MediaPipe Team
|
ad4ae6559b
|
Add an extra op to rescale face stylizer generation output from [-1, 1] to [0, 1].
This conversion is to support running the model on both GPU and CPU.
PiperOrigin-RevId: 528400297
|
2023-04-30 23:14:29 -07:00 |
|
MediaPipe Team
|
c450283715
|
Add a filegroup for referencing model.
PiperOrigin-RevId: 528251316
|
2023-04-30 01:19:19 -07:00 |
|
MediaPipe Team
|
cf22c97143
|
Add the TFLite conversion API to BlazeFaceStylizer in model maker.
PiperOrigin-RevId: 527806005
|
2023-04-28 00:30:51 -07:00 |
|
MediaPipe Team
|
82b8e4d7bf
|
Update the face stylizer config to match the latest encoder and detector config.
PiperOrigin-RevId: 527637477
|
2023-04-27 11:37:16 -07:00 |
|
MediaPipe Team
|
b05fd21709
|
Refactor the loss functions to initialize the VGG loss function in the init function to avoid duplicated initialization.
PiperOrigin-RevId: 527424556
|
2023-04-26 17:49:19 -07:00 |
|
MediaPipe Team
|
48aa88f39d
|
Change object detector learning rate decay to cosine decay.
PiperOrigin-RevId: 527337105
|
2023-04-26 12:13:17 -07:00 |
|
MediaPipe Team
|
507ed0d91d
|
Add custom metadata for object detection model with out-of-graph nms.
PiperOrigin-RevId: 527083453
|
2023-04-25 14:58:51 -07:00 |
|
Jiuqiang Tang
|
3bc8276678
|
Remove "All Rights Reserved." in copyright headers.
PiperOrigin-RevId: 526982992
|
2023-04-25 09:06:29 -07:00 |
|
MediaPipe Team
|
56df724c36
|
Add customizable face stylizer module in MediaPipe model maker
PiperOrigin-RevId: 526883862
|
2023-04-25 00:47:45 -07:00 |
|
MediaPipe Team
|
33c8c68bba
|
Add a default_applicable_licenses to model_maker/python/vision/core.
PiperOrigin-RevId: 526716940
|
2023-04-24 12:08:34 -07:00 |
|
MediaPipe Team
|
abded49e5b
|
Internal change
PiperOrigin-RevId: 526300079
|
2023-04-22 10:52:14 -07:00 |
|
MediaPipe Team
|
a6c1bb6324
|
Internal change
PiperOrigin-RevId: 526235882
|
2023-04-22 00:28:52 -07:00 |
|
MediaPipe Team
|
3e0ed2ced0
|
Internal Changes
PiperOrigin-RevId: 525180095
|
2023-04-18 10:14:08 -07:00 |
|
MediaPipe Team
|
43fd744296
|
Internal Changes
PiperOrigin-RevId: 524997017
|
2023-04-17 17:43:40 -07:00 |
|
MediaPipe Team
|
0067a1b5c2
|
Internal changes
PiperOrigin-RevId: 522248624
|
2023-04-05 22:37:11 -07:00 |
|
MediaPipe Team
|
5a1a9269e6
|
Internal Changes
PiperOrigin-RevId: 522247775
|
2023-04-05 22:31:13 -07:00 |
|
MediaPipe Team
|
7ae4d0175a
|
CL will fix the typos in the tasks files
PiperOrigin-RevId: 522240681
|
2023-04-05 21:42:19 -07:00 |
|
MediaPipe Team
|
6605f551e7
|
Object Detector add batch_size and train_data to get_steps_per_epoch.
PiperOrigin-RevId: 522149938
|
2023-04-05 14:11:29 -07:00 |
|
MediaPipe Team
|
5615c1e459
|
Delete duplicate public APIs in object detector
PiperOrigin-RevId: 522098326
|
2023-04-05 10:58:08 -07:00 |
|
MediaPipe Team
|
d9f940f8b2
|
Model Maker object detector change learning_rate_boundaries to learning_rate_epoch_boundaries.
PiperOrigin-RevId: 521024056
|
2023-03-31 15:19:26 -07:00 |
|
MediaPipe Team
|
88d68341de
|
Migrate face stylizer model files to GCS to use downloadable models in model maker.
PiperOrigin-RevId: 520848629
|
2023-03-31 00:11:51 -07:00 |
|
MediaPipe Team
|
1eeb89e95f
|
Add the model configuration and training hyperparameters for BlazeFaceStylizer.
