def get_estimator(epochs=20,
batch_size=4,
max_train_steps_per_epoch=None,
max_eval_steps_per_epoch=None,
save_dir=tempfile.mkdtemp(),
log_steps=20,
data_dir=None):
# step 1
csv = montgomery.load_data(root_dir=data_dir)
pipeline = fe.Pipeline(
train_data=csv,
eval_data=csv.split(0.2),
batch_size=batch_size,
ops=[
ReadImage(inputs="image",
parent_path=csv.parent_path,
outputs="image",
color_flag='gray'),
ReadImage(inputs="mask_left",
parent_path=csv.parent_path,
outputs="mask_left",
color_flag='gray',
mode='!infer'),
ReadImage(inputs="mask_right",
parent_path=csv.parent_path,
outputs="mask_right",
color_flag='gray',
mode='!infer'),
CombineLeftRightMask(inputs=("mask_left", "mask_right"),
outputs="mask",
mode='!infer'),
Delete(keys=["mask_left", "mask_right"], mode='!infer'),
Resize(image_in="image", width=512, height=512),
Resize(image_in="mask", width=512, height=512, mode='!infer'),
Sometimes(numpy_op=HorizontalFlip(
image_in="image", mask_in="mask", mode='train')),
Sometimes(numpy_op=Rotate(image_in="image",
mask_in="mask",
limit=(-10, 10),
border_mode=cv2.BORDER_CONSTANT,
mode='train')),
Minmax(inputs="image", outputs="image"),
Minmax(inputs="mask", outputs="mask", mode='!infer'),
Reshape(shape=(1, 512, 512), inputs="image", outputs="image"),
Reshape(shape=(1, 512, 512),
inputs="mask",
outputs="mask",
mode='!infer')
])
# step 2
model = fe.build(
model_fn=lambda: UNet(input_size=(1, 512, 512)),
optimizer_fn=lambda x: torch.optim.Adam(params=x, lr=0.0001),
model_name="lung_segmentation")
network = fe.Network(ops=[
ModelOp(inputs="image", model=model, outputs="pred_segment"),
CrossEntropy(
inputs=("pred_segment", "mask"), outputs="loss", form="binary"),
UpdateOp(model=model, loss_name="loss")
])
# step 3
traces = [
Dice(true_key="mask", pred_key="pred_segment"),
BestModelSaver(model=model,
save_dir=save_dir,
metric='Dice',
save_best_mode='max')
]
estimator = fe.Estimator(
network=network,
pipeline=pipeline,
epochs=epochs,
log_steps=log_steps,
traces=traces,
max_train_steps_per_epoch=max_train_steps_per_epoch,
max_eval_steps_per_epoch=max_eval_steps_per_epoch)
return estimator
def get_estimator(max_len=20,
epochs=10,
batch_size=64,
train_steps_per_epoch=None,
eval_steps_per_epoch=None,
save_dir=tempfile.mkdtemp(),
pretrained_model='bert-base-uncased',
data_dir=None):
# step 1 prepare data
train_data, eval_data, data_vocab, label_vocab = mitmovie_ner.load_data(
root_dir=data_dir)
tokenizer = BertTokenizer.from_pretrained(pretrained_model,
do_lower_case=True)
tag2idx = char2idx(label_vocab)
pipeline = fe.Pipeline(train_data=train_data,
eval_data=eval_data,
batch_size=batch_size,
ops=[
Tokenize(inputs="x",
outputs="x",
tokenize_fn=tokenizer.tokenize),
WordtoId(
inputs="x",
outputs="x",
mapping=tokenizer.convert_tokens_to_ids),
WordtoId(inputs="y",
outputs="y",
mapping=tag2idx),
PadSequence(max_len=max_len,
inputs="x",
outputs="x"),
PadSequence(max_len=max_len,
value=len(tag2idx),
inputs="y",
outputs="y"),
AttentionMask(inputs="x", outputs="x_masks")
])
# step 2. prepare model
model = fe.build(
model_fn=lambda: ner_model(max_len, pretrained_model, label_vocab),
optimizer_fn=lambda: tf.optimizers.Adam(1e-5))
network = fe.Network(ops=[
ModelOp(model=model, inputs=["x", "x_masks"], outputs="y_pred"),
Reshape(inputs="y", outputs="y", shape=(-1, )),
