Archive original DeepEthogram pretrained models from NAS

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pretrained_models/200221_115158_TinyMotionNet/opticalflow_metrics.tiff filter=lfs diff=lfs merge=lfs -text
+pretrained_models/200310_174416_MotionNet_kinetics/opticalflow_metrics.tiff filter=lfs diff=lfs merge=lfs -text
+pretrained_models/200313_125331_TinyMotionNet3D_kinetics/opticalflow_metrics.tiff filter=lfs diff=lfs merge=lfs -text
+pretrained_models/200409_101808_hidden_two_stream_kinetics_degs/classification_metrics.tiff filter=lfs diff=lfs merge=lfs -text
+pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/classification_metrics.tiff filter=lfs diff=lfs merge=lfs -text
+pretrained_models/200415_125824_hidden_two_stream_kinetics_degf/classification_metrics.tiff filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,39 @@
+Academic and Non-Commercial Research Use Software License and Terms of Use
+DeepEthogram: Automated behavior classification (the “Software”, tracked by Harvard Case No. 8336).  The Software was developed by Christopher Harvey and Jim Bohnslav, Department of Neurobiology, Harvard Medical School.
+Using the Software indicates your agreement to be bound by the terms of this Software Use Agreement (“Agreement”). Absent your agreement to the terms below, you (the “End User”) have no rights to hold or use the Software whatsoever.
+President and Fellows of Harvard College (“Harvard”) agrees to grant hereunder the limited non-exclusive license to End User for the use of the Software in the performance of End User’s internal, non-commercial research and academic use at End User’s academic or not-for-profit research institution (“Institution”) on the following terms and conditions:
+    1. NO REDISTRIBUTION. The Software remains the property of Harvard, and End User shall not publish, distribute, or otherwise transfer or make available the Software to any other party.
+
+    2. NO COMMERCIAL USE. End User shall not use the Software for commercial purposes, including for any internal research purposes for or on behalf of any for-profit entity, and any such use of the Software is expressly prohibited.  This prohibition includes, but is not limited to, use of the Software in fee-for-service arrangements, core facilities or laboratories or to provide research services to (or in collaboration with) third parties for a fee, and in industry-sponsored collaborative research projects where any commercial rights are granted to the sponsor.  If End User wishes to use the Software for commercial purposes or for any other restricted purpose, End User must execute a separate license agreement with Harvard.
+
+Requests for use of the Software for or on behalf of for-profit entities or for any commercial purposes, please contact:
+
+Office of Technology Development
+Harvard University
+Smith Campus Center, Suite 727E
+1350 Massachusetts Avenue
+Cambridge, MA 02138 USA
+Telephone: (617) 495-3067
+E-mail: otd@harvard.edu
+
+    3. OWNERSHIP AND COPYRIGHT NOTICE. Harvard owns all intellectual property in the Software. End User shall gain no ownership to the Software. End User shall not remove or delete and shall retain in the Software, in any modifications to Software and in any Derivative Works, the copyright, trademark, or other notices pertaining to Software as provided with the Software.
+
+    4. DERIVATIVE WORKS. End User may create and use Derivative Works, as such term is defined under U.S. copyright laws, provided that any such Derivative Works shall be restricted to non-commercial, internal research and academic use at End User’s Institution.  End User shall not distribute Derivative Works to any third party without the express written consent of Harvard.
+
+    5. FEEDBACK. In order to improve the Software, comments from End Users may be useful. End User agrees to provide Harvard with feedback on the End User’s use of the Software (e.g., any bugs in the Software, the user experience, etc.).  Harvard is permitted to use such information provided by End User in making changes and improvements to the Software without compensation or an accounting to End User.
