def test_resnet3d_network_creation(self, model_id, temporal_size,
spatial_size, activation,
aggregate_endpoints):
"""Test for creation of a ResNet3D-50 classifier."""
input_specs = tf.keras.layers.InputSpec(
shape=[None, temporal_size, spatial_size, spatial_size, 3])
temporal_strides = [1, 1, 1, 1]
temporal_kernel_sizes = [(3, 3, 3), (3, 1, 3, 1), (3, 1, 3, 1, 3, 1),
(1, 3, 1)]
tf.keras.backend.set_image_data_format('channels_last')
backbone = backbones.ResNet3D(
model_id=model_id,
temporal_strides=temporal_strides,
temporal_kernel_sizes=temporal_kernel_sizes,
input_specs=input_specs,
activation=activation)
num_classes = 1000
model = video_classification_model.VideoClassificationModel(
backbone=backbone,
num_classes=num_classes,
input_specs={'image': input_specs},
dropout_rate=0.2,
aggregate_endpoints=aggregate_endpoints,
)
inputs = np.random.rand(2, temporal_size, spatial_size, spatial_size, 3)
logits = model(inputs)
self.assertAllEqual([2, num_classes], logits.numpy().shape)
def test_serialize_deserialize(self):
"""Validate the classification network can be serialized and deserialized."""
model_id = 50
temporal_strides = [1, 1, 1, 1]
temporal_kernel_sizes = [(3, 3, 3), (3, 1, 3, 1), (3, 1, 3, 1, 3, 1),
(1, 3, 1)]
backbone = backbones.ResNet3D(
model_id=model_id,
temporal_strides=temporal_strides,
temporal_kernel_sizes=temporal_kernel_sizes)
model = video_classification_model.VideoClassificationModel(
backbone=backbone, num_classes=1000)
config = model.get_config()
new_model = video_classification_model.VideoClassificationModel.from_config(
config)
# Validate that the config can be forced to JSON.
_ = new_model.to_json()
# If the serialization was successful, the new config should match the old.
self.assertAllEqual(model.get_config(), new_model.get_config())
def build_video_classification_model(
input_specs: tf.keras.layers.InputSpec,
model_config: video_classification_cfg.VideoClassificationModel,
num_classes: int,
l2_regularizer: tf.keras.regularizers.Regularizer = None
) -> tf.keras.Model:
"""Builds the video classification model."""
input_specs_dict = {'image': input_specs}
norm_activation_config = model_config.norm_activation
backbone = backbones.factory.build_backbone(
input_specs=input_specs,
backbone_config=model_config.backbone,
norm_activation_config=norm_activation_config,
l2_regularizer=l2_regularizer)
model = video_classification_model.VideoClassificationModel(
backbone=backbone,
num_classes=num_classes,
input_specs=input_specs_dict,
dropout_rate=model_config.dropout_rate,
aggregate_endpoints=model_config.aggregate_endpoints,
kernel_regularizer=l2_regularizer,
require_endpoints=model_config.require_endpoints)
return model