def test_deeplabv3_builder(self, backbone_type, input_size, weight_decay):
num_classes = 21
input_specs = tf.keras.layers.InputSpec(
shape=[None, input_size[0], input_size[1], 3])
model_config = semantic_segmentation_cfg.SemanticSegmentationModel(
num_classes=num_classes,
backbone=backbones.Backbone(type=backbone_type,
mobilenet=backbones.MobileNet(
model_id='MobileNetV2',
output_stride=16)),
decoder=decoders.Decoder(type='aspp',
aspp=decoders.ASPP(level=4,
num_filters=256,
dilation_rates=[],
spp_layer_version='v1',
output_tensor=True)),
head=semantic_segmentation_cfg.SegmentationHead(
level=4,
low_level=2,
num_convs=1,
upsample_factor=2,
use_depthwise_convolution=True))
l2_regularizer = (tf.keras.regularizers.l2(weight_decay)
if weight_decay else None)
model = factory.build_segmentation_model(input_specs=input_specs,
model_config=model_config,
l2_regularizer=l2_regularizer)
quantization_config = common.Quantization()
_ = qat_factory.build_qat_segmentation_model(
model=model,
quantization=quantization_config,
input_specs=input_specs)
def test_mobilenet_creation(self, model_id, filter_size_scale):
"""Test creation of Mobilenet models."""
network = backbones.MobileNet(model_id=model_id,
filter_size_scale=filter_size_scale,
norm_momentum=0.99,
norm_epsilon=1e-5)
backbone_config = backbones_cfg.Backbone(
type='mobilenet',
mobilenet=backbones_cfg.MobileNet(
model_id=model_id, filter_size_scale=filter_size_scale))
norm_activation_config = common_cfg.NormActivation(norm_momentum=0.99,
norm_epsilon=1e-5,
use_sync_bn=False)
factory_network = factory.build_backbone(
input_specs=tf.keras.layers.InputSpec(shape=[None, None, None, 3]),
backbone_config=backbone_config,
norm_activation_config=norm_activation_config)
network_config = network.get_config()
factory_network_config = factory_network.get_config()
self.assertEqual(network_config, factory_network_config)
def test_builder(self, backbone_type, decoder_type, input_size,
quantize_detection_head, quantize_detection_decoder):
num_classes = 2
input_specs = tf.keras.layers.InputSpec(
shape=[None, input_size[0], input_size[1], 3])
if backbone_type == 'spinenet_mobile':
backbone_config = backbones.Backbone(
type=backbone_type,
spinenet_mobile=backbones.SpineNetMobile(
model_id='49',
stochastic_depth_drop_rate=0.2,
min_level=3,
max_level=7,
use_keras_upsampling_2d=True))
elif backbone_type == 'mobilenet':
backbone_config = backbones.Backbone(type=backbone_type,
mobilenet=backbones.MobileNet(
model_id='MobileNetV2',
filter_size_scale=1.0))
else:
raise ValueError(
'backbone_type {} is not supported'.format(backbone_type))
if decoder_type == 'identity':
decoder_config = decoders.Decoder(type=decoder_type)
elif decoder_type == 'fpn':
decoder_config = decoders.Decoder(type=decoder_type,
fpn=decoders.FPN(
num_filters=128,
use_separable_conv=True,
use_keras_layer=True))
else:
raise ValueError(
'decoder_type {} is not supported'.format(decoder_type))
model_config = retinanet_cfg.RetinaNet(
num_classes=num_classes,
input_size=[input_size[0], input_size[1], 3],
backbone=backbone_config,
decoder=decoder_config,
head=retinanet_cfg.RetinaNetHead(attribute_heads=None,
use_separable_conv=True))
l2_regularizer = tf.keras.regularizers.l2(5e-5)
# Build the original float32 retinanet model.
model = factory.build_retinanet(input_specs=input_specs,
model_config=model_config,
l2_regularizer=l2_regularizer)
# Call the model with dummy input to build the head part.
dummpy_input = tf.zeros([1] + model_config.input_size)
model(dummpy_input, training=True)
# Build the QAT model from the original model with quantization config.
qat_model = qat_factory.build_qat_retinanet(
model=model,
quantization=common.Quantization(
quantize_detection_decoder=quantize_detection_decoder,
quantize_detection_head=quantize_detection_head),
model_config=model_config)
if quantize_detection_head:
# head become a RetinaNetHeadQuantized when we apply quantization.
self.assertIsInstance(
qat_model.head,
qat_dense_prediction_heads.RetinaNetHeadQuantized)
else:
# head is a RetinaNetHead if we don't apply quantization on head part.
self.assertIsInstance(qat_model.head,
dense_prediction_heads.RetinaNetHead)
self.assertNotIsInstance(
qat_model.head,
qat_dense_prediction_heads.RetinaNetHeadQuantized)
if decoder_type == 'FPN':
if quantize_detection_decoder:
# FPN decoder become a general keras functional model after applying
# quantization.
self.assertNotIsInstance(qat_model.decoder, fpn.FPN)
else:
self.assertIsInstance(qat_model.decoder, fpn.FPN)
def image_classification_imagenet_mobilenet() -> cfg.ExperimentConfig:
"""Image classification on imagenet with mobilenet."""