+
+    6. NON ASSERT. End User acknowledges that Harvard may develop modifications to the Software that may be based on the feedback provided by End User under Section 5 above. Harvard shall not be restricted in any way by End User regarding the use of such information.  End User acknowledges the right of Harvard to prepare, publish, display, reproduce, transmit and or use modifications to the Software that may be substantially similar or functionally equivalent to End User’s modifications and/or improvements if any.  In the event that End User obtains patent protection for any modification or improvement to Software, End User agrees not to allege or enjoin infringement of End User’s patent against Harvard or any of its researchers, medical or research staff, officers, directors and employees.
+
+    7. PUBLICATION & ATTRIBUTION. End User has the right to publish, present, or share results from the use of the Software.  In accordance with customary academic practice, End User will acknowledge Harvard as the provider of the Software and may cite the relevant reference(s) from the following list of publications: N/A
+
+    8. NO WARRANTIES. THE SOFTWARE IS PROVIDED "AS IS." TO THE FULLEST EXTENT PERMITTED BY LAW, HARVARD HEREBY DISCLAIMS ALL WARRANTIES OF ANY KIND (EXPRESS, IMPLIED OR OTHERWISE) REGARDING THE SOFTWARE, INCLUDING BUT NOT LIMITED TO ANY IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, OWNERSHIP, AND NON-INFRINGEMENT.  HARVARD MAKES NO WARRANTY ABOUT THE ACCURACY, RELIABILITY, COMPLETENESS, TIMELINESS, SUFFICIENCY OR QUALITY OF THE SOFTWARE.  HARVARD DOES NOT WARRANT THAT THE SOFTWARE WILL OPERATE WITHOUT ERROR OR INTERRUPTION.
+
+    9. Limitations of Liability and Remedies. USE OF THE SOFTWARE IS AT END USER’S OWN RISK. IF END USER IS DISSATISFIED WITH THE SOFTWARE, ITS EXCLUSIVE REMEDY IS TO STOP USING IT.  IN NO EVENT SHALL HARVARD BE LIABLE TO END USER OR ITS INSTITUTION, IN CONTRACT, TORT OR OTHERWISE, FOR ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, CONSEQUENTIAL, PUNITIVE OR OTHER DAMAGES OF ANY KIND WHATSOEVER ARISING OUT OF OR IN CONNECTION WITH THE SOFTWARE, EVEN IF HARVARD IS NEGLIGENT OR OTHERWISE AT FAULT, AND REGARDLESS OF WHETHER HARVARD IS ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
+
+    10. INDEMNIFICATION. To the extent permitted by law, End User shall indemnify, defend and hold harmless Harvard and its current or future directors, trustees, officers, faculty, medical and professional staff, employees, students and agents and their respective successors, heirs and assigns (the "Indemnitees"), against any liability, damage, loss or expense (including reasonable attorney's fees and expenses of litigation) incurred by or imposed upon the Indemnitees or any one of them in connection with any claims, suits, actions, demands or judgments arising from End User’s breach of this Agreement or its Institution’s use of the Software except to the extent caused by the gross negligence or willful misconduct of Harvard. This indemnification provision shall survive expiration or termination of this Agreement.
+
+    11. GOVERNING LAW. This Agreement shall be construed and governed by the laws of the Commonwealth of Massachusetts regardless of otherwise applicable choice of law standards.
+
+    12. NON-USE OF NAME.  Nothing in this License and Terms of Use shall be construed as granting End Users or their Institutions any rights or licenses to use any trademarks, service marks or logos associated with the Software.  You may not use the terms “Harvard” (or a substantially similar term) in any way that is inconsistent with the permitted uses described herein. You agree not to use any name or emblem of Harvard or any of its subdivisions for any purpose, or to falsely suggest any relationship between End User (or its Institution) and Harvard, or in any manner that would infringe or violate any of Harvard’s rights.
+
+    13. End User represents and warrants that it has the legal authority to enter into this License and Terms of Use on behalf of itself and its Institution.

