talksik/mediapipe
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 0ac604d507 Add timestamp aggregation to EmbeddingPostprocessingGraph. MediaPipe Team 2022-11-10 01:19:00 -08:00
  • f11c757629 Update C++ HandLandmarksDetectionResult to HandLandmarkerResult. MediaPipe Team 2022-11-09 23:18:02 -08:00
  • d2142e86a9 Metadata Writer: Add Bert metadata writer in Text Classifier. Yuqi Li 2022-11-09 14:51:46 -08:00
  • 116b4bb6c4 Internal change MediaPipe Team 2022-11-09 13:55:45 -08:00
  • 7066ee231e Hand Landmarker Java API and unit test. MediaPipe Team 2022-11-09 11:53:37 -08:00
  • 7ec0d8cf3b Added tolerance for vector coordinate values in embeddings kinaryml 2022-11-09 11:53:30 -08:00
  • 6f66a7fde4 Rename GestureRecognitionResult to GestureRecognizerResult. Jiuqiang Tang 2022-11-09 11:47:35 -08:00
  • 17bb174444 Refactored embeddings to embedding_result kinaryml 2022-11-09 11:42:32 -08:00
  • 4e568a1c3d Expose HandLandmarker API in PyPI packages. Jiuqiang Tang 2022-11-09 11:04:46 -08:00
  • 84895316d2 Add pre-compiled WASM files to NPM packages Sebastian Schmidt 2022-11-09 10:26:25 -08:00
  • 0a5534204f Merge pull request #3829 from kinaryml:hand-landmarker-python Copybara-Service 2022-11-09 10:23:38 -08:00
  • dc30cf9732 Updated embeddings container to use a timestamp and made parameters - head_index,head_name optional kinaryml 2022-11-08 23:51:55 -08:00
  • d327b3649d Fixed some typos in methods and comments kinaryml 2022-11-08 23:47:58 -08:00
  • dd6fdedd5f Added some sanity tests kinaryml 2022-11-08 23:15:58 -08:00
  • 36c50ff8f3 Merge branch 'google:master' into image-embedder-python Kinar R 2022-11-09 12:41:55 +05:30
  • 7e251bc6b6 Merge branch 'hand-landmarker-python' of https://github.com/kinaryml/mediapipe into hand-landmarker-python kinaryml 2022-11-08 23:07:30 -08:00
  • 812fa2cc70 Merge branch 'google:master' into hand-landmarker-python Kinar R 2022-11-09 12:37:06 +05:30
  • 46f135e54d Renamed HandLandmarksDetectionResult to HandLandmarkerResult kinaryml 2022-11-08 23:06:28 -08:00
  • b4e1833dd0 Internal change MediaPipe Team 2022-11-08 20:34:23 -08:00
  • a5bcb97d88 Adds an AverageWordVecModel. MediaPipe Team 2022-11-08 18:27:53 -08:00
  • c31aaa94a6 Adds a BertClassifier. MediaPipe Team 2022-11-08 16:47:48 -08:00
  • 669d539551 NPM package definitions for MediaPipe Tasks Sebastian Schmidt 2022-11-08 15:44:35 -08:00
  • 253ff0f85c Update the Java doc for model asset for BaseOptions Lu Wang 2022-11-08 14:54:10 -08:00
  • 0917e8cb8e Support continual training image classifier from saved checkpoint files. MediaPipe Team 2022-11-08 14:47:19 -08:00
  • b3d19fa1af Use model bundle writer when exporting models in gesture recognizer MediaPipe Team 2022-11-08 13:50:28 -08:00
  • 0363d60511 Open-sources TextEmbedder. MediaPipe Team 2022-11-08 13:46:50 -08:00
  • 37930609ff Update landmark_detection_result.py Kinar R 2022-11-09 02:58:38 +05:30
  • ace098f370 Add proper Cast for MultiPort MediaPipe Team 2022-11-08 11:55:04 -08:00
  • 96e2eb38c7 Merge branch 'hand-landmarker-python' of https://github.com/kinaryml/mediapipe into hand-landmarker-python kinaryml 2022-11-08 11:27:13 -08:00
  • 77cc4c53ab Updated the 'test_create_from_options_fails_with_invalid_model_path' test case kinaryml 2022-11-08 11:26:02 -08:00
  • 6dd6d8921f Merge branch 'google:master' into hand-landmarker-python Kinar R 2022-11-09 00:52:20 +05:30
  • 7a1e55b872 Adds unit tests for TextEmbedder. MediaPipe Team 2022-11-08 10:59:38 -08:00
  • 72f08c6878 Used loops instead of list comprehension kinaryml 2022-11-08 10:57:12 -08:00