Reshape(inputs="y_pred",
outputs="y_pred",
shape=(-1, len(label_vocab) + 1)),
CrossEntropy(inputs=("y_pred", "y"), outputs="loss"),
UpdateOp(model=model, loss_name="loss")
])
traces = [
Accuracy(true_key="y", pred_key="y_pred"),
BestModelSaver(model=model, save_dir=save_dir)
]
# step 3 prepare estimator
estimator = fe.Estimator(network=network,
pipeline=pipeline,
epochs=epochs,
traces=traces,
train_steps_per_epoch=train_steps_per_epoch,
eval_steps_per_epoch=eval_steps_per_epoch)
return estimator
def get_estimator(epochs=20, batch_size=128, max_train_steps_per_epoch=None, save_dir=tempfile.mkdtemp()):
# Dataset Creation
(x_train, y_train), (x_eval, y_eval) = tf.keras.datasets.mnist.load_data()
x_eval0, y_eval0 = x_eval[np.where((y_eval == 1))], np.ones(y_eval[np.where((y_eval == 1))].shape)
x_eval1, y_eval1 = x_eval[np.where((y_eval != 1))], y_eval[np.where((y_eval != 1))]
# Ensuring outliers comprise 50% of the dataset
index = np.random.choice(x_eval1.shape[0], int(x_eval0.shape[0]), replace=False)
x_eval1, y_eval1 = x_eval1[index], np.zeros(y_eval1[index].shape)
x_train, y_train = x_train[np.where((y_train == 1))], np.zeros(y_train[np.where((y_train == 1))].shape)
train_data = fe.dataset.NumpyDataset({"x": x_train, "y": y_train})
x_eval, y_eval = np.concatenate([x_eval0, x_eval1]), np.concatenate([y_eval0, y_eval1])
eval_data = fe.dataset.NumpyDataset({"x": x_eval, "y": y_eval})
pipeline = fe.Pipeline(
train_data=train_data,
eval_data=eval_data,
batch_size=batch_size,
ops=[
ExpandDims(inputs="x", outputs="x"),
Normalize(inputs="x", outputs="x", mean=1.0, std=1.0, max_pixel_value=127.5),
LambdaOp(fn=lambda x: x + np.random.normal(loc=0.0, scale=0.155, size=(28, 28, 1)).astype(np.float32),
inputs="x",
outputs="x_w_noise",
mode="train"),
ChannelTranspose(inputs="x", outputs="x"),
ChannelTranspose(inputs="x_w_noise", outputs="x_w_noise", mode="train")
])
recon_model = fe.build(model_fn=reconstructor,
optimizer_fn=lambda x: torch.optim.RMSprop(x, lr=2e-4),
model_name="reconstructor")
disc_model = fe.build(model_fn=discriminator,
optimizer_fn=lambda x: torch.optim.RMSprop(x, lr=1e-4),
model_name="discriminator")
network = fe.Network(ops=[
ModelOp(model=recon_model, inputs="x_w_noise", outputs="x_fake", mode="train"),
ModelOp(model=recon_model, inputs="x", outputs="x_fake", mode="eval"),
ModelOp(model=disc_model, inputs="x_fake", outputs="fake_score"),
ModelOp(model=disc_model, inputs="x", outputs="true_score"),
RLoss(inputs=("fake_score", "x_fake", "x"), outputs="rloss"),
UpdateOp(model=recon_model, loss_name="rloss"),
DLoss(inputs=("true_score", "fake_score"), outputs="dloss"),
UpdateOp(model=disc_model, loss_name="dloss"),
])
traces = [
F1AUCScores(true_key="y", pred_key="fake_score", mode="eval", output_name=["auc_score", "f1_score"]),
BestModelSaver(model=recon_model, save_dir=save_dir, metric='f1_score', save_best_mode='max'),
BestModelSaver(model=disc_model, save_dir=save_dir, metric='f1_score', save_best_mode='max'),
]
estimator = fe.Estimator(pipeline=pipeline,
network=network,
epochs=epochs,
traces=traces,
max_train_steps_per_epoch=max_train_steps_per_epoch,
log_steps=50)
return estimator
def get_estimator(batch_size=8,
epochs=25,
max_train_steps_per_epoch=None,
max_eval_steps_per_epoch=None,
save_dir=tempfile.mkdtemp(),
data_dir=None):