README.md

@@ -0,0 +1,101 @@
+---
+language: en
+license: other
+license_name: deepethogram-academic-noncommercial
+license_link: LICENSE
+library_name: deepethogram
+tags:
+- deepethogram
+- pytorch
+- optical-flow
+- animal-behavior
+- kinetics
+- pretrained
+---
+
+# DeepEthogram pretrained models
+
+Archived pretrained weights for [DeepEthogram](https://github.com/jbohnslav/deepethogram),
+a pipeline for supervised behavior classification from raw video pixels.
+These weights initialize optical-flow and feature-extractor training on your own behavior dataset.
+They are not ready-to-use classifiers for your behavior labels. No videos, datasets, or trained
+sequence classifiers are included.
+
+## Download
+
+Install the [Hugging Face CLI](https://huggingface.co/docs/huggingface_hub/guides/cli), then download
+into an existing DeepEthogram project's `models` directory:
+
+```bash
+hf download jbohnslav/deepethogram-pretrained --local-dir /path/to/your_project/models
+```
+
+The resulting layout must be `your_project/models/pretrained_models/<run>/...`.
+Preserve the run names and nested `flow`/`spatial` directories. Downloading the full repository also
+includes this card, the license, and `SHA256SUMS` in the destination directory.
+For reproducible downloads, pass `--revision` with a release tag or commit ID.
+
+Verify the model files from that directory:
+
+```bash
+cd /path/to/your_project/models
+shasum -a 256 -c SHA256SUMS
+```
+
+Use the DeepEthogram GUI or training commands to select the pretrained weights. Models retain
+the original PyTorch checkpoint format; use DeepEthogram rather than Transformers to load them.
+
+## Contents
+
+The archive contains 30 files (2,058,618,150 bytes), preserved from the author's NAS copy of
+`niv_revision_deepethogram/models/pretrained_models`. `SHA256SUMS` lists the size-independent
+SHA-256 identity of every archived file. Original checkpoints, YAML hyperparameters, model
+definitions, HDF5 metrics, and TIFF training plots are retained without conversion.
+
+| Run | Component | Architecture | Status |
+| --- | --- | --- | --- |
+| `200221_115158_TinyMotionNet` | Flow generator | TinyMotionNet | Checkpoint present |
+| `200310_174416_MotionNet_kinetics` | Flow generator | MotionNet | Checkpoint present |
+| `200313_125331_TinyMotionNet3D_kinetics` | Flow generator | TinyMotionNet3D | Checkpoint present |
+| `200409_101808_hidden_two_stream_kinetics_degs` | DEG-s feature extractor | ResNet3D-34 | Flow-classifier checkpoint only; incomplete |
+| `200410_142156_hidden_two_stream_kinetics_degm` | DEG-m feature extractor | ResNet50 | Full and separate stream checkpoints present |
+| `200415_125824_hidden_two_stream_kinetics_degf` | DEG-f feature extractor | ResNet18 | Full and separate stream checkpoints present |
+
+## Training and intended use
+
+The historical configuration files identify Kinetics700 as the pretraining dataset and specify
+700 classes for feature extractors. The three flow models provide motion estimates; feature
+extractors combine appearance and motion. Fine-tune on your own labeled videos, then train a
+sequence model to classify your behaviors. Keep training, validation, and test videos separate.
+
+Historical hyperparameters describe the original training environment and contain old filesystem
+paths and YAML serialization tags. They are provenance records, not portable project configs.
+The archived `.pt` files use legacy PyTorch serialization.
+
+## Known limitations
+
+- The DEG-s folder has `flow/checkpoint.pt` but no top-level checkpoint or spatial checkpoint.
+  DeepEthogram's current model discovery skips this incomplete feature extractor. This release
+  provides three discoverable flow generators and the DEG-m/DEG-f feature extractors.
+- DEG-f has no `classification_metrics.h5`; the legacy folders use `hyperparameters.yaml`,
+  rather than `config.yaml`. Some inference helpers require newer run files. Use this bundle
+  for pretraining initialization and use the new run produced by fine-tuning for inference.
+- No task-specific behavior class names, thresholds, or sequence model are supplied.
+- The publication's behavior-classification results describe trained pipelines and datasets;
+  they are not benchmark scores for this archive alone.
+- This is a NAS-sourced archive. Byte-for-byte equivalence with the historical Google Drive ZIP
+  has not been established.
+
+## License and citation
+
+The accompanying [LICENSE](LICENSE) reproduces the DeepEthogram repository's Harvard
+Academic and Non-Commercial Research Use Software License and Terms of Use unchanged.
+It restricts commercial use and end-user redistribution. This mirror does not grant additional
+permissions or relicense the original assets. Commercial licensing inquiries should go to the
+Harvard Office of Technology Development as described in that license.
+
+Please cite:
+
+Bohnslav et al. (2021). *DeepEthogram, a machine learning pipeline for supervised behavior
+classification from raw pixels*. eLife 10:e63377.
+[doi:10.7554/eLife.63377](https://doi.org/10.7554/eLife.63377).

