├── LICENSE ├── README.md ├── convert2file.py ├── download_gqn.py └── gqn_dataset.py /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # gqn_datasets_translator 2 | 3 | With major contributions from [versatran01](https://github.com/versatran01). 4 | 5 | ### Data downloader and data converter for DeepMind GQN dataset https://github.com/deepmind/gqn-datasets to use with other libraries than TensorFlow 6 | 7 | Don't hesitate to make a pull request. 8 | 9 | **Dependencies** 10 | 11 | You need to install: 12 | 13 | - TensorFlow [here](https://www.tensorflow.org/install/) 14 | - gsutil [here](https://cloud.google.com/storage/docs/gsutil_install) *Note that gsutil works in python 2.\* only* 15 | 16 | 17 | **Download the tfrecord dataset** 18 | 19 | If you want to download the entire dataset: 20 | ```shell 21 | gsutil -m cp -R gs://gqn-dataset/ . 22 | ``` 23 | 24 | If you want to download a proportion of the dataset only: 25 | ```shell 26 | python download_gqn.py 27 | ``` 28 | 29 | **Convert the raw dataset** 30 | 31 | Command line options: 32 | ```shell 33 | usage: convert2file.py [-h] [-b BATCH_SIZE] [-n FIRST_N] [-m MODE] 34 | base_dir dataset 35 | 36 | Convert gqn tfrecords to gzip files. 37 | 38 | positional arguments: 39 | base_dir base directory of gqn dataset 40 | dataset datasets to convert, eg. shepard_metzler_5_parts 41 | 42 | optional arguments: 43 | -h, --help show this help message and exit 44 | -b BATCH_SIZE, --batch-size BATCH_SIZE 45 | number of sequences in each output file 46 | -n FIRST_N, --first-n FIRST_N 47 | convert only the first n tfrecords if given 48 | -m MODE, --mode MODE whether to convert train or test 49 | ``` 50 | 51 | Convert all records with all sequences in sm5 train (400 records, 2000 seq each): 52 | ```shell 53 | python convert2file.py ~/gqn_dataset shepard_metzler_5_parts 54 | ``` 55 | 56 | Convert first 20 records with batch size of 128 in sm5 test: 57 | ```shell 58 | python convert2file.py ~/gqn_dataset shepard_metzler_5_parts -n 20 -b 128 -m test 59 | ``` 60 | 61 | **Size of the datasets:** 62 | 63 | | Names | Sizes | 64 | | ------------- |:-------------:| 65 | | _total_ | 1.45 Tb | 66 | | ------------- | --------------| 67 | | jaco | 198.97 Gb | 68 | | mazes | 136.23 Gb | 69 | | rooms\_free\_camera\_no\_object\_rotations | 255.75 Gb | 70 | | rooms\_free\_camera\_with\_object\_rotations | 598.75 Gb | 71 | | rooms\_ring\_camera | 250.89 Gb | 72 | | shepard\_metzler\_5\_parts | 21.09 Gb | 73 | | shepard\_metzler\_7\_parts | 23.68 Gb | 74 | -------------------------------------------------------------------------------- /convert2file.py: -------------------------------------------------------------------------------- 1 | import os 2 | import tensorflow as tf 3 | import torch 4 | import gzip 5 | from functools import partial 6 | from collections import namedtuple 7 | import argparse as ap 8 | import multiprocessing as mp 9 | 10 | 11 | """ 12 | This file converts tfrecords in deepmind gqn dataset to gzip files. Each tfrecord will be converted 13 | to a single gzip file (561-of-900.tfrecord -> 561-of-900.pt.gz). 14 | 15 | Each gzip file contains a list of tuples, where each tuple is of (images, poses) 16 | For example, when converting the shepard_metzler_5_parts dataset with batch_size of 32, the gzip 17 | file contains a list of length 32, each tuple contains images (15,64,64,3) and poses (15,5), where 18 | 15 is the sequence length. 