PiperOrigin-RevId: 520767282
|
2023-03-30 16:07:11 -07:00 |
|
MediaPipe Team
|
0c8f691a36
|
Internal changes
PiperOrigin-RevId: 520411557
|
2023-03-29 12:35:20 -07:00 |
|
MediaPipe Team
|
9ee02481b1
|
Fix object detector pascal voc dataloader issue
PiperOrigin-RevId: 520160549
|
2023-03-28 16:06:44 -07:00 |
|
MediaPipe Team
|
97c271644a
|
Open Source Object Detector
PiperOrigin-RevId: 519201221
|
2023-03-24 11:53:18 -07:00 |
|
MediaPipe Team
|
27a5a6d433
|
Internal Changes
PiperOrigin-RevId: 518976200
|
2023-03-23 15:20:50 -07:00 |
|
MediaPipe Team
|
cb2ee87705
|
Internal change
PiperOrigin-RevId: 518591192
|
2023-03-22 09:34:23 -07:00 |
|
MediaPipe Team
|
560945ad39
|
Internal Changes
PiperOrigin-RevId: 517219631
|
2023-03-16 13:58:02 -07:00 |
|
MediaPipe Team
|
3b66ac0623
|
Import the saved Keras models of BlazeFaceStylizer components into MediaPipe model maker.
PiperOrigin-RevId: 517044265
|
2023-03-16 00:44:06 -07:00 |
|
MediaPipe Team
|
6774794d02
|
Add the dataset module for face stylizer in model maker.
PiperOrigin-RevId: 516628350
|
2023-03-14 14:11:20 -07:00 |
|
MediaPipe Team
|
c94de4032d
|
Fix preprocess Callable typing
PiperOrigin-RevId: 515818356
|
2023-03-10 21:50:46 -08:00 |
|
MediaPipe Team
|
2d8f937913
|
Improve docstring of image classifier model spec.
PiperOrigin-RevId: 515466722
|
2023-03-09 16:06:40 -08:00 |
|
Yuqi Li
|
9e7950a69a
|
Make each model file in the model asset bundle to be aligned relative to the start of the file (alignment = 4).
PiperOrigin-RevId: 511624410
|
2023-02-22 16:15:24 -08:00 |
|
MediaPipe Team
|
40b0dc960a
|
Internal Changes
PiperOrigin-RevId: 511604893
|
2023-02-22 14:55:03 -08:00 |
|
MediaPipe Team
|
bdd1c24990
|
Refactor common methods into vision/core/image_utils.py and vision/core/test_utils.py
PiperOrigin-RevId: 509968910
|
2023-02-15 16:54:38 -08:00 |
|
MediaPipe Team
|
99fc975f49
|
Add download model on demand to text classifier
PiperOrigin-RevId: 508441452
|
2023-02-09 12:15:17 -08:00 |
|
MediaPipe Team
|
28f728bed5
|
Change gesture_recognizer to download model files on-demand from GCS.
PiperOrigin-RevId: 508424508
|
2023-02-09 11:13:06 -08:00 |
|
MediaPipe Team
|
d283e6a05a
|
Support downloading model files on-demand from GCS in model_maker
PiperOrigin-RevId: 506174708
|
2023-01-31 18:43:35 -08:00 |
|
MediaPipe Team
|
afb0182935
|
Internal model maker change.
PiperOrigin-RevId: 504472342
|
2023-01-24 23:16:21 -08:00 |
|
MediaPipe Team
|
4e135ccdb9
|
Internal Model Maker change.
PiperOrigin-RevId: 504315641
|
2023-01-24 10:38:25 -08:00 |
|
MediaPipe Team
|
9cbb76939d
|
Adds smaller MobileBERT model.
PiperOrigin-RevId: 501451414
|
2023-01-11 20:35:39 -08:00 |
|
MediaPipe Team
|
d40fa6b16d
|
Internal Model Maker change.
PiperOrigin-RevId: 500758488
|
2023-01-09 11:04:45 -08:00 |
|
MediaPipe Team
|
e3131d7d78
|
Internal change
PiperOrigin-RevId: 499521620
|
2023-01-04 10:33:04 -08:00 |
|
MediaPipe Team
|
add5600d0d
|
Internal change
PiperOrigin-RevId: 499351795
|
2023-01-03 17:20:46 -08:00 |
|
MediaPipe Team
|
7e36a5e2ae
|
Set filecmp.cmp(shallow=False) in model_maker unit tests.
PiperOrigin-RevId: 498218578
|
2022-12-28 11:25:28 -08:00 |
|
MediaPipe Team
|
5a71b551e5
|
Remove duplicate and non-public api for model_maker
PiperOrigin-RevId: 497251246
|
2022-12-22 15:31:12 -08:00 |
|
MediaPipe Team
|
36f054dfbe
|
Internal model maker change
PiperOrigin-RevId: 497196512
|
2022-12-22 10:43:15 -08:00 |
|
MediaPipe Team
|
5c0f548f5f
|
Switches to tf.keras.optimizers.experimental.AdamW instead of the legacy AdamW.
PiperOrigin-RevId: 496821354
|
2022-12-20 20:53:13 -08:00 |
|
MediaPipe Team
|
a7b52d2c52
|
Internal changes
PiperOrigin-RevId: 496754449
|
2022-12-20 14:37:18 -08:00 |
|
MediaPipe Team
|
3e6cd5d2bf
|
Add support for customizing gesture recognizer layers
PiperOrigin-RevId: 496456160
|
2022-12-19 11:57:09 -08:00 |
|