SHA256SUMS

@@ -0,0 +1,30 @@
+9940cc4db1b9730a6b8dd3554eb9a0b23aac1f7db1e9c1c34a29020d09e90910  pretrained_models/200221_115158_TinyMotionNet/TinyMotionNet_definition.pt
+07d8617e5ee84bc1bbeac57d3a6844595d471b8446f44f3f0cd626c30907eeb4  pretrained_models/200221_115158_TinyMotionNet/checkpoint.pt
+ca9dc207f8771c79e3c54f257fea095389eb63be3b9e510e769e5a695ba65acb  pretrained_models/200221_115158_TinyMotionNet/hyperparameters.yaml
+10eec7c0444c277566c135038e82a161f24220822ac23e7085ff00baf2597347  pretrained_models/200221_115158_TinyMotionNet/opticalflow_metrics.h5
+f05abfa77fecbe775a5986504859330a9b9b063628c48a0782c9ef27b0b399ff  pretrained_models/200221_115158_TinyMotionNet/opticalflow_metrics.tiff
+4a7e5ea029ae836cf7831469b2e6f78d23ebeb1426b001c17f96546f443b3de4  pretrained_models/200310_174416_MotionNet_kinetics/MotionNet_definition.pt
+c75e175724ae04a94fc622cfe8949e63656a60639556b65f8d640eb2944a511a  pretrained_models/200310_174416_MotionNet_kinetics/checkpoint.pt
+fc8f58e37e37dccc2f6bddb0ad8ce1b39b0d448d78048adedf8a60b32f6668eb  pretrained_models/200310_174416_MotionNet_kinetics/hyperparameters.yaml
+606e55cc6b2da9336ef664b2dda3715af56fc6e32751e0fe2f25f40bd60b706a  pretrained_models/200310_174416_MotionNet_kinetics/opticalflow_metrics.h5
+ee83903a80888664e6d15bcf19f0de31e2319c09dc8ad419dc6df67460dbba1e  pretrained_models/200310_174416_MotionNet_kinetics/opticalflow_metrics.tiff
+ee83ba63405e3e832e024ad034c90853ab4b9ccc2c954801d9c0197f6a8c38be  pretrained_models/200313_125331_TinyMotionNet3D_kinetics/TinyMotionNet3D_definition.pt
+6d84b4bc9536438f6687b75a9883f265b9a138365547fd06168790231662ad00  pretrained_models/200313_125331_TinyMotionNet3D_kinetics/checkpoint.pt
+73041516074c0c5edf51e837361775941d3c1c902852bf82415ec6499e7c6f12  pretrained_models/200313_125331_TinyMotionNet3D_kinetics/hyperparameters.yaml
+59943e49341281327f7f757bba5dcd2a392f3e60522234a1f284176dce051a11  pretrained_models/200313_125331_TinyMotionNet3D_kinetics/opticalflow_metrics.h5
+bab3c5aa9a7d0de262955979b2c8eb15608b1200ff6ec369a6328e1215362656  pretrained_models/200313_125331_TinyMotionNet3D_kinetics/opticalflow_metrics.tiff
+b27204bdbe3c6406126854e76c40ef013c90a12059a6a0598e57544df20e7c59  pretrained_models/200409_101808_hidden_two_stream_kinetics_degs/classification_metrics.h5
+6228e911b4d7e8eb1a5c0cb19fe211bf373269b34e050c3ff2861661646c0c96  pretrained_models/200409_101808_hidden_two_stream_kinetics_degs/classification_metrics.tiff
+ac5cc3886237e8a8c39996810aaf7cdd0d66fd2000cf139b931172edfea0f4da  pretrained_models/200409_101808_hidden_two_stream_kinetics_degs/flow/checkpoint.pt
+8d37f2e97b07a2bbb796525e1fdcccee5820f3b636e970a51b14256dc6345645  pretrained_models/200409_101808_hidden_two_stream_kinetics_degs/hyperparameters.yaml
+c0dfbe2fe4e930265da2aec6bc20093bed96de7fffc828ac8cb9295640e2e665  pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/checkpoint.pt
+1add6cfbd87a08977b470af17a00fd0bc7fe5a90784fb2d0752bf017a5b79109  pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/classification_metrics.h5
+55382efcdb11160d13736cc2d7120485528abc75c3d4d2f1014362ed2fb7d3d1  pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/classification_metrics.tiff
+ad8047b45cd94aa3b9e67b3c1e80b79d8b7f96725eff65d87bcb8118d8b269f9  pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/flow/checkpoint.pt
+a696a03829cc7ec7790d4bc5ceacf1a70d8aee49a0ba9a360a51078bb489b3ca  pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/hyperparameters.yaml
+b39e09235ebfa2d51dc12d650df8813e8084d4e836b7de8c486d1eee2e23d7c1  pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/spatial/checkpoint.pt
+9dae6071064c461d2e29460e611254380135de6c7b8f62374c25f0344b140349  pretrained_models/200415_125824_hidden_two_stream_kinetics_degf/checkpoint.pt
+7efa87c07bec7709cc78d81edfb8359b812901ac1b76a4bb8ebaf8518383b816  pretrained_models/200415_125824_hidden_two_stream_kinetics_degf/classification_metrics.tiff
+eb20d8a5223e7b5f6f5a2e0aebaf1020f56dc7654ae97f6d6a524cd473a9421a  pretrained_models/200415_125824_hidden_two_stream_kinetics_degf/flow/checkpoint.pt
+a8fc5b01fe3ec87e2d329a391cae925bd225a06649bc5a3c450dae60621cfba7  pretrained_models/200415_125824_hidden_two_stream_kinetics_degf/hyperparameters.yaml
+df093808e0d75f1095105a1b53659073009dc6115c93cc6764dac5269b62e361  pretrained_models/200415_125824_hidden_two_stream_kinetics_degf/spatial/checkpoint.pt