19 | 20 | In the original implementation, each sequence is converted to a gzip file, this results in more than 21 | 800K small files on the disk. Here we choose to pack multiple sequences into one gzip file, thus 22 | avoiding having too many small files. Note that the gqn implementation from wohlert 23 | (https://github.com/wohlert/generative-query-network-pytorch) works with the original version. In 24 | order for it to work with the new format, one can simply change (in wohlert gqn) batch_size to 1 25 | and do a squeeze after the loader. 26 | 27 | It is also recommended to remove the first 500 records of both shepard metzler dataset as they 28 | only contain 20 sequences, compared to the last 400 records which contain 2000 sequences. 29 | 30 | Example: 31 | convert all records with all sequences in sm5 train (400 records, 2000 seq each) 32 | python convert2file.py ~/gqn_dataset shepard_metzler_5_parts 33 | 34 | Convert first 20 records with batch size of 128 in sm5 test 35 | python convert2file.py ~/gqn_dataset shepard_metzler_5_parts -n 20 -b 128 -m test 36 | """ 37 | 38 | tf.logging.set_verbosity(tf.logging.ERROR) # disable annoying logging 39 | os.environ["CUDA_VISIBLE_DEVICES"] = "-1" # disable gpu 40 | 41 | DatasetInfo = namedtuple('DatasetInfo', ['image_size', 'seq_length']) 42 | 43 | all_datasets = dict( 44 | jaco=DatasetInfo(image_size=64, seq_length=11), 45 | mazes=DatasetInfo(image_size=84, seq_length=300), 46 | rooms_free_camera_with_object_rotations=DatasetInfo(image_size=128, seq_length=10), 47 | rooms_ring_camera=DatasetInfo(image_size=64, seq_length=10), 48 | rooms_free_camera_no_object_rotations=DatasetInfo(image_size=64, seq_length=10), 49 | shepard_metzler_5_parts=DatasetInfo(image_size=64, seq_length=15), 50 | shepard_metzler_7_parts=DatasetInfo(image_size=64, seq_length=15) 51 | ) 52 | 53 | _pose_dim = 5 54 | 55 | 56 | def collect_files(path, ext=None, key=None): 57 | if key is None: 58 | files = sorted(os.listdir(path)) 59 | else: 60 | files = sorted(os.listdir(path), key=key) 61 | 62 | if ext is not None: 63 | files = [f for f in files if os.path.splitext(f)[-1] == ext] 64 | 65 | return [os.path.join(path, fname) for fname in files] 66 | 67 | 68 | def convert_record(record, info, batch_size=None): 69 | print(record) 70 | 71 | path, filename = os.path.split(record) 72 | basename = os.path.splitext(filename)[0] 73 | scenes = process_record(record, info, batch_size) 74 | # scenes is a list of tuples (image_seq, pose_seq) 75 | out = os.path.join(path, f'{basename}.pt.gz') 76 | save_to_disk(scenes, out) 77 | 78 | 79 | def save_to_disk(scenes, path): 80 | with gzip.open(path, 'wb') as f: 81 | torch.save(scenes, f) 82 | 83 | 84 | def process_record(record, info, batch_size=None): 85 | engine = tf.python_io.tf_record_iterator(record) 86 | 87 | scenes = [] 88 | for i, data in enumerate(engine): 89 | if i == batch_size: 90 | break 91 | scene = convert_to_numpy(data, info) 92 | scenes.append(scene) 93 | 94 | return scenes 95 | 96 | 97 | def process_images(example, seq_length, image_size): 98 | """Instantiates the ops used to preprocess the frames data.""" 99 | images = tf.concat(example['frames'], axis=0) 100 | images = tf.map_fn(tf.image.decode_jpeg, tf.reshape(images, [-1]), 101 | dtype=tf.uint8, back_prop=False) 102 | shape = (image_size, image_size, 3) 103 | images = tf.reshape(images, (-1, seq_length) + shape) 104 | return images 105 | 106 | 107 | def process_poses(example, seq_length): 108 | """Instantiates the ops used to preprocess