def call(self, inputs):
x = inputs
x = self.conv1(x)
x = self.maxpool1(x)
x = self.conv2(x)
x = self.maxpool2(x)
x = self.flatten(x)
x = self.dense1(x)
x = self.dense2(x)
x = self.gaussianconnection(x)
# x = tf.reshape(x, [batchsz,-1]) # reshape成平面层
# x = self.dense5(x) # 输出层
return x
myLeNet = LeNet()
myLeNet.compile(optimizer=optimizers.Adam(lr=1e-3), loss=tf.losses.CategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
# tensorboard 可视化过程
tb = TensorBoard(
log_dir='logs',
histogram_freq=0,
write_graph=True,
write_images=False,
update_freq='batch',
profile_batch=2,
embeddings_freq=0,
embeddings_metadata=None
)
tb.on_epoch_begin(0)
myLeNet.fit(db, epochs=10, validation_data = db_test, validation_freq = 1, callbacks=[tb])
myLeNet.evaluate(db_test)
embeddings_freq=1)
loss_history = []
cos_loss_history = []
T = 0.0
t0 = time.time()
tbcb.set_model(model)
tbcb.on_train_begin()
f = open('log.txt', 'w')
try:
for epoch in range(200):
tbcb.on_epoch_begin(epoch)
cos_loss = CosineSimilarity()
for step in (range(num_batch)):
tbcb.on_train_batch_begin(step)
print('========== step: {:03d} / {:03d} ============\r'.format(
step, num_batch),
end='')
u, seq, pos, neg = sampler.next_batch()
seq = tf.convert_to_tensor(seq)
pos = tf.convert_to_tensor(pos)
neg = tf.convert_to_tensor(neg)
with tf.GradientTape() as tape:
tensorboard = TensorBoard(log_dir="logs/")
tensorboard.set_model(model)
tensorboard.on_train_begin()
epochs = 3
train_logs_dict = {}
test_logs_dict = {}
for epoch in range(epochs):
training_acc, testing_acc, training_loss, testing_loss = [], [], [], []
print("\nStart of epoch %d" % (epoch + 1, ))
# Iterate over the batches of the dataset.
modelcheckpoint.on_epoch_begin(epoch)
earlystop.on_epoch_begin(epoch)
reduce_lr.on_epoch_begin(epoch)
tensorboard.on_epoch_begin(epoch)
for x_batch_train, y_batch_train in get_batch(batch_size, x_train,
y_train):
train_loss, train_accuracy = model.train_on_batch(
x_batch_train, y_batch_train)
training_acc.append(train_accuracy)
training_loss.append(train_loss)
for x_batch_test, y_batch_test in get_batch(batch_size, x_test, y_test):
test_loss, test_accuracy = model.test_on_batch(x_batch_test,
y_batch_test)
testing_acc.append(test_accuracy)
testing_loss.append(test_loss)
train_logs_dict = get_logs(train_logs_dict, epoch, model, x_train, y_train)
