WGAN.py

gistfile1.txt

File "/home/yanboyang713/Documents/SyntheticOversampling/src/WGAN.py", line 48, in train_step  *
        fake_data = gen(noise, training=True)
    File "/home/yanboyang713/Documents/SyntheticOversampling/test/lib/python3.10/site-packages/keras/src/utils/traceback_utils.py", line 70, in error_handler  **
        raise e.with_traceback(filtered_tb) from None
    File "/tmp/__autograph_generated_file6v04vxxq.py", line 10, in tf__call
        x = ag__.converted_call(ag__.ld(self).input_layer, (ag__.ld(inputs),), None, fscope)

    ValueError: Exception encountered when calling layer 'generator_1' (type Generator).
    
    in user code:
    
        File "/home/yanboyang713/Documents/SyntheticOversampling/src/WGAN.py", line 23, in call  *
            x = self.input_layer(inputs)
        File "/home/yanboyang713/Documents/SyntheticOversampling/test/lib/python3.10/site-packages/keras/src/utils/traceback_utils.py", line 70, in error_handler  **
            raise e.with_traceback(filtered_tb) from None
    
        ValueError: tf.function only supports singleton tf.Variables created on the first call. Make sure the tf.Variable is only created once or created outside tf.function. See https://www.tensorflow.org/guide/function#creating_tfvariables for more information.
    
    
    Call arguments received by layer 'generator_1' (type Generator):
      • inputs=tf.Tensor(shape=(8, 10), dtype=float32)