the cameras data.""" 109 | poses = example['cameras'] 110 | poses = tf.reshape(poses, (-1, seq_length, _pose_dim)) 111 | return poses 112 | 113 | 114 | def convert_to_numpy(raw_data, info): 115 | seq_length = info.seq_length 116 | image_size = info.image_size 117 | 118 | feature = {'frames': tf.FixedLenFeature(shape=seq_length, dtype=tf.string), 119 | 'cameras': tf.FixedLenFeature(shape=seq_length * _pose_dim, dtype=tf.float32)} 120 | example = tf.parse_single_example(raw_data, feature) 121 | 122 | images = process_images(example, seq_length, image_size) 123 | poses = process_poses(example, seq_length) 124 | 125 | return images.numpy().squeeze(), poses.numpy().squeeze() 126 | 127 | 128 | if __name__ == '__main__': 129 | tf.enable_eager_execution() 130 | parser = ap.ArgumentParser(description='Convert gqn tfrecords to gzip files.') 131 | parser.add_argument('base_dir', nargs=1, 132 | help='base directory of gqn dataset') 133 | parser.add_argument('dataset', nargs=1, 134 | help='datasets to convert, eg. shepard_metzler_5_parts') 135 | parser.add_argument('-b', '--batch-size', type=int, default=None, 136 | help='number of sequences in each output file') 137 | parser.add_argument('-n', '--first-n', type=int, default=None, 138 | help='convert only the first n tfrecords if given') 139 | parser.add_argument('-m', '--mode', type=str, default='train', 140 | help='whether to convert train or test') 141 | args = parser.parse_args() 142 | 143 | base_dir = os.path.expanduser(args.base_dir[0]) 144 | dataset = args.dataset[0] 145 | 146 | print(f'base_dir: {base_dir}') 147 | print(f'dataset: {dataset}') 148 | 149 | info = all_datasets[dataset] 150 | data_dir = os.path.join(base_dir, dataset) 151 | records = collect_files(os.path.join(data_dir, args.mode), '.tfrecord') 152 | 153 | if args.first_n is not None: 154 | records = records[:args.first_n] 155 | 156 | num_proc = mp.cpu_count() 157 | print(f'converting {len(records)} records in {dataset}/{args.mode}, with {num_proc} processes') 158 | 159 | with mp.Pool(processes=num_proc) as pool: 160 | f = partial(convert_record, info=info, batch_size=args.batch_size) 161 | pool.map(f, records) 162 | 163 | print('Done') -------------------------------------------------------------------------------- /download_gqn.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | 4 | import collections 5 | 6 | 7 | DatasetInfo = collections.namedtuple( 8 | 'DatasetInfo', 9 | ['basepath', 'train_size', 'test_size', 'frame_size', 'sequence_size'] 10 | ) 11 | 12 | 13 | DATASETS_INFO = dict( 14 | jaco=DatasetInfo( 15 | basepath='jaco', 16 | train_size=3600, 17 | test_size=400, 18 | frame_size=64, 19 | sequence_size=11), 20 | 21 | mazes=DatasetInfo( 22 | basepath='mazes', 23 | train_size=1080, 24 | test_size=120, 25 | frame_size=84, 26 | sequence_size=300), 27 | 28 | rooms_free_camera_with_object_rotations=DatasetInfo( 29 | basepath='rooms_free_camera_with_object_rotations', 30 | train_size=2034, 31 | test_size=226, 32 | frame_size=128, 33 | sequence_size=10), 34 | 35 | rooms_ring_camera=DatasetInfo( 36 | basepath='rooms_ring_camera', 37 | train_size=2160, 38 | test_size=240, 39 | frame_size=64, 40 | sequence_size=10), 41 | 42 | rooms_free_camera_no_object_rotations=DatasetInfo( 43 | basepath='rooms_free_camera_no_object_rotations', 44 | train_size=2160, 45 | test_size=240, 46 | frame_size=64, 47 | sequence_size=10), 48 | 49 | shepard_metzler_5_parts=DatasetInfo( 50 | basepath='shepard_metzler_5_parts', 