pretrained_models/200221_115158_TinyMotionNet/TinyMotionNet_definition.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9940cc4db1b9730a6b8dd3554eb9a0b23aac1f7db1e9c1c34a29020d09e90910
+size 7854482

pretrained_models/200221_115158_TinyMotionNet/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d8617e5ee84bc1bbeac57d3a6844595d471b8446f44f3f0cd626c30907eeb4
+size 23450307

pretrained_models/200221_115158_TinyMotionNet/hyperparameters.yaml

@@ -0,0 +1,154 @@
+LR: 0.5
+UD: 0.0
+batch_size: 32
+brightness: 0.25
+classifier: resnet18
+config_file: null
+contrast: 0.1
+crop_size: !!python/tuple
+- 256
+- 256
+data_dir: /mnt/VIDEOS2/kinetics700
+dataset: kinetics
+degrees: 10
+distributed: false
+early_stopping_begins: null
+final_activation: softmax
+flow_generator: TinyMotionNet
+flow_loss: MotionNet
+flow_max: 10
+fp16: false
+gpu_id: 1
+input_images: 11
+inputs: rgb
+kinetics: true
+lr: 0.0001
+milestones:
+- 50
+- 100
+- 150
+- 200
+- 250
+- 300
+min_lr: 5.0e-07
+model: flow_generator
+model_dir: models
+name: kinetics
+normalization:
+  flow:
+    N: 2097152000000
+    mean: null
+    std: null
+  rgb:
+    N: 209715200000
+    mean:
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    std:
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+notes: halfsize_fromscratch
+num_epochs: 1000
+num_flows: null
+num_rgb: 11
+num_workers: 8
+pad: null
+patience: 10
+preset: null
+project_dir: null
+random_resize: false
+reduction_factor: !!python/object/apply:numpy.core.multiarray.scalar
+- !!python/object/apply:numpy.dtype
+  args:
+  - f8
+  - 0
+  - 1
+  state: !!python/tuple
+  - 3
+  - <
+  - null
+  - null
+  - null
+  - -1
+  - -1
+  - 0
+- !!binary |
+  D0lIYhM91D8=
+reload_split: true
+resize: null
+scheduler: plateau
+should_overwrite_args: false
+should_viz: true
+splitfile: null
+steps_per_epoch: 1000
+steps_per_test_epoch: 20
+steps_per_validation_epoch: 1000
+stopping_type: plateau
+train_val_test_split:
+- 0.8
+- 0.2
+- 0.0
+weight_loss: true
+weights: null

pretrained_models/200221_115158_TinyMotionNet/opticalflow_metrics.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10eec7c0444c277566c135038e82a161f24220822ac23e7085ff00baf2597347
+size 160464

pretrained_models/200310_174416_MotionNet_kinetics/MotionNet_definition.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a7e5ea029ae836cf7831469b2e6f78d23ebeb1426b001c17f96546f443b3de4
+size 183651015

pretrained_models/200310_174416_MotionNet_kinetics/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c75e175724ae04a94fc622cfe8949e63656a60639556b65f8d640eb2944a511a
+size 183604611