  • 647b94240d Updated docstring kinaryml 2022-11-08 10:54:44 -08:00
  • ff6ca706c6 Internal change Jiuqiang Tang 2022-11-08 10:50:42 -08:00
  • 88ab9d4922 Used loops instead of complex list comprehensions kinaryml 2022-11-08 10:52:26 -08:00
  • c0265ca2ac Fixed some typos kinaryml 2022-11-08 10:44:21 -08:00
  • e8d771baf3 Updated landmark_detection_result kinaryml 2022-11-08 10:37:37 -08:00
  • 5c8b95666a Update "test_create_from_options_fails_with_invalid_model_path" of all tasks python api tests. Jiuqiang Tang 2022-11-08 10:34:15 -08:00
  • 0fd78c2ec6 Updated classifier python tasks to use the new classification_result dataclass kinaryml 2022-11-08 10:28:24 -08:00
  • 5e6842aa5c Migrate Java ImageClassifier / TextClassifier to new result format. MediaPipe Team 2022-11-08 09:44:15 -08:00
  • 26066787b3 Allow Web developers to opt into CPU or GPU processing Sebastian Schmidt 2022-11-08 06:35:43 -08:00
  • 9c9519eeb8 Fixed a to_pb2() bug in the landmark_detection_result container kinaryml 2022-11-08 02:55:19 -08:00
  • 0402ee383f Added hand landmarker Python API and tests kinaryml 2022-11-08 01:05:36 -08:00
  • 4a6562d423 internal MediaPipe Team 2022-11-07 22:35:30 -08:00
  • 24d03451c7 Internal change - migration MediaPipe Team 2022-11-07 22:34:41 -08:00
  • 0a08e4768b Metadata Writer: Add metadata writer for Text Classifier. Yuqi Li 2022-11-07 21:24:19 -08:00
  • b14178d305 Temporarily exclude "audio_classifier_graph" from "builtin_task_graphs" on Windows. Jiuqiang Tang 2022-11-07 17:25:13 -08:00
  • 716c7e3b8a Internal change MediaPipe Team 2022-11-07 17:21:51 -08:00
  • c3bb4bb5da Refactor image classifier Create API by defining an ImageClassifierOption which wraps the model_spec, model_options, and hparams. Also migrate the definition of HParams by extending it from BaseHParams. MediaPipe Team 2022-11-07 16:37:40 -08:00
  • 1049ef781d Add image_segmenter namespace and update image segmenter proto for java package. MediaPipe Team 2022-11-07 16:17:25 -08:00
  • 1a151d9ffb Internal change Camillo Lugaresi 2022-11-07 16:17:13 -08:00
  • 6f38a7a21f Add hand landmarker C++ api. MediaPipe Team 2022-11-07 16:15:54 -08:00
  • 83608d4670 Merge branch 'master' into image-embedder-python Kinar R 2022-11-08 05:02:46 +05:30
  • 571c0b1fef Expose MediaPipe Tasks Audio and Text APIs in MediaPipe PyPI packages. Jiuqiang Tang 2022-11-07 15:15:58 -08:00
  • 63a759accc Implement MediaPipe AudioClassifier Tasks Python API. Adjust the AudioClassifier Tasks C++ API to remove "sample_rate" from its options. Jiuqiang Tang 2022-11-07 14:26:21 -08:00
  • 51dbd9779c Introduce Stream/SidePacket aliases for Source/SideSource MediaPipe Team 2022-11-07 14:16:29 -08:00
  • e994efd40f Add entry points for NPM packages Sebastian Schmidt 2022-11-07 14:12:58 -08:00
  • 664d9c49e7 Revised image embedder implementation kinaryml 2022-11-07 13:59:07 -08:00
  • ba1ee5b404 Merge branch 'master' into image-embedder-python Kinar R 2022-11-08 02:53:20 +05:30
  • 6b54cae34c Internal change - cleanup MediaPipe Team 2022-11-07 11:40:43 -08:00
  • 2371051e17 Open Source the remaining Web implementation files Sebastian Schmidt 2022-11-07 10:33:12 -08:00
  • c02f3933d4 Temporarily exclude "text_classifier_graph" from "builtin_task_graphs" on Windows. Jiuqiang Tang 2022-11-07 10:26:19 -08:00
  • 9f4496db77 Fix typos Jiuqiang Tang 2022-11-07 10:22:49 -08:00
  • 17a2de8cf7 Rename TextClassificationResult to TextClassifierResult. Jiuqiang Tang 2022-11-07 09:37:03 -08:00
  • 4c06303ec7 Merge pull request #3820 from kinaryml:text-classifier-python Copybara-Service 2022-11-06 22:15:09 -08:00