train_batch_size = 4096
eval_batch_size = 4096
steps_per_epoch = IMAGENET_TRAIN_EXAMPLES // train_batch_size
config = cfg.ExperimentConfig(
task=ImageClassificationTask(
model=ImageClassificationModel(
num_classes=1001,
dropout_rate=0.2,
input_size=[224, 224, 3],
backbone=backbones.Backbone(type='mobilenet',
mobilenet=backbones.MobileNet(
model_id='MobileNetV2',
filter_size_scale=1.0)),
norm_activation=common.NormActivation(norm_momentum=0.997,
norm_epsilon=1e-3,
use_sync_bn=False)),
losses=Losses(l2_weight_decay=1e-5, label_smoothing=0.1),
train_data=DataConfig(input_path=os.path.join(
IMAGENET_INPUT_PATH_BASE, 'train*'),
is_training=True,
global_batch_size=train_batch_size),
validation_data=DataConfig(input_path=os.path.join(
IMAGENET_INPUT_PATH_BASE, 'valid*'),
is_training=False,
global_batch_size=eval_batch_size)),
trainer=cfg.TrainerConfig(
steps_per_loop=steps_per_epoch,
summary_interval=steps_per_epoch,
checkpoint_interval=steps_per_epoch,
train_steps=500 * steps_per_epoch,
validation_steps=IMAGENET_VAL_EXAMPLES // eval_batch_size,
validation_interval=steps_per_epoch,
optimizer_config=optimization.OptimizationConfig({
'optimizer': {
'type': 'rmsprop',
'rmsprop': {
'rho': 0.9,
'momentum': 0.9,
'epsilon': 0.002,
}
},
'learning_rate': {
'type': 'exponential',
'exponential': {
'initial_learning_rate':
0.008 * (train_batch_size // 128),
'decay_steps': int(2.5 * steps_per_epoch),
'decay_rate': 0.98,
'staircase': True
}
},
'warmup': {
'type': 'linear',
'linear': {
'warmup_steps': 5 * steps_per_epoch,
'warmup_learning_rate': 0
}
},
})),
restrictions=[
'task.train_data.is_training != None',
'task.validation_data.is_training != None'
])
return config
def mnv2_deeplabv3_cityscapes() -> cfg.ExperimentConfig:
"""Image segmentation on cityscapes with mobilenetv2 deeplabv3."""
train_batch_size = 16
eval_batch_size = 16
steps_per_epoch = CITYSCAPES_TRAIN_EXAMPLES // train_batch_size
output_stride = 16
aspp_dilation_rates = []
pool_kernel_size = [512, 1024]
level = int(np.math.log2(output_stride))