pretrained_models/200310_174416_MotionNet_kinetics/hyperparameters.yaml

@@ -0,0 +1,94 @@
+LR: 0.5
+UD: 0.0
+batch_size: 16
+brightness: 0.25
+classifier: resnet18
+config_file: null
+contrast: 0.1
+crop_size: !!python/tuple
+- 256
+- 256
+dali: true
+data_dir: /media/jim/FASTER/kinetics700
+dataset: kinetics
+degrees: 10
+distributed: false
+early_stopping_begins: null
+final_activation: softmax
+flow_generator: MotionNet
+flow_loss: MotionNet
+flow_max: 5
+fp16: false
+gpu_id: 1
+input_images: 11
+inputs: rgb
+lr: 0.0001
+milestones:
+- 50
+- 100
+- 150
+- 200
+- 250
+- 300
+min_lr: 5.0e-07
+model: flow_generator
+model_dir: models
+name: kinetics
+normalization:
+  flow:
+    N: 2097152000000
+    mean: null
+    std: null
+  rgb:
+    N: 209715200000
+    mean:
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    std:
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+notes: dali_only_3_resolutions
+num_epochs: 1000
+num_flows: null
+num_rgb: 11
+num_workers: 8
+pad: null
+patience: 10
+preset: null
+project_dir: null
+random_resize: false
+reduction_factor: !!python/object/apply:numpy.core.multiarray.scalar
+- !!python/object/apply:numpy.dtype
+  args:
+  - f8
+  - 0
+  - 1
+  state: !!python/tuple
+  - 3
+  - <
+  - null
+  - null
+  - null
+  - -1
+  - -1
+  - 0
+- !!binary |
+  D0lIYhM91D8=
+reload_split: true
+resize: null
+scheduler: plateau
+should_overwrite_args: false
+should_viz: true
+splitfile: null
+steps_per_epoch: 1000
+steps_per_test_epoch: 20
+steps_per_validation_epoch: 1000
+stopping_type: plateau
+train_val_test_split:
+- 0.8
+- 0.2
+- 0.0
+weight_loss: true
+weights: null

pretrained_models/200310_174416_MotionNet_kinetics/opticalflow_metrics.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606e55cc6b2da9336ef664b2dda3715af56fc6e32751e0fe2f25f40bd60b706a
+size 160456

pretrained_models/200313_125331_TinyMotionNet3D_kinetics/TinyMotionNet3D_definition.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee83ba63405e3e832e024ad034c90853ab4b9ccc2c954801d9c0197f6a8c38be
+size 1802648

pretrained_models/200313_125331_TinyMotionNet3D_kinetics/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d84b4bc9536438f6687b75a9883f265b9a138365547fd06168790231662ad00
+size 1769548

pretrained_models/200313_125331_TinyMotionNet3D_kinetics/hyperparameters.yaml

@@ -0,0 +1,94 @@
+LR: 0.5
+UD: 0.0
+batch_size: 32
+brightness: 0.25
+classifier: resnet18
+config_file: null
+contrast: 0.1
+crop_size: !!python/tuple
+- 256
+- 256
+dali: true
+data_dir: /media/jim/FASTER/kinetics700
+dataset: kinetics
+degrees: 10
+distributed: false
+early_stopping_begins: null
+final_activation: softmax
+flow_generator: TinyMotionNet3D
+flow_loss: MotionNet
+flow_max: 10
+fp16: false
+gpu_id: 0
+input_images: 11
+inputs: rgb
+lr: 0.0001
+milestones:
+- 50
+- 100
+- 150
+- 200
+- 250
+- 300
+min_lr: 5.0e-07
+model: flow_generator
+model_dir: models
+name: kinetics
+normalization:
+  flow:
+    N: 2097152000000
+    mean: null
+    std: null
+  rgb:
+    N: 209715200000
+    mean:
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    std:
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+notes: ''
+num_epochs: 1000
+num_flows: null
+num_rgb: 11
+num_workers: 8
+pad: null
+patience: 10
+preset: null
+project_dir: null
+random_resize: false
+reduction_factor: !!python/object/apply:numpy.core.multiarray.scalar
+- !!python/object/apply:numpy.dtype
+  args:
+  - f8
+  - 0
+  - 1
+  state: !!python/tuple
+  - 3
+  - <
+  - null
+  - null
+  - null
+  - -1
+  - -1
+  - 0
+- !!binary |
+  D0lIYhM91D8=
+reload_split: true
+resize: null
+scheduler: plateau
+should_overwrite_args: false
+should_viz: true
+splitfile: null
+steps_per_epoch: 1000
+steps_per_test_epoch: 20
+steps_per_validation_epoch: 1000
+stopping_type: plateau
+train_val_test_split:
+- 0.8
+- 0.2
+- 0.0
+weight_loss: true
+weights: /home/jim/models/200310_180439_TinyMotionNet3D_kinetics_dali_3d/checkpoint.pt

pretrained_models/200313_125331_TinyMotionNet3D_kinetics/opticalflow_metrics.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59943e49341281327f7f757bba5dcd2a392f3e60522234a1f284176dce051a11
+size 160456

pretrained_models/200409_101808_hidden_two_stream_kinetics_degs/classification_metrics.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b27204bdbe3c6406126854e76c40ef013c90a12059a6a0598e57544df20e7c59
+size 148424

pretrained_models/200409_101808_hidden_two_stream_kinetics_degs/flow/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac5cc3886237e8a8c39996810aaf7cdd0d66fd2000cf139b931172edfea0f4da
+size 255513329

pretrained_models/200409_101808_hidden_two_stream_kinetics_degs/hyperparameters.yaml

