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_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 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