Closed anasvaf closed 4 years ago
We haven't tested creating .pb with TF v2.
I think you can first create model using v1, then read it in v2_use_frozen.py https://github.com/lighttransport/VisemeNet-infer/blob/master/v2_use_frozen.py to run the inference in TF v2
FYI, net1 is not used in the inference stage(it outputs facial landmark points)
Thank you very much for your prompt response! I really appreciate it! I managed to solve the issue.
Hello, I am using TensorFlow 2.0 and I have an issue with the
tf.contrib
batch_norm layer. I have tried to replace it withthe tf.keras.layers.BatchNormalization
, since it containes similar parameters e.g., is_training --> trainable, center, etc. However, when I change the parameterscope = 'net1_land_bn'
then it complains that my first input parameter to the BatchNorm layer should be an axis, hence integer. Instead ofl2 = tf.keras.layers.BatchNormalization(l1, center=True, scale=True, trainable=phase, name='net1_land_bn')
Did you face any similar issue? Thank you in advance! Tasos