search

LynnHo / AttGAN-Tensorflow

AttGAN: Facial Attribute Editing by Only Changing What You Want (IEEE TIP 2019)
MIT License
605 stars 135 forks source link

Error in testing #10

Closed Snarendranath closed 5 years ago

LynnHo commented 5 years ago

@Snarendranath Is there any information about the error?

ChanningPing commented 5 years ago

I also encounter error in testing. The testing command is : python test.py \ --experiment_name my_exp_name \ --test_int 1.0

The error message is as follows: Traceback (most recent call last): File "test.py", line 69, in <module> te_data = data.Celeba('./data', atts, img_size, 1, part='test', shuffle=False, sess=sess, crop=not use_cropped_img) File "/home/qping/AttGAN-Tensorflow-master/data.py", line 280, in __init__ repeat=repeat) File "/home/qping/AttGAN-Tensorflow-master/data.py", line 70, in disk_image_batch_dataset map_func_, num_threads, shuffle, buffer_size, repeat) File "/home/qping/AttGAN-Tensorflow-master/data.py", line 24, in batch_dataset dataset = dataset.map(map_func, num_parallel_calls=num_threads) File "/home/qping/tensorflow/venv/local/lib/python2.7/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 853, in map return ParallelMapDataset(self, map_func, num_parallel_calls) File "/home/qping/tensorflow/venv/local/lib/python2.7/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 1870, in __init__ super(ParallelMapDataset, self).__init__(input_dataset, map_func) File "/home/qping/tensorflow/venv/local/lib/python2.7/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 1839, in __init__ self._map_func.add_to_graph(ops.get_default_graph()) File "/home/qping/tensorflow/venv/local/lib/python2.7/site-packages/tensorflow/python/framework/function.py", line 484, in add_to_graph self._create_definition_if_needed() File "/home/qping/tensorflow/venv/local/lib/python2.7/site-packages/tensorflow/python/framework/function.py", line 319, in _create_definition_if_needed self._create_definition_if_needed_impl() File "/home/qping/tensorflow/venv/local/lib/python2.7/site-packages/tensorflow/python/framework/function.py", line 336, in _create_definition_if_needed_impl outputs = self._func(*inputs) File "/home/qping/tensorflow/venv/local/lib/python2.7/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 1802, in tf_map_func ret = map_func(*nested_args) File "/home/qping/AttGAN-Tensorflow-master/data.py", line 63, in map_func_ return map_func(*parse_func(*args)) File "/home/qping/AttGAN-Tensorflow-master/data.py", line 248, in _map_func img = tf.image.resize_images(img, [img_size, img_size]) / 127.5 - 1 TypeError: unsupported operand type(s) for /: 'Tensor' and 'float'

I also tried commenting out the from __future__ import division at the head of test.py, but the error persists. Thank you for your help!

ChanningPing commented 5 years ago

Also, the training and eval worked perfectly fine for me. Only error in testing.

LynnHo commented 5 years ago

@ChanningPing Have you modified the code? Such error looks really strange.

CastellanLiu commented 5 years ago

@ChanningPing Is your data in './data'? Maybe you could check the type and content of 'img' by print it out in the _map_func.