# load CUB200 dataset.
train_data = cub200.load_data(root_dir=data_dir)
eval_data = train_data.split(0.3)
test_data = eval_data.split(0.5)
# step 1, pipeline
pipeline = fe.Pipeline(batch_size=batch_size,
train_data=train_data,
eval_data=eval_data,
test_data=test_data,
ops=[
ReadImage(inputs="image",
outputs="image",
parent_path=train_data.parent_path),
Normalize(inputs="image",
outputs="image",
mean=1.0,
std=1.0,
max_pixel_value=127.5),
ReadMat(file='annotation',
keys="seg",
parent_path=train_data.parent_path),
Delete(keys="annotation"),
LongestMaxSize(max_size=512,
image_in="image",
image_out="image",
mask_in="seg",
mask_out="seg"),
PadIfNeeded(min_height=512,
min_width=512,
image_in="image",
image_out="image",
mask_in="seg",
mask_out="seg",
border_mode=cv2.BORDER_CONSTANT,
value=0,
mask_value=0),
ShiftScaleRotate(
image_in="image",
mask_in="seg",
image_out="image",
mask_out="seg",
mode="train",
shift_limit=0.2,
rotate_limit=15.0,
scale_limit=0.2,
border_mode=cv2.BORDER_CONSTANT,
value=0,
mask_value=0),
Sometimes(
HorizontalFlip(image_in="image",
mask_in="seg",
image_out="image",
mask_out="seg",
mode="train")),
ChannelTranspose(inputs="image",
outputs="image"),
Reshape(shape=(1, 512, 512),
inputs="seg",
outputs="seg")
])
# step 2, network
resunet50 = fe.build(model_fn=ResUnet50,
model_name="resunet50",
optimizer_fn=lambda x: torch.optim.Adam(x, lr=1e-4))
uncertainty = fe.build(model_fn=UncertaintyLossNet,
model_name="uncertainty",
optimizer_fn=lambda x: torch.optim.Adam(x, lr=1e-5))
network = fe.Network(ops=[
ModelOp(inputs='image',
model=resunet50,
outputs=["label_pred", "mask_pred"]),
CrossEntropy(inputs=["label_pred", "label"],
outputs="cls_loss",
form="sparse",
average_loss=False),
CrossEntropy(inputs=["mask_pred", "seg"],
outputs="seg_loss",
form="binary",
average_loss=False),
ModelOp(inputs=["cls_loss", "seg_loss"],
model=uncertainty,
outputs="total_loss"),
ReduceLoss(inputs="total_loss", outputs="total_loss"),
UpdateOp(model=resunet50, loss_name="total_loss"),
UpdateOp(model=uncertainty, loss_name="total_loss")
])
# step 3, estimator
traces = [
Accuracy(true_key="label", pred_key="label_pred"),
Dice(true_key="seg", pred_key='mask_pred'),
BestModelSaver(model=resunet50,
save_dir=save_dir,
metric="total_loss",
save_best_mode="min"),
LRScheduler(model=resunet50,
lr_fn=lambda step: cosine_decay(
step, cycle_length=13200, init_lr=1e-4))
]
estimator = fe.Estimator(
network=network,
pipeline=pipeline,
traces=traces,
epochs=epochs,
max_train_steps_per_epoch=max_train_steps_per_epoch,
max_eval_steps_per_epoch=max_eval_steps_per_epoch,
log_steps=500)
return estimator
def get_estimator(target_size=128,
epochs=55,
save_dir=tempfile.mkdtemp(),
max_train_steps_per_epoch=None,
data_dir=None):
# assert growth parameters
num_grow = np.log2(target_size) - 2
assert num_grow >= 1 and num_grow % 1 == 0, "need exponential of 2 and greater than 8 as target size"
