 Visualizza su TensorFlow.org |  Esegui in Google Colab |  Visualizza su GitHub |  Scarica taccuino |  Vedi il modello del mozzo TF |
Yunpeng Li, Dominik Roblek, and Marco Tagliasacchi. Da qui a lì: video intermedi utilizzando le convoluzioni 3D dirette, 2019.
https://arxiv.org/abs/1905.10240
Caratteristiche dell'hub attuale:
- ha modelli per BAIR Robot push video e set di dati video d'azione KTH (sebbene questa colab utilizzi solo BAIR)
- Set di dati BAIR già disponibile nell'hub. Tuttavia, i video KTH devono essere forniti dagli utenti stessi.
- solo valutazione (generazione video) per ora
- la dimensione del batch e la dimensione del frame sono hardcoded
Impostare
Dal momento che tfds.load('bair_robot_pushing_small', split='test') sarebbe scaricare un archivio 30GB che contiene anche i dati di allenamento, scarichiamo un archivio separato che solo contiene i dati di test 190MB. Il set di dati utilizzato è stato pubblicato da questo lavoro ed è autorizzato come Creative Commons BY 4.0.
import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
import tensorflow_hub as hub
import tensorflow_datasets as tfds
from tensorflow_datasets.core import SplitGenerator
from tensorflow_datasets.video.bair_robot_pushing import BairRobotPushingSmall
import tempfile
import pathlib
TEST_DIR = pathlib.Path(tempfile.mkdtemp()) / "bair_robot_pushing_small/softmotion30_44k/test/"
# Download the test split to $TEST_DIRmkdir -p $TEST_DIRwget -nv https://storage.googleapis.com/download.tensorflow.org/data/bair_test_traj_0_to_255.tfrecords -O $TEST_DIR/traj_0_to_255.tfrecords
2021-11-05 12:44:33 URL:https://storage.googleapis.com/download.tensorflow.org/data/bair_test_traj_0_to_255.tfrecords [189852160/189852160] -> "/tmp/tmpn_2q0lmh/bair_robot_pushing_small/softmotion30_44k/test/traj_0_to_255.tfrecords" [1]
# Since the dataset builder expects the train and test split to be downloaded,
# patch it so it only expects the test data to be available
builder = BairRobotPushingSmall()
test_generator = SplitGenerator(name='test', gen_kwargs={"filedir": str(TEST_DIR)})
builder._split_generators = lambda _: [test_generator]
builder.download_and_prepare()
BAIR: Demo basata su input array numpy
# @title Load some example data (BAIR).
batch_size = 16
# If unable to download the dataset automatically due to "not enough disk space", please download manually to Google Drive and
# load using tf.data.TFRecordDataset.
ds = builder.as_dataset(split="test")
test_videos = ds.batch(batch_size)
first_batch = next(iter(test_videos))
input_frames = first_batch['image_aux1'][:, ::15]
input_frames = tf.cast(input_frames, tf.float32)
# @title Visualize loaded videos start and end frames.
print('Test videos shape [batch_size, start/end frame, height, width, num_channels]: ', input_frames.shape)
sns.set_style('white')
plt.figure(figsize=(4, 2*batch_size))
for i in range(batch_size)[:4]:
plt.subplot(batch_size, 2, 1 + 2*i)
plt.imshow(input_frames[i, 0] / 255.0)
plt.title('Video {}: First frame'.format(i))
plt.axis('off')
plt.subplot(batch_size, 2, 2 + 2*i)
plt.imshow(input_frames[i, 1] / 255.0)
plt.title('Video {}: Last frame'.format(i))
plt.axis('off')
Test videos shape [batch_size, start/end frame, height, width, num_channels]: (16, 2, 64, 64, 3)
Modulo hub di carico
hub_handle = 'https://tfhub.dev/google/tweening_conv3d_bair/1'
module = hub.load(hub_handle).signatures['default']
WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/weights:0' shape=(4, 4, 4, 3, 64) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/weights:0' shape=(4, 4, 4, 3, 64) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/beta:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/beta:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/gamma:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/gamma:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/weights:0' shape=(4, 4, 4, 64, 128) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/weights:0' shape=(4, 4, 4, 64, 128) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/LayerNorm/beta:0' shape=(128,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/LayerNorm/beta:0' shape=(128,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/weights:0' shape=(4, 4, 4, 3, 64) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/weights:0' shape=(4, 4, 4, 3, 64) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/beta:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/beta:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/gamma:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/gamma:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/weights:0' shape=(4, 4, 4, 64, 128) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/weights:0' shape=(4, 4, 4, 64, 128) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/LayerNorm/beta:0' shape=(128,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/LayerNorm/beta:0' shape=(128,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/weights:0' shape=(4, 4, 4, 3, 64) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/weights:0' shape=(4, 4, 4, 3, 64) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/beta:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/beta:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/gamma:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/gamma:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/weights:0' shape=(4, 4, 4, 64, 128) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/weights:0' shape=(4, 4, 4, 64, 128) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/LayerNorm/beta:0' shape=(128,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/LayerNorm/beta:0' shape=(128,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/weights:0' shape=(4, 4, 4, 3, 64) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/weights:0' shape=(4, 4, 4, 3, 64) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/beta:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/beta:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/gamma:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_0/LayerNorm/gamma:0' shape=(64,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/weights:0' shape=(4, 4, 4, 64, 128) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/weights:0' shape=(4, 4, 4, 64, 128) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/LayerNorm/beta:0' shape=(128,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables(). WARNING:tensorflow:Unable to create a python object for variable <tf.Variable 'video_discriminator/conv_1/LayerNorm/beta:0' shape=(128,) dtype=float32_ref> because it is a reference variable. It may not be visible to training APIs. If this is a problem, consider rebuilding the SavedModel after running tf.compat.v1.enable_resource_variables().
Genera e mostra i video
filled_frames = module(input_frames)['default'] / 255.0
# Show sequences of generated video frames.
# Concatenate start/end frames and the generated filled frames for the new videos.
generated_videos = np.concatenate([input_frames[:, :1] / 255.0, filled_frames, input_frames[:, 1:] / 255.0], axis=1)
for video_id in range(4):
fig = plt.figure(figsize=(10 * 2, 2))
for frame_id in range(1, 16):
ax = fig.add_axes([frame_id * 1 / 16., 0, (frame_id + 1) * 1 / 16., 1],
xmargin=0, ymargin=0)
ax.imshow(generated_videos[video_id, frame_id])
ax.axis('off')
