total_time = 0
# get the whole model
vgg = vgg16()
start_time = time.time()
vgg = vgg.to(device)
total_time += time.time() - start_time
# training setting
num_iter = NUM_ITERS
batch_size = BATCH_SIZE
optimizer = optim.Adam(vgg.parameters(), lr=LERANING_RATE)
# data generator
gen = random_input_generator(num_iter, batch_size, format='NCHW')
# begin training
for idx, data in enumerate(gen):
x_batch = torch.Tensor(data[0])
y_batch = torch.Tensor(data[1]).long()
start_time = time.time()
x_batch = x_batch.to(device)
y_batch = y_batch.to(device)
# forward + backward
outputs = vgg(x_batch)
loss = F.cross_entropy(outputs, y_batch)
info = psutil.virtual_memory()
monitor_interval = MONITOR_INTERVAL
avg_mem_usage = 0
max_mem_usage = 0
count = 0
total_time = 0
# training setting
num_iter = NUM_ITERS
batch_size = BATCH_SIZE
train_weights = vgg.weights
optimizer = tf.optimizers.Adam(learning_rate=LERANING_RATE)
loss_object = tl.cost.cross_entropy
# data generator
gen = random_input_generator(num_iter, batch_size)
# training function
def train_step(x_batch, y_batch):
# forward + backward
with tf.GradientTape() as tape:
## compute outputs
_logits = vgg(x_batch)
## compute loss and update model
_loss = loss_object(_logits, y_batch)
grad = tape.gradient(_loss, train_weights)
optimizer.apply_gradients(zip(grad, train_weights))
total_time = 0
# get the whole model
vgg = vgg16()
start_time = time.time()
vgg = vgg.to(device)
total_time += time.time() - start_time
# training setting
num_iter = NUM_ITERS
batch_size = BATCH_SIZE
optimizer = optim.Adam(vgg.parameters(), lr=LERANING_RATE)
# data generator
gen = random_input_generator(num_iter, batch_size, format='NCHW')
# begin training
for idx, data in enumerate(gen):
start_time = time.time()
x_batch = torch.Tensor(data[0])
y_batch = torch.Tensor(data[1]).long()
x_batch = x_batch.to(device)
y_batch = y_batch.to(device)
# forward + backward
outputs = vgg(x_batch)
loss = F.cross_entropy(outputs, y_batch)
