paarthneekhara / text-to-image

Text to image synthesis using thought vectors
MIT License
2.16k stars 394 forks source link

Training Error #27

Open dheeru999 opened 7 years ago

dheeru999 commented 7 years ago

While running the (Train. py) i am facing the following errors. Please help me to solve those errors.

/usr/bin/python2.7 /home/mcis-lap-40/raviwork/Tensorflow_Models/text-to-image-master/train.py Traceback (most recent call last): File "/home/mcis-lap-40/raviwork/Tensorflow_Models/text-to-image-master/train.py", line 250, in main() File "/home/mcis-lap-40/raviwork/Tensorflow_Models/text-to-image-master/train.py", line 77, in main input_tensors, variables, loss, outputs, checks = gan.build_model() File "/home/mcis-lap-40/raviwork/Tensorflow_Models/text-to-image-master/model.py", line 37, in build_model fake_image = self.generator(t_z, t_real_caption) File "/home/mcis-lap-40/raviwork/Tensorflow_Models/text-to-image-master/model.py", line 137, in generator z_concat = tf.concat(1, [t_z, reduced_text_embedding]) File "/home/mcis-lap-40/.local/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1061, in concat dtype=dtypes.int32).get_shape( File "/home/mcis-lap-40/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 611, in convert_to_tensor as_ref=False) File "/home/mcis-lap-40/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 676, in internal_convert_to_tensor ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref) File "/home/mcis-lap-40/.local/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 121, in _constant_tensor_conversion_function return constant(v, dtype=dtype, name=name) File "/home/mcis-lap-40/.local/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 102, in constant tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape)) File "/home/mcis-lap-40/.local/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 376, in make_tensor_proto _AssertCompatible(values, dtype) File "/home/mcis-lap-40/.local/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 302, in _AssertCompatible (dtype.name, repr(mismatch), type(mismatch).name)) TypeError: Expected int32, got list containing Tensors of type '_Message' instead.

Process finished with exit code 1

paarthneekhara commented 7 years ago

This is again a tensorflow version issue.. Please check the function definition in your tf version and modify the method call accordingly - tf.concat => tf.concat([t_z, reduced_text_embedding], axis=1) You may need to update some other method calls as well.

dheeru999 commented 7 years ago

Thanks for responding............. Can u mention Which (Tensorflow) Version Is suitable for this model..

=> tf.concat([t_z, reduced_text_embedding], axis=1)---- I have changed this ,but still the error remains same...

(You may need to update some other method calls as well)-- Can u mention what are the other method calls that i need to update......