  • 4b0423e3a2 Internal change MediaPipe Team 2022-11-06 19:32:48 -08:00
  • 9504c5e6a1 Add a create_from_array classmethod to the AudioData class. Jiuqiang Tang 2022-11-05 00:07:43 -07:00
  • b44c49250b Removed unused constant kinaryml 2022-11-04 22:36:13 -07:00
  • 740d2e47b5 Merge branch 'google:master' into text-classifier-python Kinar R 2022-11-05 11:03:24 +05:30
  • 91782a2772 Internal change Hadon Nash 2022-11-04 19:45:46 -07:00
  • 416f91180b Remove the use of designated initializers. Jiuqiang Tang 2022-11-04 16:55:26 -07:00
  • 35f635d8ff Add an argument to packet_creator.create_matrix to allow the input matrix to be transposed first. Jiuqiang Tang 2022-11-04 16:37:14 -07:00
  • c10ebe8476 Remove the use of designated initializers. Jiuqiang Tang 2022-11-04 13:21:40 -07:00
  • b1d1ef0124 Merge branch 'google:master' into image-embedder-python Kinar R 2022-11-05 00:17:26 +05:30
  • 5e1a2fcdbb Update EmbeddingResult format and dependent tasks. MediaPipe Team 2022-11-04 11:18:27 -07:00
  • 66e591d4bc Remove the use of designated initializers. Jiuqiang Tang 2022-11-04 11:13:30 -07:00
  • f05868d8e0 Set up the Open Source build for MediaPipe Tasks Web Sebastian Schmidt 2022-11-04 10:57:26 -07:00
  • 5fd3701cfd Expose ImageSegmenter and GestureRecognizer APIs in PyPI packages. Jiuqiang Tang 2022-11-04 10:37:52 -07:00
  • 57759aedaf Enable using tasks metadata components in MediaPipe PyPI packages. Jiuqiang Tang 2022-11-04 09:45:33 -07:00
  • 8b2c937b9e Migrate AudioClassifier C++ to use new ClassificationResult struct. MediaPipe Team 2022-11-04 09:44:07 -07:00
  • 93a587a422 Make the python documentation clear to resolve https://github.com/google/mediapipe/issues/3805. Jiuqiang Tang 2022-11-04 08:44:10 -07:00
  • 62cd67e996 Internal change MediaPipe Team 2022-11-04 08:36:31 -07:00
  • 5f5f50d8f7 Implement MediaPipe Tasks Python AudioData. Jiuqiang Tang 2022-11-04 08:30:30 -07:00
  • 5024c815f1 Merge pull request #3813 from kinaryml:image-segmenter-minor-fixes Copybara-Service 2022-11-03 21:41:37 -07:00
  • b2cc2cc60c Internal changes MediaPipe Team 2022-11-03 17:21:24 -07:00
  • 06cb73fc81 Modified internal dependencies. MediaPipe Team 2022-11-03 15:42:59 -07:00
  • e2d50745ac Revised image embedder implementation kinaryml 2022-11-03 14:30:21 -07:00
  • d29c3d7512 Add metadata writer to image_classifier in model_maker MediaPipe Team 2022-11-03 11:28:56 -07:00
  • 492607152a Reverted changes to rect kinaryml 2022-11-03 10:56:38 -07:00
  • 5a68ba84b6 Merge branch 'master' into image-embedder-python Kinar R 2022-11-03 23:24:31 +05:30
  • b472d8ff66 Add the missing __init__.py file. Jiuqiang Tang 2022-11-03 09:22:35 -07:00
  • 716e59f90c Merge pull request #3801 from kinaryml:gesture-recognizer-python Copybara-Service 2022-11-03 08:52:17 -07:00
  • 14e18a03d6 Removed unused custom classifier options in tests kinaryml 2022-11-03 02:54:57 -07:00
  • de619e2702 Removed a comment kinaryml 2022-11-03 02:33:50 -07:00
  • 2001e2b77c Removed unused file kinaryml 2022-11-03 02:32:55 -07:00
  • 6e9a070dd1 Added text classifier implementation and tests kinaryml 2022-11-03 02:29:40 -07:00
  • 35a04522fa Moved the OutputType and Activation classes to ImageSegmenter's inner classes kinaryml 2022-11-03 00:46:00 -07:00
  • ddf37d014e Fix test utils bug when two file names have same ending. MediaPipe Team 2022-11-02 22:30:37 -07:00
  • 1b5da09a92 Install node and npm on Docker as a prerequisite to open sourcing the Web files Sebastian Schmidt 2022-11-02 16:42:36 -07:00