def test_accumulate(self, ):
dim = 20
data = np.random.random(size=(4, dim)).astype(np.float32)
label = np.random.randint(0, 10, size=(4, 1)).astype(np.int64)
net = MyModel()
optim = fluid.optimizer.SGD(learning_rate=0.001,
parameter_list=net.parameters())
inputs = [InputSpec([None, dim], 'float32', 'x')]
labels = [InputSpec([None, 1], 'int64', 'label')]
for amp_cfg in [None, 'O1']:
model = Model(net, inputs, labels)
model.prepare(
optim,
loss=CrossEntropyLoss(reduction="sum"),
amp_configs=amp_cfg)
losses, grads = [], []
for stat in [False, False, True]:
loss, = model.train_batch([data], [label], update=stat)
losses.append(loss)
grads.append([p.grad.numpy() for p in net.parameters()])
for grad1, grad2, grad3 in zip(*grads):
np.testing.assert_almost_equal(grad1 * 2, grad2, decimal=4)
np.testing.assert_almost_equal(
grad3, np.zeros_like(grad3), decimal=4)
np.testing.assert_almost_equal(losses[0], losses[1], decimal=4)
np.testing.assert_almost_equal(losses[0], losses[2], decimal=4)
def test_dygraph_export_deploy_model_about_inputs(self):
self.set_seed()
np.random.seed(201)
mnist_data = MnistDataset(mode='train')
paddle.disable_static()
# without inputs
save_dir = os.path.join(tempfile.mkdtemp(),
'.cache_test_dygraph_export_deploy')
if not os.path.exists(save_dir):
os.makedirs(save_dir)
for initial in ["fit", "train_batch", "eval_batch", "predict_batch"]:
net = LeNet()
model = Model(net)
optim = fluid.optimizer.Adam(
learning_rate=0.001, parameter_list=model.parameters())
model.prepare(
optimizer=optim, loss=CrossEntropyLoss(reduction="sum"))
if initial == "fit":
model.fit(mnist_data, batch_size=64, verbose=0)
else:
img = np.array(
np.random.random((1, 1, 28, 28)), dtype=np.float32)
label = np.array(np.random.rand(1, 1), dtype=np.int64)
if initial == "train_batch":
model.train_batch([img], [label])
elif initial == "eval_batch":
model.eval_batch([img], [label])
else:
model.predict_batch([img])
model.save(save_dir, training=False)
shutil.rmtree(save_dir)
# with inputs, and the type of inputs is InputSpec
save_dir = os.path.join(tempfile.mkdtemp(),
'.cache_test_dygraph_export_deploy_2')
if not os.path.exists(save_dir):
os.makedirs(save_dir)
net = LeNet()
inputs = InputSpec([None, 1, 28, 28], 'float32', 'x')
model = Model(net, inputs)
optim = fluid.optimizer.Adam(
learning_rate=0.001, parameter_list=model.parameters())
model.prepare(optimizer=optim, loss=CrossEntropyLoss(reduction="sum"))
model.save(save_dir, training=False)
shutil.rmtree(save_dir)
def test_amp_training_purefp16(self):
if not fluid.is_compiled_with_cuda():
self.skipTest('module not tested when ONLY_CPU compling')
data = np.random.random(size=(4, 1, 28, 28)).astype(np.float32)
label = np.random.randint(0, 10, size=(4, 1)).astype(np.int64)
paddle.enable_static()
paddle.set_device('gpu')
net = LeNet()
amp_level = "O2"
inputs = InputSpec([None, 1, 28, 28], "float32", 'x')
labels = InputSpec([None, 1], "int64", "y")
model = Model(net, inputs, labels)
optim = paddle.optimizer.Adam(learning_rate=0.001,
parameters=model.parameters(),
multi_precision=True)
amp_configs = {"level": amp_level, "use_fp16_guard": False}
model.prepare(optimizer=optim,
loss=CrossEntropyLoss(reduction="sum"),
amp_configs=amp_configs)
model.train_batch([data], [label])
def test_train_batch(self, dynamic=True):
dim = 20
data = np.random.random(size=(4, dim)).astype(np.float32)
label = np.random.randint(0, 10, size=(4, 1)).astype(np.int64)
def get_expect():
fluid.enable_dygraph(fluid.CPUPlace())
self.set_seed()
m = MyModel()
optim = fluid.optimizer.SGD(learning_rate=0.001,
parameter_list=m.parameters())
m.train()
output = m(to_tensor(data))
loss = CrossEntropyLoss(reduction='sum')(output, to_tensor(label))
avg_loss = fluid.layers.reduce_sum(loss)
avg_loss.backward()
optim.minimize(avg_loss)
m.clear_gradients()
fluid.disable_dygraph()
return avg_loss.numpy()
ref = get_expect()
for dynamic in [True, False]:
device = paddle.set_device('cpu')
fluid.enable_dygraph(device) if dynamic else None
self.set_seed()
net = MyModel()
optim2 = fluid.optimizer.SGD(learning_rate=0.001,
parameter_list=net.parameters())
inputs = [InputSpec([None, dim], 'float32', 'x')]
labels = [InputSpec([None, 1], 'int64', 'label')]
model = Model(net, inputs, labels)
model.prepare(optim2, loss=CrossEntropyLoss(reduction="sum"))
loss, = model.train_batch([data], [label])
np.testing.assert_allclose(loss.flatten(), ref.flatten())
fluid.disable_dygraph() if dynamic else None
