add model TSM

CITATION.cff

+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+authors:
+  - name: "MMAction2 Contributors"
+title: "OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark"
+date-released: 2020-07-21
+url: "https://github.com/open-mmlab/mmaction2"
+license: Apache-2.0

LICENSE

+Copyright 2018-2019 Open-MMLab. All rights reserved.
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2018-2019 Open-MMLab.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

MANIFEST.in

+include mmaction/.mim/model-index.yml
+recursive-include mmaction/.mim/configs *.py *.yml
+recursive-include mmaction/.mim/tools *.sh *.py

configs/_base_/default_runtime.py

+checkpoint_config = dict(interval=1)
+log_config = dict(
+    interval=20,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook'),
+    ])
+# runtime settings
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+
+# disable opencv multithreading to avoid system being overloaded
+opencv_num_threads = 0
+# set multi-process start method as `fork` to speed up the training
+mp_start_method = 'fork'

configs/_base_/models/audioonly_r50.py

+# model settings
+model = dict(
+    type='AudioRecognizer',
+    backbone=dict(
+        type='ResNetAudio',
+        depth=50,
+        pretrained=None,
+        in_channels=1,
+        norm_eval=False),
+    cls_head=dict(
+        type='AudioTSNHead',
+        num_classes=400,
+        in_channels=1024,
+        dropout_ratio=0.5,
+        init_std=0.01),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/bmn_400x100.py

+# model settings
+model = dict(
+    type='BMN',
+    temporal_dim=100,
+    boundary_ratio=0.5,
+    num_samples=32,
+    num_samples_per_bin=3,
+    feat_dim=400,
+    soft_nms_alpha=0.4,
+    soft_nms_low_threshold=0.5,
+    soft_nms_high_threshold=0.9,
+    post_process_top_k=100)

configs/_base_/models/bsn_pem.py

+# model settings
+model = dict(
+    type='PEM',
+    pem_feat_dim=32,
+    pem_hidden_dim=256,
+    pem_u_ratio_m=1,
+    pem_u_ratio_l=2,
+    pem_high_temporal_iou_threshold=0.6,
+    pem_low_temporal_iou_threshold=0.2,
+    soft_nms_alpha=0.75,
+    soft_nms_low_threshold=0.65,
+    soft_nms_high_threshold=0.9,
+    post_process_top_k=100)

configs/_base_/models/bsn_tem.py

+# model settings
+model = dict(
+    type='TEM',
+    temporal_dim=100,
+    boundary_ratio=0.1,
+    tem_feat_dim=400,
+    tem_hidden_dim=512,
+    tem_match_threshold=0.5)

configs/_base_/models/c3d_sports1m_pretrained.py

+# model settings
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='C3D',
+        pretrained=  # noqa: E251
+        'https://download.openmmlab.com/mmaction/recognition/c3d/c3d_sports1m_pretrain_20201016-dcc47ddc.pth',  # noqa: E501
+        style='pytorch',
+        conv_cfg=dict(type='Conv3d'),
+        norm_cfg=None,
+        act_cfg=dict(type='ReLU'),
+        dropout_ratio=0.5,
+        init_std=0.005),
+    cls_head=dict(
+        type='I3DHead',
+        num_classes=101,
+        in_channels=4096,
+        spatial_type=None,
+        dropout_ratio=0.5,
+        init_std=0.01),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='score'))

configs/_base_/models/i3d_r50.py

+# model settings
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet3d',
+        pretrained2d=True,
+        pretrained='torchvision://resnet50',
+        depth=50,
+        conv1_kernel=(5, 7, 7),
+        conv1_stride_t=2,
+        pool1_stride_t=2,
+        conv_cfg=dict(type='Conv3d'),
+        norm_eval=False,
+        inflate=((1, 1, 1), (1, 0, 1, 0), (1, 0, 1, 0, 1, 0), (0, 1, 0)),
+        zero_init_residual=False),
+    cls_head=dict(
+        type='I3DHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        dropout_ratio=0.5,
+        init_std=0.01),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))
+
+# This setting refers to https://github.com/open-mmlab/mmaction/blob/master/mmaction/models/tenons/backbones/resnet_i3d.py#L329-L332  # noqa: E501

configs/_base_/models/ircsn_r152.py

+# model settings
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet3dCSN',
+        pretrained2d=False,
+        pretrained=None,
+        depth=152,
+        with_pool2=False,
+        bottleneck_mode='ir',
+        norm_eval=False,
+        zero_init_residual=False),
+    cls_head=dict(
+        type='I3DHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        dropout_ratio=0.5,
+        init_std=0.01),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob', max_testing_views=10))

configs/_base_/models/r2plus1d_r34.py

+# model settings
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet2Plus1d',
+        depth=34,
+        pretrained=None,
+        pretrained2d=False,
+        norm_eval=False,
+        conv_cfg=dict(type='Conv2plus1d'),
+        norm_cfg=dict(type='SyncBN', requires_grad=True, eps=1e-3),
+        conv1_kernel=(3, 7, 7),
+        conv1_stride_t=1,
+        pool1_stride_t=1,
+        inflate=(1, 1, 1, 1),
+        spatial_strides=(1, 2, 2, 2),
+        temporal_strides=(1, 2, 2, 2),
+        zero_init_residual=False),
+    cls_head=dict(
+        type='I3DHead',
+        num_classes=400,
+        in_channels=512,
+        spatial_type='avg',
+        dropout_ratio=0.5,
+        init_std=0.01),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/slowfast_r50.py