config = cfg.ExperimentConfig(
task=SemanticSegmentationTask(
model=SemanticSegmentationModel(
# Cityscapes uses only 19 semantic classes for train/evaluation.
# The void (background) class is ignored in train and evaluation.
num_classes=19,
input_size=[None, None, 3],
backbone=backbones.Backbone(type='mobilenet',
mobilenet=backbones.MobileNet(
model_id='MobileNetV2',
output_stride=output_stride)),
decoder=decoders.Decoder(
type='aspp',
aspp=decoders.ASPP(level=level,
dilation_rates=aspp_dilation_rates,
pool_kernel_size=pool_kernel_size)),
head=SegmentationHead(level=level, num_convs=0),
norm_activation=common.NormActivation(activation='relu',
norm_momentum=0.99,
norm_epsilon=1e-3,
use_sync_bn=True)),
losses=Losses(l2_weight_decay=4e-5),
train_data=DataConfig(input_path=os.path.join(
CITYSCAPES_INPUT_PATH_BASE, 'train_fine**'),
crop_size=[512, 1024],
output_size=[1024, 2048],
is_training=True,
global_batch_size=train_batch_size,
aug_scale_min=0.5,
aug_scale_max=2.0),
validation_data=DataConfig(input_path=os.path.join(
CITYSCAPES_INPUT_PATH_BASE, 'val_fine*'),
output_size=[1024, 2048],
is_training=False,
global_batch_size=eval_batch_size,
resize_eval_groundtruth=True,
drop_remainder=False),
# Coco pre-trained mobilenetv2 checkpoint
init_checkpoint=
'gs://tf_model_garden/cloud/vision-2.0/deeplab/deeplabv3_mobilenetv2_coco/best_ckpt-63',
init_checkpoint_modules='backbone'),
trainer=cfg.TrainerConfig(
steps_per_loop=steps_per_epoch,
summary_interval=steps_per_epoch,
checkpoint_interval=steps_per_epoch,
train_steps=100000,
validation_steps=CITYSCAPES_VAL_EXAMPLES // eval_batch_size,
validation_interval=steps_per_epoch,
best_checkpoint_eval_metric='mean_iou',
best_checkpoint_export_subdir='best_ckpt',
best_checkpoint_metric_comp='higher',
optimizer_config=optimization.OptimizationConfig({
'optimizer': {
'type': 'sgd',
'sgd': {
'momentum': 0.9
}
},
'learning_rate': {
'type': 'polynomial',
'polynomial': {
'initial_learning_rate': 0.01,
'decay_steps': 100000,
'end_learning_rate': 0.0,
'power': 0.9
}
},
'warmup': {
'type': 'linear',
'linear': {
'warmup_steps': 5 * steps_per_epoch,
'warmup_learning_rate': 0
}
}
})),
restrictions=[
'task.train_data.is_training != None',
'task.validation_data.is_training != None'
])
return config
def maskrcnn_mobilenet_coco() -> cfg.ExperimentConfig:
"""COCO object detection with Mask R-CNN with MobileNet backbone."""
steps_per_epoch = 232
coco_val_samples = 5000
train_batch_size = 512
eval_batch_size = 512
config = cfg.ExperimentConfig(
runtime=cfg.RuntimeConfig(mixed_precision_dtype='bfloat16'),
task=MaskRCNNTask(
annotation_file=os.path.join(COCO_INPUT_PATH_BASE,
'instances_val2017.json'),
model=MaskRCNN(
backbone=backbones.Backbone(
type='mobilenet',
mobilenet=backbones.MobileNet(model_id='MobileNetV2')),
decoder=decoders.Decoder(
type='fpn',
fpn=decoders.FPN(num_filters=128, use_separable_conv=True)),
rpn_head=RPNHead(use_separable_conv=True,
num_filters=128), # 1/2 of original channels.
detection_head=DetectionHead(
use_separable_conv=True, num_filters=128,
fc_dims=512), # 1/2 of original channels.
mask_head=MaskHead(use_separable_conv=True,
num_filters=128), # 1/2 of original channels.
anchor=Anchor(anchor_size=3),
norm_activation=common.NormActivation(
activation='relu6',
norm_momentum=0.99,
norm_epsilon=0.001,
use_sync_bn=True),
num_classes=91,
input_size=[512, 512, 3],
min_level=3,
max_level=6,
include_mask=True),
losses=Losses(l2_weight_decay=0.00004),
train_data=DataConfig(
input_path=os.path.join(COCO_INPUT_PATH_BASE, 'train*'),
is_training=True,
global_batch_size=train_batch_size,
parser=Parser(
aug_rand_hflip=True, aug_scale_min=0.5, aug_scale_max=2.0)),
validation_data=DataConfig(
input_path=os.path.join(COCO_INPUT_PATH_BASE, 'val*'),
is_training=False,
global_batch_size=eval_batch_size,
drop_remainder=False)),
trainer=cfg.TrainerConfig(
train_steps=steps_per_epoch * 350,
validation_steps=coco_val_samples // eval_batch_size,
validation_interval=steps_per_epoch,
steps_per_loop=steps_per_epoch,
summary_interval=steps_per_epoch,
checkpoint_interval=steps_per_epoch,
optimizer_config=optimization.OptimizationConfig({
'optimizer': {
'type': 'sgd',
'sgd': {
'momentum': 0.9
}
},
'learning_rate': {
'type': 'stepwise',
'stepwise': {
'boundaries': [
steps_per_epoch * 320, steps_per_epoch * 340
],
'values': [0.32, 0.032, 0.0032],
}
},
'warmup': {
'type': 'linear',
'linear': {
'warmup_steps': 2000,
'warmup_learning_rate': 0.0067
}
}
})),
restrictions=[
'task.train_data.is_training != None',
'task.validation_data.is_training != None',
])
return config
def panoptic_deeplab_mobilenetv3_small_coco() -> cfg.ExperimentConfig:
"""COCO panoptic segmentation with Panoptic Deeplab."""
