ValueError: axes don't match array about hashgan HOT 4 CLOSED

It seems that there is something wrong with your data. Can you check whether the images exist in the ./data/cifar10 folder?

cannot open test/999_3533.jpg 0 0 1 0 0 0 0 0 0 0

cannot open test/999_7383.jpg 0 0 0 0 1 0 0 0 0 0

cannot open train/1_8331.jpg 0 1 0 0 0 0 0 0 0 0

cannot open train/4_5356.jpg 0 0 0 0 0 0 0 0 0 1

cannot open test/999_3276.jpg 0 0 0 0 1 0 0 0 0 0

from hashgan.

Thank you very much. I was trying to open data_list. Could you please have a look on this issue?

{'DATA': {'DATA_ROOT': './data/cifar10',
'DB_SIZE': 54000,
'IMAGE_DIR': './output/cifar10_step_1_ACGAN_SCALE_G_10.0/images',
'LABEL_DIM': 10,
'LIST_ROOT': './data_list/cifar10',
'LOG_DIR': './output/cifar10_step_1_ACGAN_SCALE_G_10.0/logs',
'MAP_R': 54000,
'MODEL_DIR': './output/cifar10_step_1_ACGAN_SCALE_G_10.0/models',
'OUTPUT_DIM': 3072,
'OUTPUT_DIR': './output/cifar10_step_1_ACGAN_SCALE_G_10.0',
'TEST_SIZE': 1000,
'USE_DATASET': 'cifar10',
'WIDTH_HEIGHT': 32},
'MODEL': {'ALEXNET_PRETRAINED_MODEL_PATH': './pretrained_models/reference_pretrain.npy',
'DIM': 64,
'DIM_D': 128,
'DIM_G': 128,
'D_ARCHITECTURE': 'NORM',
'D_PRETRAINED_MODEL_PATH': '',
'G_ARCHITECTURE': 'NORM',
'G_PRETRAINED_MODEL_PATH': '',
'HASH_DIM': 64},
'TRAIN': {'ACGAN_SCALE': 1.0,
'ACGAN_SCALE_FAKE': 1.0,
'ACGAN_SCALE_G': 10.0,
'BATCH_SIZE': 64,
'CHECKPOINT_FREQUENCY': 1000,
'CROSS_ENTROPY_ALPHA': 10,
'DECAY': True,
'EVALUATE_MODE': False,
'EVAL_FREQUENCY': 10000,
'FAKE_RATIO': 1.0,
'G_LR': 0.0001,
'ITERS': 100000,
'LR': 0.0001,
'NORMED_CROSS_ENTROPY': True,
'N_CRITIC': 5,
'SAMPLE_FREQUENCY': 1000,
'WGAN_SCALE': 1.0,
'WGAN_SCALE_G': 1.0,
'WGAN_SCALE_GP': 10.0}}
Traceback (most recent call last):
File "/home/umair/anaconda3/envs/HashGAN/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1576, in _create_c_op
c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 8 and 128 for 'Conv2D' (op: 'Conv2D') with input shapes: [64,128,8,8], [1,1,128,128].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "main.py", line 270, in
main(config)
File "main.py", line 169, in main
model = Model(cfg)
File "main.py", line 47, in init
self.build_graph()
File "main.py", line 53, in build_graph
labeled_fake_data = generator(self.batch_size, self.labeled_labels_holder, cfg=self.cfg)
File "/home/umair/HashGAN-1.0/lib/architecture.py", line 399, in generator
return old_generator(n_samples, labels, noise=noise, cfg=cfg)
File "/home/umair/HashGAN-1.0/lib/architecture.py", line 118, in old_generator
3, output, resample='up')
File "/home/umair/HashGAN-1.0/lib/architecture.py", line 79, in residual_block
he_init=False, biases=True, inputs=inputs)
File "/home/umair/HashGAN-1.0/lib/architecture.py", line 46, in upsample_conv
name, input_dim, output_dim, filter_size, output, he_init=he_init, biases=biases)
File "/home/umair/HashGAN-1.0/lib/ops.py", line 95, in conv2D
data_format='NHWC'
File "/home/umair/anaconda3/envs/HashGAN/lib/python3.6/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 956, in conv2d
data_format=data_format, dilations=dilations, name=name)
File "/home/umair/anaconda3/envs/HashGAN/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/umair/anaconda3/envs/HashGAN/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 454, in new_func
return func(*args, **kwargs)
File "/home/umair/anaconda3/envs/HashGAN/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3155, in create_op
op_def=op_def)
File "/home/umair/anaconda3/envs/HashGAN/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1731, in init
control_input_ops)
File "/home/umair/anaconda3/envs/HashGAN/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1579, in _create_c_op
raise ValueError(str(e))
ValueError: Dimensions must be equal, but are 8 and 128 for 'Conv2D' (op: 'Conv2D') with input shapes: [64,128,8,8], [1,1,128,128].

from hashgan.

Hi, I have no idea about your issue based on the traceback. Could you tell me more about the issue? Such as what have you done to the codes? What's the version of Tensorflow?

from hashgan.

I am closing this issue due to the long time of inactivity, feel free to reopen it if there is any question. Thanks!

from hashgan.