 TensorFlow.org で実行 |
 Google Colab で実行
|
 GitHub でソースを表示 |
 ノートブックをダウンロード |
 TF Hub モデルを見る |
Yunpeng Li, Dominik Roblek, and Marco Tagliasacchi. From Here to There: Video Inbetweening Using Direct 3D Convolutions, 2019.
https://arxiv.org/abs/1905.10240
現在の Hub の特徴:
- BAIR ロボットによる動画のプッシュと KTH アクション動画データセットのモデルがあります（この Colab では BAIR のみを使用）。
- BAIR データセットはすでに Hub に提供されていますが、KTH 動画はユーザーが提供する必要があります。
- 現在のところ、評価のみ（動画生成）です。
- バッチサイズとフレームサイズはハードコードされています。
セットアップ
tfds.load('bair_robot_pushing_small', split='test') は、トレーニングデータも含む 30GB のアーカイブをダウンロードするため、190MB のテストデータのみを含む別のアーカイブをダウンロードします。使用されたデータセットはこの論文で公開されており、Creative Commons BY 4.0 としてライセンスを提供しています。
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/"
2024-01-11 17:58:16.902174: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2024-01-11 17:58:16.902225: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2024-01-11 17:58:16.903908: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
# 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
2024-01-11 17:58:23 URL:https://storage.googleapis.com/download.tensorflow.org/data/bair_test_traj_0_to_255.tfrecords [189852160/189852160] -> "/tmpfs/tmp/tmp0acudqhc/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()
WARNING:absl:DEPRECATED! Do not use a DatasetBuilder class directly, but call `tfds.builder_cls('bair_robot_pushing_small')`.
BAIR: Numpy 配列の入力に基づく実演
# @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)
WARNING:absl:`FeatureConnector.dtype` is deprecated. Please change your code to use NumPy with the field `FeatureConnector.np_dtype` or use TensorFlow with the field `FeatureConnector.tf_dtype`. WARNING:absl:`FeatureConnector.dtype` is deprecated. Please change your code to use NumPy with the field `FeatureConnector.np_dtype` or use TensorFlow with the field `FeatureConnector.tf_dtype`.
# @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)
Hub モジュールの読み込み
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().
動画の生成と表示
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')
