ds_train = ds_train.map(scale,
num_parallel_calls=tf.data.experimental.AUTOTUNE)
ds_train = ds_train.cache()
ds_train = ds_train.shuffle(ds_info.splits['train'].num_examples)
ds_train = ds_train.batch(128)
ds_train = ds_train.prefetch(tf.data.experimental.AUTOTUNE)
model = KerasModel(input_shape=(28, 28, 1))
ds_test = ds_test.map(scale, num_parallel_calls=tf.data.experimental.AUTOTUNE)
ds_test = ds_test.batch(128)
ds_test = ds_test.cache()
ds_test = ds_test.prefetch(tf.data.experimental.AUTOTUNE)
logdir = "logs/" + datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = keras.callbacks.TensorBoard(log_dir=logdir)
model.compile(
tf.keras.optimizers.Adam(0.001),
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=[tf.keras.metrics.SparseCategoricalAccuracy()])
model.fit(ds_train,
epochs=6,
validation_data=ds_test,
batch_size=50,
verbose=True,
callbacks=[tensorboard_callback])
model.summary()
print("train_x", train_x.shape, train_x.dtype)
input_shape = (img_width, img_height, img_num_channels)
logdir = "logs/" + datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = keras.callbacks.TensorBoard(log_dir=logdir)
model = KerasModel(input_shape)
# tf.keras.utils.plot_model(model, to_file='model_plot.png', show_shapes=True, show_layer_names=True)
model.compile(
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer=keras.optimizers.Adam(0.001),
metrics=[tf.keras.metrics.SparseCategoricalAccuracy()])
# Fit data to model
history = model.fit(train_x,
train_y,
callbacks=[tensorboard_callback],
batch_size=50,
epochs=6,
verbose=True,
validation_split=0.2)
model.summary()
score = model.evaluate(test_x, test_y, verbose=0)
model.save('saved_model/model')
probabilities = model.predict(test_x, verbose=True)
print(probabilities)
if model_to_run == "KERAS_CNN":
# ################################################ KERAS MODEL ################################################### #
# These file paths are specified so that model parameters can be saved after training
model_name_json_path = os.path.join(os.path.abspath(__file__), '..',
'data', 'Keras_best_model.json')
model_name_h5_path = os.path.join(os.path.abspath(__file__), '..',
'data', 'Keras_best_model.h5')
y_train = train_labels.numpy()
X_train = data_loaders_original["train"].dataset.imgs
X_test = data_loaders_original["test"].dataset.imgs
keras_model = KerasModel(model_name_json_path=model_name_json_path,
model_name_h5_path=model_name_h5_path,
X=X_train)
keras_model.fit(X=X_train, y=y_train)
y_pred = keras_model.predict(X_train)
tr_error = np.mean(y_pred != y_train[:, None])
print(f"Keras Model Training Error is: {tr_error}")
test_labels = keras_model.predict(X_test)
save_results_in_csv(test_labels)
elif model_to_run == "TRANSFER_LEARNING":
### load Resnet152 pre-trained model
model_conv = torchvision.models.resnet152(pretrained=True)
model = TransferLearningModel(model_conv)
#Train the model with pre-trained Resnet
print("Training model...")
bst3.fit(X_train, y_train)
# ------------------------------------------------------------------
from keras.callbacks import Callback as keras_clb
random.seed(666)
np.random.seed(666)
class LearningRateClb(keras_clb):
def on_epoch_end(self, epoch, logs={}):
if epoch == 300:
self.model.optimizer.lr.set_value(0.01)
bst4 = KerasModel(cols_k2, 600)
bst4.fit_process(X_train_nn, y_train)
bst4.fit(X_train_nn, y_train, callbacks=[LearningRateClb()])
# ------------------------------------------------------------------
bst5 = LogisticRegression()
bst5.fit(X_train_reg, y_train)
# ------------------------------------------------------------------
params = {
'silent': 1,
'objective': 'binary:logistic',
'max_depth': 3,
'eta': 0.01,
'subsample': 0.65,
'colsample_bytree': 0.3,
'min_child_weight': 5,
'n': 1140,
}
def get_real_data():
#df = util.load_data_to_dataframe('dataset/val_test_split.json')
#unseen_test = create_features(df)
#unseen_test.to_csv('cache/val_test_split.csv', index=False)
unseen_test = filterout_mac_features(pd.read_csv('cache/val_test_split.csv'))
train_feats, train_labels, _ = get_feats_labels_ids(unseen_test)
return train_feats, train_labels
X, Y, X_test, Y_test = get_data()
# PART 2 FIT MODEL
model = KerasModel()
model.fit(X, Y)
print("predicting on kfold validation")
# PART 5 EVALUATE ON UNSEEN
X_real, Y_real = get_real_data()
real_predict = model.predict(X_real)
print(f"Average f1s on unseen: {f1_score(Y_real, real_predict, average='micro')}")
# PART 6 PREPARE SUBMISSION
def get_data_for_submitting():
#df_test = util.load_data_to_dataframe('dataset/test.json')
#prepared_df = create_features(df_test)
#prepared_df.to_csv('cache/test.csv', index=False)
prepared_df = filterout_mac_features(pd.read_csv('cache/test.csv'))