train_steps = 200000
train_batch_size = 64
eval_batch_size = 1
steps_per_epoch = _COCO_TRAIN_EXAMPLES // train_batch_size
validation_steps = _COCO_VAL_EXAMPLES // eval_batch_size
num_panoptic_categories = 201
num_thing_categories = 91
ignore_label = 0
is_thing = [False]
for idx in range(1, num_panoptic_categories):
is_thing.append(True if idx <= num_thing_categories else False)
input_size = [640, 640, 3]
output_stride = 16
aspp_dilation_rates = [6, 12, 18]
level = int(np.math.log2(output_stride))
config = cfg.ExperimentConfig(
runtime=cfg.RuntimeConfig(mixed_precision_dtype='float32',
enable_xla=True),
task=PanopticDeeplabTask(
init_checkpoint=
'gs://tf_model_garden/vision/panoptic/panoptic_deeplab/imagenet/mobilenetv3_small/ckpt-312000',
init_checkpoint_modules=['backbone'],
model=PanopticDeeplab(
num_classes=num_panoptic_categories,
input_size=input_size,
backbone=backbones.Backbone(type='mobilenet',
mobilenet=backbones.MobileNet(
model_id='MobileNetV3Small',
filter_size_scale=1.0,
stochastic_depth_drop_rate=0.0,
output_stride=output_stride)),
decoder=decoders.Decoder(
type='aspp',
aspp=decoders.ASPP(level=level,
num_filters=256,
pool_kernel_size=input_size[:2],
dilation_rates=aspp_dilation_rates,
use_depthwise_convolution=True,
dropout_rate=0.1)),
semantic_head=SemanticHead(level=level,
num_convs=1,
num_filters=256,
kernel_size=5,
use_depthwise_convolution=True,
upsample_factor=1,
low_level=[3, 2],
low_level_num_filters=[64, 32],
fusion_num_output_filters=256,
prediction_kernel_size=1),
instance_head=InstanceHead(level=level,
num_convs=1,
num_filters=32,
kernel_size=5,
use_depthwise_convolution=True,
upsample_factor=1,
low_level=[3, 2],
low_level_num_filters=[32, 16],
fusion_num_output_filters=128,
prediction_kernel_size=1),
shared_decoder=False,
generate_panoptic_masks=True,
post_processor=PanopticDeeplabPostProcessor(
output_size=input_size[:2],
center_score_threshold=0.1,
thing_class_ids=list(range(1, num_thing_categories)),
label_divisor=256,
stuff_area_limit=4096,
ignore_label=ignore_label,
nms_kernel=41,
keep_k_centers=200,
rescale_predictions=True)),
losses=Losses(label_smoothing=0.0,
ignore_label=ignore_label,
l2_weight_decay=0.0,
top_k_percent_pixels=0.2,
segmentation_loss_weight=1.0,
center_heatmap_loss_weight=200,
center_offset_loss_weight=0.01),
train_data=DataConfig(
input_path=os.path.join(_COCO_INPUT_PATH_BASE, 'train*'),
is_training=True,
global_batch_size=train_batch_size,
parser=Parser(
aug_scale_min=0.5,
aug_scale_max=2.0,
aug_rand_hflip=True,
aug_type=common.Augmentation(
type='autoaug',
autoaug=common.AutoAugment(
augmentation_name='panoptic_deeplab_policy')),
sigma=8.0,
small_instance_area_threshold=4096,
small_instance_weight=3.0)),
validation_data=DataConfig(
input_path=os.path.join(_COCO_INPUT_PATH_BASE, 'val*'),
is_training=False,
global_batch_size=eval_batch_size,
parser=Parser(resize_eval_groundtruth=False,
groundtruth_padded_size=[640, 640],
aug_scale_min=1.0,
aug_scale_max=1.0,
aug_rand_hflip=False,
aug_type=None,
sigma=8.0,
small_instance_area_threshold=4096,
small_instance_weight=3.0),
drop_remainder=False),
evaluation=Evaluation(ignored_label=ignore_label,
max_instances_per_category=256,
offset=256 * 256 * 256,
is_thing=is_thing,
rescale_predictions=True,
report_per_class_pq=False,
report_per_class_iou=False,
report_train_mean_iou=False)),
trainer=cfg.TrainerConfig(
train_steps=train_steps,
validation_steps=validation_steps,
validation_interval=steps_per_epoch,
steps_per_loop=steps_per_epoch,
summary_interval=steps_per_epoch,
checkpoint_interval=steps_per_epoch,
optimizer_config=optimization.OptimizationConfig({
'optimizer': {
'type': 'adam',
},
'learning_rate': {
'type': 'polynomial',
'polynomial': {
'initial_learning_rate': 0.001,
'decay_steps': train_steps,
'end_learning_rate': 0.0,
'power': 0.9
}
},
'warmup': {
'type': 'linear',
'linear': {
'warmup_steps': 2000,
'warmup_learning_rate': 0
}
}
})),
restrictions=[
'task.train_data.is_training != None',
'task.validation_data.is_training != None'
])
return config