def main():
input_params = {
'use_text': True, # 是否使用text
'use_img': True, # 是否使用img
'target': 'isclick' # 预测目标
}
feature_columns, train_model_input, train_labels, test_model_input, test_labels = get_input(
**input_params)
iterations = 10 # 跑多次取平均
for i in range(iterations):
print(f'iteration {i + 1}/{iterations}')
model = DeepFM(feature_columns,
feature_columns,
use_image=input_params["use_img"],
use_text=input_params["use_text"],
embedding_size=10)
model.compile("adagrad",
"binary_crossentropy",
metrics=["binary_crossentropy"])
history = model.fit(train_model_input,
train_labels,
batch_size=4096,
epochs=1,
verbose=1,
validation_data=(test_model_input, test_labels))
model.compile(loss=tf.keras.losses.binary_crossentropy,
optimizer=tf.keras.optimizers.Adam(learning_rate=learning_rate),
metrics=METRICS)
# ---------早停法 -----
early_stopping = tf.keras.callbacks.EarlyStopping(monitor='val_auc',
verbose=1,
patience=10,
mode='max',
restore_best_weights=True)
model.fit(
train_X,
train_y,
epochs=epochs,
# callbacks=[checkpoint],
callbacks=[early_stopping, checkpoint],
batch_size=batch_size,
validation_split=0.1,
validation_data=(val_X, val_y)) # class_weight={0:1, 1:3}, # 样本均衡
print('test AUC: %f' % model.evaluate(test_X, test_y)[1])
# ------------- model evaluation in test dataset ----
train_predictions_weighted = model.predict(train_X, batch_size=batch_size)
test_predictions_weighted = model.predict(test_X, batch_size=batch_size)
# ------------- confusion matrix
from sklearn.metrics import confusion_matrix, roc_curve
import matplotlib.pyplot as plt
v_reg = 1e-4
hidden_units = [256, 128, 64]
output_dim = 1
activation = 'relu'
model = DeepFM(k, w_reg, v_reg, hidden_units, output_dim, activation)
optimizer = optimizers.SGD(0.01)
train_dataset = tf.data.Dataset.from_tensor_slices((X_train, y_train))
train_dataset = train_dataset.batch(32).prefetch(
tf.data.experimental.AUTOTUNE)
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit(train_dataset, epochs=100)
logloss, auc = model.evaluate(X_test, y_test)
print('logloss {}\nAUC {}'.format(round(logloss, 2), round(auc, 2)))
model.summary()
# summary_writer = tf.summary.create_file_writer('E:\\PycharmProjects\\tensorboard')
# for i in range(500):
# with tf.GradientTape() as tape:
# y_pre = model(X_train)
# loss = tf.reduce_mean(losses.binary_crossentropy(y_true=y_train, y_pred=y_pre))
# print(loss.numpy())
# with summary_writer.as_default():
# tf.summary.scalar("loss", loss, step=i)
# grad = tape.gradient(loss, model.variables)
# optimizer.apply_gradients(grads_and_vars=zip(grad, model.variables))
# ============================Build Model==========================
mirrored_strategy = tf.distribute.MirroredStrategy()
with mirrored_strategy.scope():
model = DeepFM(feature_columns,
hidden_units=hidden_units,
dnn_dropout=dnn_dropout)
model.summary()
# ============================Compile============================
model.compile(loss=binary_crossentropy,
optimizer=Adam(learning_rate=learning_rate),
metrics=[AUC()])
# ============================model checkpoint======================
# check_path = '../save/deepfm_weights.epoch_{epoch:04d}.val_loss_{val_loss:.4f}.ckpt'
# checkpoint = tf.keras.callbacks.ModelCheckpoint(check_path, save_weights_only=True,
# verbose=1, period=5)
# ==============================Fit==============================
model.fit(
train_X,
train_y,
epochs=epochs,
callbacks=[
EarlyStopping(monitor='val_loss',
patience=2,
restore_best_weights=True)
], # checkpoint,
batch_size=batch_size,
validation_split=0.1)
# ===========================Test==============================
print('test AUC: %f' %
model.evaluate(test_X, test_y, batch_size=batch_size)[1])
embed_dim=embed_dim,
read_part=read_part,
sample_num=sample_num,
test_size=test_size)
train_X, train_y = train
test_X, test_y = test
# ============================Build Model==========================
model = DeepFM(feature_columns,
k=k,
hidden_units=hidden_units,
dnn_dropout=dnn_dropout)
model.summary()
# ============================model checkpoint======================
# check_path = '../save/deepfm_weights.epoch_{epoch:04d}.val_loss_{val_loss:.4f}.ckpt'
# checkpoint = tf.keras.callbacks.ModelCheckpoint(check_path, save_weights_only=True,
# verbose=1, period=5)
# ============================Compile============================
model.compile(loss=binary_crossentropy,
optimizer=Adam(learning_rate=learning_rate),
metrics=[AUC()])
# ==============================Fit==============================
model.fit(
train_X,
train_y,
epochs=epochs,
# callbacks=[checkpoint],
batch_size=batch_size,
validation_split=0.1)
# ===========================Test==============================
print('test AUC: %f' % model.evaluate(test_X, test_y)[1])