num_phases = int(2 * num_grow + 1)
assert epochs % num_phases == 0, "epoch must be multiple of {} for size {}".format(
num_phases, target_size)
num_grow, phase_length = int(num_grow), int(epochs / num_phases)
event_epoch = [1, 1 + phase_length] + [
phase_length * (2 * i + 1) + 1 for i in range(1, num_grow)
]
event_size = [4] + [2**(i + 3) for i in range(num_grow)]
# set up data schedules
dataset = nih_chestxray.load_data(root_dir=data_dir)
resize_map = {
epoch: Resize(image_in="x", image_out="x", height=size, width=size)
for (epoch, size) in zip(event_epoch, event_size)
}
resize_low_res_map1 = {
epoch: Resize(image_in="x",
image_out="x_low_res",
height=size // 2,
width=size // 2)
for (epoch, size) in zip(event_epoch, event_size)
}
resize_low_res_map2 = {
epoch: Resize(image_in="x_low_res",
image_out="x_low_res",
height=size,
width=size)
for (epoch, size) in zip(event_epoch, event_size)
}
batch_size_map = {
epoch: 512 // size * get_num_devices() if size <= 128 else 4 *
get_num_devices()
for (epoch, size) in zip(event_epoch, event_size)
}
batch_scheduler = EpochScheduler(epoch_dict=batch_size_map)
pipeline = fe.Pipeline(
batch_size=batch_scheduler,
train_data=dataset,
drop_last=True,
ops=[
ReadImage(inputs="x", outputs="x", color_flag='gray'),
EpochScheduler(epoch_dict=resize_map),
EpochScheduler(epoch_dict=resize_low_res_map1),
EpochScheduler(epoch_dict=resize_low_res_map2),
Normalize(inputs=["x", "x_low_res"],
outputs=["x", "x_low_res"],
mean=1.0,
std=1.0,
max_pixel_value=127.5),
LambdaOp(fn=lambda: np.random.normal(size=[512]).astype('float32'),
outputs="z")
])
# now model schedule
fade_in_alpha = tf.Variable(initial_value=1.0,
dtype='float32',
trainable=False)
d_models = fe.build(
model_fn=lambda: build_D(fade_in_alpha,
target_resolution=int(np.log2(target_size)),
num_channels=1),
optimizer_fn=[
lambda: Adam(0.001, beta_1=0.0, beta_2=0.99, epsilon=1e-8)
] * len(event_size),
model_name=["d_{}".format(size) for size in event_size])
g_models = fe.build(
model_fn=lambda: build_G(fade_in_alpha,
target_resolution=int(np.log2(target_size)),
num_channels=1),
optimizer_fn=[
lambda: Adam(0.001, beta_1=0.0, beta_2=0.99, epsilon=1e-8)
] * len(event_size) + [None],
model_name=["g_{}".format(size) for size in event_size] + ["G"])
fake_img_map = {
epoch: ModelOp(inputs="z", outputs="x_fake", model=model)
for (epoch, model) in zip(event_epoch, g_models[:-1])
}
fake_score_map = {
epoch: ModelOp(inputs="x_fake", outputs="fake_score", model=model)
for (epoch, model) in zip(event_epoch, d_models)
}
real_score_map = {
epoch: ModelOp(inputs="x_blend", outputs="real_score", model=model)
for (epoch, model) in zip(event_epoch, d_models)
}
interp_score_map = {
epoch: ModelOp(inputs="x_interp", outputs="interp_score", model=model)
for (epoch, model) in zip(event_epoch, d_models)
}
g_update_map = {
epoch: UpdateOp(loss_name="gloss", model=model)