51 | train_size=900, 52 | test_size=100, 53 | frame_size=64, 54 | sequence_size=15), 55 | 56 | shepard_metzler_7_parts=DatasetInfo( 57 | basepath='shepard_metzler_7_parts', 58 | train_size=900, 59 | test_size=100, 60 | frame_size=64, 61 | sequence_size=15) 62 | ) 63 | 64 | 65 | if len(sys.argv) < 3: 66 | print(' [!] you need to give a dataset and a proportion to download') 67 | exit() 68 | 69 | 70 | PROP = float(sys.argv[2]) 71 | DATASET = sys.argv[1] 72 | dataset_info = DATASETS_INFO[DATASET] 73 | 74 | top_path = f'{DATASET}' 75 | train_path = f'{DATASET}/train' 76 | test_path = f'{DATASET}/test' 77 | 78 | train_nb = int(PROP * dataset_info.train_size) 79 | test_nb = int(PROP * dataset_info.test_size) 80 | 81 | train_length = len(str(dataset_info.train_size)) 82 | train_template = '{:0%d}-of-{:0%d}.tfrecord' % (train_length, train_length) 83 | 84 | test_length = len(str(dataset_info.test_size)) 85 | test_template = '{:0%d}-of-{:0%d}.tfrecord' % (test_length, test_length) 86 | 87 | os.mkdir(top_path) 88 | os.mkdir(train_path) 89 | os.mkdir(test_path) 90 | 91 | header = 'gsutil -m cp gs://gqn-dataset/{}'.format(DATASET) 92 | 93 | ## train copy 94 | for i in range(train_nb): 95 | file = train_template.format(i+1, dataset_info.train_size) 96 | command = '{0}/train/{1} {2}/{1}'.format(header, file, train_path) 97 | # print(command) 98 | os.system(command) 99 | 100 | ## test copy 101 | for i in range(test_nb): 102 | file = test_template.format(i+1, dataset_info.test_size) 103 | command = '{0}/test/{1} {2}/{1}'.format(header, file, test_path) 104 | # print(command) 105 | os.system(command) 106 | -------------------------------------------------------------------------------- /gqn_dataset.py: -------------------------------------------------------------------------------- 1 | import os 2 | import gzip 3 | import torch 4 | 5 | def collect_files(path, ext=None, key=None): 6 | if key is None: 7 | files = sorted(os.listdir(path)) 8 | else: 9 | files = sorted(os.listdir(path), key=key) 10 | 11 | if ext is not None: 12 | files = [f for f in files if os.path.splitext(f)[-1] == ext] 13 | 14 | return [os.path.join(path, fname) for fname in files] 15 | 16 | _base_dir = os.path.expanduser('~/Workspace/dataset/gqn_dataset') 17 | 18 | 19 | class GQNDataset: 20 | def __init__(self, base_dir=_base_dir, scene='shepard_metzler_5_parts', 21 | mode='train', transform=None): 22 | self.base_dir = os.path.expanduser(base_dir) 23 | self.data_dir = os.path.join(self.base_dir, scene, mode) 24 | self.filenames = collect_files(self.data_dir, ext='.gz') 25 | self.transform = transform 26 | 27 | def __len__(self): 28 | return len(self.filenames) 29 | 30 | def __getitem__(self, i): 31 | filename = self.filenames[i] 32 | 33 | with gzip.open(filename, 'rb') as f: 34 | data = torch.load(f) 35 | 36 | images_list, poses_list = list(zip(*data)) 37 | images_seqs = np.array(images_list) 38 | poses_seqs = np.array(poses_list) 39 | 40 | return images_seqs 41 | 42 | 43 | if __name__ == '__main__': 44 | import matplotlib.pyplot as plt 45 | import numpy as np 46 | 47 | ds = GQNDataset(mode='train') 48 | images_list = ds[0] 49 | 50 | n = 6 51 | f = plt.figure(figsize=(12, 8)) 52 | axes = f.subplots(nrows=n, ncols=1, sharex=True, sharey=True) 53 | for i in range(n): 54 | images = images_list[i] 55 | grid = np.hstack(images[:10]) 56 | axes[i].imshow(grid) 57 | plt.show() 58 | --------------------------------------------------------------------------------