@@ -0,0 +1,106 @@
+LR: 0.5
+UD: 0.0
+arch: hidden_two_stream
+background_weight: 1.0
+batch_size: 48
+brightness: 0.25
+classifier: resnet3d_34
+config_file: null
+contrast: 0.1
+crop_size: !!python/tuple
+- 224
+- 224
+curriculum: true
+dali: true
+data_dir: /media/jim/FASTER/kinetics700
+dataset: kinetics
+degrees: 10
+distributed: true
+dropout_p: 0
+early_stopping_begins: null
+final_activation: softmax
+flow_generator: TinyMotionNet3D
+flow_loss: MotionNet
+flow_max: 10
+flow_style: polar
+fp16: false
+fusion: average
+gpu_id: 0
+input_images: 11
+inputs: rgb
+lr: 0.0001
+milestones:
+- 50
+- 100
+- 150
+- 200
+- 250
+- 300
+min_lr: 5.0e-07
+model: feature_extractor
+model_dir: models
+name: kinetics
+normalization:
+  flow:
+    N: 2097152000000
+    mean: null
+    std: null
+  rgb:
+    N: 209715200000
+    mean:
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    std:
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+notes: degs_224_dali_nodropout_weightdecay
+num_classes: 700
+num_epochs: 1000
+num_flows: 10
+num_rgb: 11
+num_workers: 2
+pad: null
+patience: 10
+pos_weight: null
+preset: null
+project_dir: null
+random_resize: false
+reduction_factor: !!python/object/apply:numpy.core.multiarray.scalar
+- !!python/object/apply:numpy.dtype
+  args:
+  - f8
+  - 0
+  - 1
+  state: !!python/tuple
+  - 3
+  - <
+  - null
+  - null
+  - null
+  - -1
+  - -1
+  - 0
+- !!binary |
+  D0lIYhM91D8=
+reload_split: true
+resize: null
+sampler: null
+sampling_ratio: null
+scheduler: plateau
+should_overwrite_args: false
+should_viz: true
+spatial_only: true
+splitfile: null
+steps_per_epoch: 1000
+steps_per_test_epoch: 20
+steps_per_validation_epoch: 1000
+stopping_type: plateau
+train_val_test_split:
+- 0.8
+- 0.2
+- 0.0
+weight_decay: 0.0001
+weight_loss: false
+weights: null

pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0dfbe2fe4e930265da2aec6bc20093bed96de7fffc828ac8cb9295640e2e665
+size 383713235

pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/classification_metrics.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1add6cfbd87a08977b470af17a00fd0bc7fe5a90784fb2d0752bf017a5b79109
+size 148424

pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/flow/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8047b45cd94aa3b9e67b3c1e80b79d8b7f96725eff65d87bcb8118d8b269f9
+size 100151960

pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/hyperparameters.yaml

@@ -0,0 +1,106 @@
+LR: 0.5
+UD: 0.0
+arch: hidden_two_stream
+background_weight: 1.0
+batch_size: 24
+brightness: 0.25
+classifier: resnet50
+config_file: null
+contrast: 0.1
+crop_size: !!python/tuple
+- 224
+- 224
+curriculum: true
+dali: true
+data_dir: /media/jim/FASTER/kinetics700
+dataset: kinetics
+degrees: 10
+distributed: true
+dropout_p: 0
+early_stopping_begins: null
+final_activation: softmax
+flow_generator: MotionNet
+flow_loss: MotionNet
+flow_max: 10
+flow_style: polar
+fp16: false
+fusion: average
+gpu_id: 1
+input_images: 11
+inputs: rgb
+lr: 0.0001
+milestones:
+- 50
+- 100
+- 150
+- 200
+- 250
+- 300
+min_lr: 5.0e-07
+model: feature_extractor
+model_dir: models
+name: kinetics
+normalization:
+  flow:
+    N: 2097152000000
+    mean: null
+    std: null
+  rgb:
+    N: 209715200000
+    mean:
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    std:
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+notes: degm_224_nodropout_weightdecay
+num_classes: 700
+num_epochs: 1000
+num_flows: 10
+num_rgb: 1
+num_workers: 2
+pad: null
+patience: 10
+pos_weight: null
+preset: null
+project_dir: null
+random_resize: false
+reduction_factor: !!python/object/apply:numpy.core.multiarray.scalar
+- !!python/object/apply:numpy.dtype
+  args:
+  - f8
+  - 0
+  - 1
+  state: !!python/tuple
+  - 3
+  - <
+  - null
+  - null
+  - null
+  - -1
+  - -1
+  - 0
+- !!binary |
+  D0lIYhM91D8=
+reload_split: true
+resize: null
+sampler: null
+sampling_ratio: null
+scheduler: plateau
+should_overwrite_args: false
+should_viz: true
+spatial_only: true
+splitfile: null
+steps_per_epoch: 1000
+steps_per_test_epoch: 20
+steps_per_validation_epoch: 1000
+stopping_type: plateau
+train_val_test_split:
+- 0.8
+- 0.2
+- 0.0
+weight_decay: 0.0001
+weight_loss: false
+weights: null