for (epoch, model) in zip(event_epoch, g_models[:-1])
}
d_update_map = {
epoch: UpdateOp(loss_name="dloss", model=model)
for (epoch, model) in zip(event_epoch, d_models)
}
network = fe.Network(ops=[
EpochScheduler(fake_img_map),
EpochScheduler(fake_score_map),
ImageBlender(
alpha=fade_in_alpha, inputs=("x", "x_low_res"), outputs="x_blend"),
EpochScheduler(real_score_map),
Interpolate(inputs=("x_fake", "x"), outputs="x_interp"),
EpochScheduler(interp_score_map),
GradientPenalty(inputs=("x_interp", "interp_score"), outputs="gp"),
GLoss(inputs="fake_score", outputs="gloss"),
DLoss(inputs=("real_score", "fake_score", "gp"), outputs="dloss"),
EpochScheduler(g_update_map),
EpochScheduler(d_update_map)
])
traces = [
AlphaController(alpha=fade_in_alpha,
fade_start_epochs=event_epoch[1:],
duration=phase_length,
batch_scheduler=batch_scheduler,
num_examples=len(dataset)),
ModelSaver(model=g_models[-1],
save_dir=save_dir,
frequency=phase_length),
ImageSaving(epoch_model_map={
epoch - 1: model
for (epoch,
model) in zip(event_epoch[1:] + [epochs + 1], g_models[:-1])
},
save_dir=save_dir)
]
estimator = fe.Estimator(
pipeline=pipeline,
network=network,
epochs=epochs,
traces=traces,
max_train_steps_per_epoch=max_train_steps_per_epoch)
return estimator
def get_estimator(batch_size=4,
epochs=2,
max_train_steps_per_epoch=None,
log_steps=100,
style_weight=5.0,
content_weight=1.0,
tv_weight=1e-4,
save_dir=tempfile.mkdtemp(),
style_img_path='Vassily_Kandinsky,_1913_-_Composition_7.jpg',
data_dir=None):
train_data, _ = mscoco.load_data(root_dir=data_dir,
load_bboxes=False,
load_masks=False,
load_captions=False)
style_img = cv2.imread(style_img_path)
assert style_img is not None, "cannot load the style image, please go to the folder with style image"
style_img = cv2.resize(style_img, (256, 256))
style_img = (style_img.astype(np.float32) - 127.5) / 127.5
pipeline = fe.Pipeline(train_data=train_data,
batch_size=batch_size,
ops=[
ReadImage(inputs="image", outputs="image"),
Normalize(inputs="image",
outputs="image",
mean=1.0,
std=1.0,
max_pixel_value=127.5),
Resize(height=256,
width=256,
image_in="image",
image_out="image"),
LambdaOp(fn=lambda: style_img,
outputs="style_image"),
])
model = fe.build(model_fn=StyleTransferNet,
model_name="style_transfer_net",
optimizer_fn=lambda: tf.optimizers.Adam(1e-3))
network = fe.Network(ops=[
ModelOp(inputs="image", model=model, outputs="image_out"),
ExtractVGGFeatures(inputs="style_image", outputs="y_style"),
ExtractVGGFeatures(inputs="image", outputs="y_content"),
ExtractVGGFeatures(inputs="image_out", outputs="y_pred"),
StyleContentLoss(style_weight=style_weight,
content_weight=content_weight,
tv_weight=tv_weight,
inputs=('y_pred', 'y_style', 'y_content',
'image_out'),
outputs='loss'),
UpdateOp(model=model, loss_name="loss")
])
estimator = fe.Estimator(
network=network,
pipeline=pipeline,
traces=ModelSaver(model=model, save_dir=save_dir, frequency=1),
