cassdlcm/mediapipe
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Setting training for the encoder and decoder when converting to TFLite.

Browse Source 
Also add selected TF ops to TFLite converter.

PiperOrigin-RevId: 557520277
This commit is contained in:
MediaPipe Team 2023-08-16 09:59:53 -07:00 committed by Copybara-Service
parent ee217ceb67
commit 9e45e2b6e9
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
mediapipe/model_maker/python/vision/face_stylizer/face_stylizer.py
View File

@ -231,8 +231,8 @@ class FaceStylizer(object):
# Create an end-to-end model by concatenating encoder and decoder
inputs = tf.keras.Input(shape=(256, 256, 3))
x = self._encoder(inputs)
x = self._decoder({'inputs': x + self.w_avg})
x = self._encoder(inputs, training=True)
x = self._decoder({'inputs': x + self.w_avg}, training=True)
x = x['image'][-1]
# Scale the data range from [-1, 1] to [0, 1] to support running inference
# on both CPU and GPU.
@ -241,6 +241,10 @@ class FaceStylizer(object):
face_stylizer_model_buffer = model_util.convert_to_tflite(
model=model,
supported_ops=[
tf.lite.OpsSet.TFLITE_BUILTINS,
tf.lite.OpsSet.SELECT_TF_OPS,
],
preprocess=self._preprocessor,
)