def test_spinenet_creation(self, model_id): """Test creation of SpineNet models.""" input_size = 128 min_level = 3 max_level = 7 input_specs = tf.keras.layers.InputSpec( shape=[None, input_size, input_size, 3]) network = backbones.SpineNet(input_specs=input_specs, min_level=min_level, max_level=max_level, norm_momentum=0.99, norm_epsilon=1e-5) backbone_config = backbones_cfg.Backbone( type='spinenet', spinenet=backbones_cfg.SpineNet(model_id=model_id)) 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, input_size, input_size, 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 retinanet_spinenet_coco() -> cfg.ExperimentConfig: """COCO object detection with RetinaNet using SpineNet backbone.""" train_batch_size = 256 eval_batch_size = 8 steps_per_epoch = COCO_TRAIN_EXAMPLES // train_batch_size input_size = 640 config = cfg.ExperimentConfig( runtime=cfg.RuntimeConfig(mixed_precision_dtype='float32'), task=RetinaNetTask( annotation_file=os.path.join(COCO_INPUT_PATH_BASE, 'instances_val2017.json'), model=RetinaNet( backbone=backbones.Backbone(type='spinenet', spinenet=backbones.SpineNet( model_id='49', stochastic_depth_drop_rate=0.2, min_level=3, max_level=7)), decoder=decoders.Decoder(type='identity', identity=decoders.Identity()), anchor=Anchor(anchor_size=3), norm_activation=common.NormActivation(use_sync_bn=True, activation='swish'), num_classes=91, input_size=[input_size, input_size, 3], min_level=3, max_level=7), losses=Losses(l2_weight_decay=4e-5), 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=0.1, 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)), trainer=cfg.TrainerConfig( train_steps=500 * steps_per_epoch, validation_steps=COCO_VAL_EXAMPLES // 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': [475 * steps_per_epoch, 490 * steps_per_epoch], 'values': [ 0.32 * train_batch_size / 256.0, 0.032 * train_batch_size / 256.0, 0.0032 * train_batch_size / 256.0 ], } }, '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', 'task.model.min_level == task.model.backbone.spinenet.min_level', 'task.model.max_level == task.model.backbone.spinenet.max_level', ]) return config
def cascadercnn_spinenet_coco() -> cfg.ExperimentConfig: """COCO object detection with Cascade RCNN-RS with SpineNet backbone.""" steps_per_epoch = 463 coco_val_samples = 5000 train_batch_size = 256 eval_batch_size = 8 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='spinenet', spinenet=backbones.SpineNet( model_id='49', min_level=3, max_level=7, )), decoder=decoders.Decoder( type='identity', identity=decoders.Identity()), roi_sampler=ROISampler(cascade_iou_thresholds=[0.6, 0.7]), detection_head=DetectionHead( class_agnostic_bbox_pred=True, cascade_class_ensemble=True), anchor=Anchor(anchor_size=3), norm_activation=common.NormActivation( use_sync_bn=True, activation='swish'), num_classes=91, input_size=[640, 640, 3], min_level=3, max_level=7, 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=0.1, aug_scale_max=2.5)), 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 * 500, 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 * 475, steps_per_epoch * 490 ], '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', 'task.model.min_level == task.model.backbone.spinenet.min_level', 'task.model.max_level == task.model.backbone.spinenet.max_level', ]) return config
def deep_mask_head_rcnn_spinenet_coco() -> cfg.ExperimentConfig: """COCO object detection with Mask R-CNN with SpineNet backbone.""" steps_per_epoch = 463 coco_val_samples = 5000 train_batch_size = 256 eval_batch_size = 8 config = cfg.ExperimentConfig( runtime=cfg.RuntimeConfig(mixed_precision_dtype='bfloat16'), task=DeepMaskHeadRCNNTask( annotation_file=os.path.join(maskrcnn_config.COCO_INPUT_PATH_BASE, 'instances_val2017.json'), # pytype: disable=wrong-keyword-args model=DeepMaskHeadRCNN( backbone=backbones.Backbone(type='spinenet', spinenet=backbones.SpineNet( model_id='49', min_level=3, max_level=7, )), decoder=decoders.Decoder(type='identity', identity=decoders.Identity()), anchor=maskrcnn_config.Anchor(anchor_size=3), norm_activation=common.NormActivation(use_sync_bn=True), num_classes=91, input_size=[640, 640, 3], min_level=3, max_level=7, include_mask=True), # pytype: disable=wrong-keyword-args losses=maskrcnn_config.Losses(l2_weight_decay=0.00004), train_data=maskrcnn_config.DataConfig( input_path=os.path.join(maskrcnn_config.COCO_INPUT_PATH_BASE, 'train*'), is_training=True, global_batch_size=train_batch_size, parser=maskrcnn_config.Parser(aug_rand_hflip=True, aug_scale_min=0.5, aug_scale_max=2.0)), validation_data=maskrcnn_config.DataConfig( input_path=os.path.join(maskrcnn_config.COCO_INPUT_PATH_BASE, 'val*'), is_training=False, global_batch_size=eval_batch_size, drop_remainder=False)), # pytype: disable=wrong-keyword-args 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', 'task.model.min_level == task.model.backbone.spinenet.min_level', 'task.model.max_level == task.model.backbone.spinenet.max_level', ]) return config