epochs=epochs,
max_train_steps_per_epoch=max_train_steps_per_epoch,
log_steps=log_steps)
return estimator
def get_estimator(epochs=200,
batch_size=128,
train_steps_per_epoch=None,
eval_steps_per_epoch=None,
save_dir=tempfile.mkdtemp(),
data_dir=None):
# step 1. prepare pipeline
train_data, eval_data = omniglot.load_data(root_dir=data_dir)
test_data = eval_data.split(0.5)
pipeline = fe.Pipeline(
train_data=train_data,
eval_data=eval_data,
test_data=test_data,
batch_size=batch_size,
ops=[
ReadImage(inputs="x_a", outputs="x_a", color_flag='gray'),
ReadImage(inputs="x_b", outputs="x_b", color_flag='gray'),
Sometimes(
ShiftScaleRotate(image_in="x_a",
image_out="x_a",
shift_limit=0.05,
scale_limit=0.2,
rotate_limit=10,
mode="train"),
prob=0.89),
Sometimes(
ShiftScaleRotate(image_in="x_b",
image_out="x_b",
shift_limit=0.05,
scale_limit=0.2,
rotate_limit=10,
mode="train"),
prob=0.89),
Minmax(inputs="x_a", outputs="x_a"),
Minmax(inputs="x_b", outputs="x_b")
])
# step 2. prepare model
model = fe.build(model_fn=siamese_network, model_name="siamese_net", optimizer_fn="adam")
network = fe.Network(ops=[
ModelOp(inputs=["x_a", "x_b"], model=model, outputs="y_pred"),
CrossEntropy(inputs=("y_pred", "y"), outputs="loss", form="binary"),
UpdateOp(model=model, loss_name="loss")
])
# step 3.prepare estimator
traces = [
LRScheduler(model=model, lr_fn=lr_schedule),
Accuracy(true_key="y", pred_key="y_pred"),
OneShotAccuracy(dataset=eval_data, model=model, output_name='one_shot_accuracy'),
BestModelSaver(model=model, save_dir=save_dir, metric="one_shot_accuracy", save_best_mode="max"),
EarlyStopping(monitor="one_shot_accuracy", patience=20, compare='max', mode="eval")
]
estimator = fe.Estimator(network=network,
pipeline=pipeline,
epochs=epochs,
traces=traces,
train_steps_per_epoch=train_steps_per_epoch,
eval_steps_per_epoch=eval_steps_per_epoch)
return estimator
def get_estimator(epsilon=0.04,
epochs=20,
batch_size=32,
code_length=16,
train_steps_per_epoch=None,
eval_steps_per_epoch=None,
save_dir=tempfile.mkdtemp()):
# step 1
train_data, eval_data = cifair10.load_data()
test_data = eval_data.split(0.5)
pipeline = fe.Pipeline(train_data=train_data,
eval_data=eval_data,
test_data=test_data,
batch_size=batch_size,
ops=[
Normalize(inputs="x",
outputs="x",
mean=(0.4914, 0.4822, 0.4465),
std=(0.2471, 0.2435, 0.2616)),
Hadamard(inputs="y",
outputs="y_code",
n_classes=10)
])
# step 2
model = fe.build(model_fn=lambda: ecc_lenet(code_length=code_length),
optimizer_fn='adam')
network = fe.Network(ops=[
Watch(inputs="x", mode=('eval', 'test')),
ModelOp(model=model, inputs="x", outputs="y_pred_code"),
Hinge(inputs=("y_pred_code", "y_code"), outputs="base_hinge"),
UpdateOp(model=model, loss_name="base_hinge"),
UnHadamard(inputs="y_pred_code",
outputs="y_pred",
n_classes=10,
mode=('eval', 'test')),
# The adversarial attack:
FGSM(data="x",
loss="base_hinge",
