Open sam7199 opened 3 years ago
I think the problem occurred because I use the specific Bert Server which is used to convert Chinese into word vector, and you can have a try to find the right version for English. Thanks for your following and I created this project by rectified some mistakes in aloychen's repository.
I am new to Tensorflow can you guide me on how to convert this so that it take input in English ? and Great work I have change the train.txt into english but I am getting the folllowing error when i try to train trainTextToFace.py
Using TensorFlow backend. Dense NO.1 Dense NO.2 Dense NO.3 Reshape over WARNING:tensorflow:From /tensorflow-1.15.2/python3.7/tensorflow_core/python/ops/resource_variable_ops.py:1630: calling BaseResourceVariable.init (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version. Instructions for updating: If using Keras pass *_constraint arguments to layers. compile over Traceback (most recent call last): File "trainTextToFace.py", line 28, in
train()
File "trainTextToFace.py", line 24, in train
model.fit(sentenceEmbedding, imageDlatents, batch_size = 50, epochs = 200)
File "/tensorflow-1.15.2/python3.7/keras/engine/training.py", line 1154, in fit
batch_size=batch_size)
File "/tensorflow-1.15.2/python3.7/keras/engine/training.py", line 504, in _standardize_user_data
self._set_inputs(x)
File "/tensorflow-1.15.2/python3.7/keras/engine/training.py", line 416, in _set_inputs
self.build(input_shape=(None,) + inputs.shape[1:])
File "/tensorflow-1.15.2/python3.7/keras/engine/sequential.py", line 222, in build
x = layer(x)
File "/tensorflow-1.15.2/python3.7/keras/engine/base_layer.py", line 446, in call
self.assert_input_compatibility(inputs)
File "/tensorflow-1.15.2/python3.7/keras/engine/base_layer.py", line 358, in assert_input_compatibility
str(K.ndim(x)))
ValueError: Input 0 is incompatible with layer dense_1: expected min_ndim=2, found ndim=1