_size,
# epochs=epochs,
# verbose=1,
# validation_data=(X_dev, y_dev),
# callbacks=callbacks)
hist = _model.fit([X_train_pics, X_train_nonpics], y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=([X_dev_pics, X_dev_nonpics], y_dev),
callbacks=callbacks)
print("\n\n\nModel fit completed")
print("plot model error/accuracy curves")
plot_hist(hist, epochs, learning_rate, batch_size, drop_out, lr_decay)
print("score model")
score_model(_model, file_path, [X_train_pics, X_train_nonpics], y_train,
[X_dev_pics, X_dev_nonpics], y_dev)