+# model settings
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet3dSlowFast',
+        pretrained=None,
+        resample_rate=8,  # tau
+        speed_ratio=8,  # alpha
+        channel_ratio=8,  # beta_inv
+        slow_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=True,
+            conv1_kernel=(1, 7, 7),
+            dilations=(1, 1, 1, 1),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            inflate=(0, 0, 1, 1),
+            norm_eval=False),
+        fast_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=False,
+            base_channels=8,
+            conv1_kernel=(5, 7, 7),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            norm_eval=False)),
+    cls_head=dict(
+        type='SlowFastHead',
+        in_channels=2304,  # 2048+256
+        num_classes=400,
+        spatial_type='avg',
+        dropout_ratio=0.5),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/slowonly_r50.py

+# model settings
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet3dSlowOnly',
+        depth=50,
+        pretrained='torchvision://resnet50',
+        lateral=False,
+        conv1_kernel=(1, 7, 7),
+        conv1_stride_t=1,
+        pool1_stride_t=1,
+        inflate=(0, 0, 1, 1),
+        norm_eval=False),
+    cls_head=dict(
+        type='I3DHead',
+        in_channels=2048,
+        num_classes=400,
+        spatial_type='avg',
+        dropout_ratio=0.5),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/tanet_r50.py

+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='TANet',
+        pretrained='torchvision://resnet50',
+        depth=50,
+        num_segments=8,
+        tam_cfg=dict()),
+    cls_head=dict(
+        type='TSMHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.5,
+        init_std=0.001),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/tin_r50.py

+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='ResNetTIN',
+        pretrained='torchvision://resnet50',
+        depth=50,
+        norm_eval=False,
+        shift_div=4),
+    cls_head=dict(
+        type='TSMHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.5,
+        init_std=0.001,
+        is_shift=False),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips=None))

configs/_base_/models/tpn_slowonly_r50.py

+# model settings
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet3dSlowOnly',
+        depth=50,
+        pretrained='torchvision://resnet50',
+        lateral=False,
+        out_indices=(2, 3),
+        conv1_kernel=(1, 7, 7),
+        conv1_stride_t=1,
+        pool1_stride_t=1,
+        inflate=(0, 0, 1, 1),
+        norm_eval=False),
+    neck=dict(
+        type='TPN',
+        in_channels=(1024, 2048),
+        out_channels=1024,
+        spatial_modulation_cfg=dict(
+            in_channels=(1024, 2048), out_channels=2048),
+        temporal_modulation_cfg=dict(downsample_scales=(8, 8)),
+        upsample_cfg=dict(scale_factor=(1, 1, 1)),
+        downsample_cfg=dict(downsample_scale=(1, 1, 1)),
+        level_fusion_cfg=dict(
+            in_channels=(1024, 1024),
+            mid_channels=(1024, 1024),
+            out_channels=2048,
+            downsample_scales=((1, 1, 1), (1, 1, 1))),
+        aux_head_cfg=dict(out_channels=400, loss_weight=0.5)),
+    cls_head=dict(
+        type='TPNHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.5,
+        init_std=0.01),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/tpn_tsm_r50.py

+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='ResNetTSM',
+        pretrained='torchvision://resnet50',
+        depth=50,
+        out_indices=(2, 3),
+        norm_eval=False,
+        shift_div=8),
+    neck=dict(
+        type='TPN',
+        in_channels=(1024, 2048),
+        out_channels=1024,
+        spatial_modulation_cfg=dict(
+            in_channels=(1024, 2048), out_channels=2048),
+        temporal_modulation_cfg=dict(downsample_scales=(8, 8)),
+        upsample_cfg=dict(scale_factor=(1, 1, 1)),
+        downsample_cfg=dict(downsample_scale=(1, 1, 1)),
+        level_fusion_cfg=dict(
+            in_channels=(1024, 1024),
+            mid_channels=(1024, 1024),
+            out_channels=2048,
+            downsample_scales=((1, 1, 1), (1, 1, 1))),
+        aux_head_cfg=dict(out_channels=174, loss_weight=0.5)),
+    cls_head=dict(
+        type='TPNHead',
+        num_classes=174,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.5,
+        init_std=0.01),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob', fcn_test=True))