E:\Users\Raytine\Anaconda3\python.exe F:/zhaiyao/CS230-IcGAN-image-editing-tensorflow-master/main.py --OPER_FLAG 1 --celebA 1
Creating directory...
Path already exists.
Path already exists.
Path already exists.
Training celebA dataset:
(8192, 64, 64, 3)
z_var (64, 1, 1, 1024)
d1 (64, 4, 4, 512)
d5 (64, 64, 64, 3)
x (64, 64, 64, 3)
c1 (64, 32, 32, 32)
Traceback (most recent call last):
File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1567, in _create_c_op
c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Shape must be rank 4 but is rank 2 for 'Conv2D_2' (op: 'Conv2D') with input shapes: [64,16,16,64], [32768,100].
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "F:/zhaiyao/CS230-IcGAN-image-editing-tensorflow-master/main.py", line 127, in
sample_path=sample_path , log_dir = log_dir , gen_learning_rate=gen_learn_rate, dis_learning_rate=dis_learn_rate , info_reg_coeff=1.0)
File "F:\zhaiyao\CS230-IcGAN-image-editing-tensorflow-master\Gan_celebA.py", line 54, in init
self.build_model2()
File "F:\zhaiyao\CS230-IcGAN-image-editing-tensorflow-master\Gan_celebA.py", line 97, in build_model2
self.e_z= self.encode_z(self.fake_images, weights=self.weights3, biases=self.biases3)
File "F:\zhaiyao\CS230-IcGAN-image-editing-tensorflow-master\Gan_celebA.py", line 456, in encode_z
c3 = tf.nn.relu(batch_normal(conv2d(c2, weights['e3'], biases['eb3']), scope='enzbn3'))
File "F:\zhaiyao\CS230-IcGAN-image-editing-tensorflow-master\ops.py", line 11, in conv2d
x = tf.nn.conv2d(x , W , strides=[1, strides , strides, 1], padding= padding)
File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 1042, in conv2d
c2 (64, 16, 16, 64)
data_format=data_format, dilations=dilations, name=name)
File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3392, in create_op
op_def=op_def)
File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1734, in init
control_input_ops)
File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1570, in _create_c_op
raise ValueError(str(e))
ValueError: Shape must be rank 4 but is rank 2 for 'Conv2D_2' (op: 'Conv2D') with input shapes: [64,16,16,64], [32768,100].
E:\Users\Raytine\Anaconda3\python.exe F:/zhaiyao/CS230-IcGAN-image-editing-tensorflow-master/main.py --OPER_FLAG 1 --celebA 1 Creating directory... Path already exists. Path already exists. Path already exists. Training celebA dataset: (8192, 64, 64, 3) z_var (64, 1, 1, 1024) d1 (64, 4, 4, 512) d5 (64, 64, 64, 3) x (64, 64, 64, 3) c1 (64, 32, 32, 32) Traceback (most recent call last): File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1567, in _create_c_op c_op = c_api.TF_FinishOperation(op_desc) tensorflow.python.framework.errors_impl.InvalidArgumentError: Shape must be rank 4 but is rank 2 for 'Conv2D_2' (op: 'Conv2D') with input shapes: [64,16,16,64], [32768,100].
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "F:/zhaiyao/CS230-IcGAN-image-editing-tensorflow-master/main.py", line 127, in
sample_path=sample_path , log_dir = log_dir , gen_learning_rate=gen_learn_rate, dis_learning_rate=dis_learn_rate , info_reg_coeff=1.0)
File "F:\zhaiyao\CS230-IcGAN-image-editing-tensorflow-master\Gan_celebA.py", line 54, in init
self.build_model2()
File "F:\zhaiyao\CS230-IcGAN-image-editing-tensorflow-master\Gan_celebA.py", line 97, in build_model2
self.e_z= self.encode_z(self.fake_images, weights=self.weights3, biases=self.biases3)
File "F:\zhaiyao\CS230-IcGAN-image-editing-tensorflow-master\Gan_celebA.py", line 456, in encode_z
c3 = tf.nn.relu(batch_normal(conv2d(c2, weights['e3'], biases['eb3']), scope='enzbn3'))
File "F:\zhaiyao\CS230-IcGAN-image-editing-tensorflow-master\ops.py", line 11, in conv2d
x = tf.nn.conv2d(x , W , strides=[1, strides , strides, 1], padding= padding)
File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 1042, in conv2d
c2 (64, 16, 16, 64)
data_format=data_format, dilations=dilations, name=name)
File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3392, in create_op
op_def=op_def)
File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1734, in init
control_input_ops)
File "E:\Users\Raytine\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1570, in _create_c_op
raise ValueError(str(e))
ValueError: Shape must be rank 4 but is rank 2 for 'Conv2D_2' (op: 'Conv2D') with input shapes: [64,16,16,64], [32768,100].