outputs="x_adverse_hinge",
epsilon=epsilon,
mode=('eval', 'test')),
ModelOp(model=model,
inputs="x_adverse_hinge",
outputs="y_pred_adv_hinge_code",
mode=('eval', 'test')),
Hinge(inputs=("y_pred_adv_hinge_code", "y_code"),
outputs="adv_hinge",
mode=('eval', 'test')),
UnHadamard(inputs="y_pred_adv_hinge_code",
outputs="y_pred_adv_hinge",
n_classes=10,
mode=('eval', 'test')),
])
# step 3
traces = [
Accuracy(true_key="y", pred_key="y_pred", output_name="base_accuracy"),
Accuracy(true_key="y",
pred_key="y_pred_adv_hinge",
output_name="adversarial_accuracy"),
BestModelSaver(model=model,
save_dir=save_dir,
metric="base_hinge",
save_best_mode="min",
load_best_final=True)
]
estimator = fe.Estimator(pipeline=pipeline,
network=network,
epochs=epochs,
traces=traces,
train_steps_per_epoch=train_steps_per_epoch,
eval_steps_per_epoch=eval_steps_per_epoch,
monitor_names=["adv_hinge"])
return estimator
def get_estimator(epochs=24,
batch_size=128,
lr_epochs=100,
max_train_steps_per_epoch=None,
save_dir=tempfile.mkdtemp()):
# step 1: prepare dataset
train_data, test_data = load_data()
pipeline = fe.Pipeline(train_data=train_data,
eval_data=test_data,
batch_size=batch_size,
ops=[
Normalize(inputs="x",
outputs="x",
mean=(0.4914, 0.4822, 0.4465),
std=(0.2471, 0.2435, 0.2616)),
PadIfNeeded(min_height=40,
min_width=40,
image_in="x",
image_out="x",
mode="train"),
RandomCrop(32,
32,
image_in="x",
image_out="x",
mode="train"),
Sometimes(
HorizontalFlip(image_in="x",
image_out="x",
mode="train")),
CoarseDropout(inputs="x",
outputs="x",
mode="train",
max_holes=1),
Onehot(inputs="y",
outputs="y",
mode="train",
num_classes=10,
label_smoothing=0.2)
])
# step 2: prepare network
model = fe.build(model_fn=ResNet9, optimizer_fn="sgd")
network = fe.Network(ops=[
ModelOp(model=model, inputs="x", outputs="y_pred"),
CrossEntropy(inputs=("y_pred", "y"), outputs="ce"),
UpdateOp(model=model, loss_name="ce")
])
# get the max learning rate
lr_max = search_max_lr(pipeline=pipeline,
model=model,
network=network,
epochs=lr_epochs)
lr_min = lr_max / 40
print(f"The maximum LR: {lr_max}, and minimun LR: {lr_min}")
mid_step = int(epochs * 0.45 * len(train_data) / batch_size)
end_step = int(epochs * len(train_data) / batch_size)
# reinitialize the model
model = fe.build(model_fn=ResNet9, optimizer_fn="sgd")
network = fe.Network(ops=[
ModelOp(model=model, inputs="x", outputs="y_pred"),
CrossEntropy(inputs=("y_pred", "y"), outputs="ce"),
UpdateOp(model=model, loss_name="ce")
])
# step 3: prepare estimator
traces = [
Accuracy(true_key="y", pred_key="y_pred"),
BestModelSaver(model=model,
save_dir=save_dir,
metric="accuracy",
save_best_mode="max"),
LRScheduler(model=model,
lr_fn=lambda step: super_schedule(step, lr_max, lr_min,
mid_step, end_step))
]
estimator = fe.Estimator(
pipeline=pipeline,
network=network,
epochs=epochs,
traces=traces,
max_train_steps_per_epoch=max_train_steps_per_epoch)
return estimator