pretrained_models/200410_142156_hidden_two_stream_kinetics_degm/spatial/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39e09235ebfa2d51dc12d650df8813e8084d4e836b7de8c486d1eee2e23d7c1
+size 99938710

pretrained_models/200415_125824_hidden_two_stream_kinetics_degf/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dae6071064c461d2e29460e611254380135de6c7b8f62374c25f0344b140349
+size 100453714

pretrained_models/200415_125824_hidden_two_stream_kinetics_degf/flow/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb20d8a5223e7b5f6f5a2e0aebaf1020f56dc7654ae97f6d6a524cd473a9421a
+size 46418827

pretrained_models/200415_125824_hidden_two_stream_kinetics_degf/hyperparameters.yaml

@@ -0,0 +1,106 @@
+LR: 0.5
+UD: 0.0
+arch: hidden_two_stream
+background_weight: 1.0
+batch_size: 32
+brightness: 0.25
+classifier: resnet18
+config_file: null
+contrast: 0.1
+crop_size: !!python/tuple
+- 224
+- 224
+curriculum: true
+dali: true
+data_dir: /media/jim/FASTER/kinetics700
+dataset: kinetics
+degrees: 10
+distributed: true
+dropout_p: 0
+early_stopping_begins: null
+final_activation: softmax
+flow_generator: TinyMotionNet
+flow_loss: MotionNet
+flow_max: 10
+flow_style: polar
+fp16: false
+fusion: average
+gpu_id: 1
+input_images: 11
+inputs: rgb
+lr: 0.0001
+milestones:
+- 50
+- 100
+- 150
+- 200
+- 250
+- 300
+min_lr: 5.0e-07
+model: feature_extractor
+model_dir: models
+name: kinetics
+normalization:
+  flow:
+    N: 2097152000000
+    mean: null
+    std: null
+  rgb:
+    N: 209715200000
+    mean:
+    - 0.4345759153366089
+    - 0.39914101362228394
+    - 0.37257176637649536
+    std:
+    - 0.2809292674064636
+    - 0.27423909306526184
+    - 0.27391594648361206
+notes: degf_224_nodropout_weightdecay
+num_classes: 700
+num_epochs: 1000
+num_flows: 10
+num_rgb: 1
+num_workers: 2
+pad: null
+patience: 10
+pos_weight: null
+preset: null
+project_dir: null
+random_resize: false
+reduction_factor: !!python/object/apply:numpy.core.multiarray.scalar
+- !!python/object/apply:numpy.dtype
+  args:
+  - f8
+  - 0
+  - 1
+  state: !!python/tuple
+  - 3
+  - <
+  - null
+  - null
+  - null
+  - -1
+  - -1
+  - 0
+- !!binary |
+  D0lIYhM91D8=
+reload_split: true
+resize: null
+sampler: null
+sampling_ratio: null
+scheduler: plateau
+should_overwrite_args: false
+should_viz: true
+spatial_only: true
+splitfile: null
+steps_per_epoch: 1000
+steps_per_test_epoch: 20
+steps_per_validation_epoch: 1000
+stopping_type: plateau
+train_val_test_split:
+- 0.8
+- 0.2
+- 0.0
+weight_decay: 0.0001
+weight_loss: false
+weights: null

pretrained_models/200415_125824_hidden_two_stream_kinetics_degf/spatial/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df093808e0d75f1095105a1b53659073009dc6115c93cc6764dac5269b62e361
+size 46205577