wzell / cmd Goto Github PK

I'm using Python3.5+Tensorflow1.2+Keras on Windows 10, and I get the following error:

`C:\Users\jindongwang\Anaconda3\python.exe C:/Users/jindongwang/Desktop/cmd-master/exp_office.py
Using TensorFlow backend.
WARNING (theano.configdefaults): g++ not detected ! Theano will be unable to execute optimized C-implementations (for both CPU and GPU) and will default to Python implementations. Performance will be severely degraded. To remove this warning, set Theano flags cxx to an empty string.

Loading office image data...
Found 2817 images belonging to 31 classes.
Found 498 images belonging to 31 classes.
Found 795 images belonging to 31 classes.

Creating/Loading image representations via VGG_16 model...
C:\Users\jindongwang\Anaconda3\lib\site-packages\keras\legacy\interfaces.py:86: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(64, (3, 3), activation="relu")
'call to the Keras 2 API: ' + signature) C:\Users\jindongwang\Anaconda3\lib\site-packages\keras\legacy\interfaces.py:86: UserWarning: Update yourConv2Dcall to the Keras 2 API:Conv2D(128, (3, 3), activation="relu") ' call to the Keras 2 API: ' + signature)
Traceback (most recent call last):
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 671, in _call_cpp_shape_fn_impl
input_tensors_as_shapes, status)
File "C:\Users\jindongwang\Anaconda3\lib\contextlib.py", line 66, in exit
next(self.gen)
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:/Users/jindongwang/Desktop/cmd-master/exp_office.py", line 53, in
'amazon', N_IMAGES_AM)
File "C:\Users\jindongwang\Desktop\cmd-master\models\office_mmatch.py", line 154, in create_img_repr
vgg16 = self.VGG_16(weights_file)
File "C:\Users\jindongwang\Desktop\cmd-master\models\office_mmatch.py", line 285, in VGG_16
model.add(MaxPooling2D((2,2), strides=(2,2)))
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\keras\models.py", line 455, in add
output_tensor = layer(self.outputs[0])
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\keras\engine\topology.py", line 554, in call
output = self.call(inputs, **kwargs)
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\keras\layers\pooling.py", line 154, in call
data_format=self.data_format)
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\keras\layers\pooling.py", line 217, in _pooling_function
pool_mode='max')
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py", line 3014, in pool2d
x = tf.nn.max_pool(x, pool_size, strides, padding=padding)
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 1769, in max_pool
name=name)
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 1605, in _max_pool
data_format=data_format, name=name)
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op
op_def=op_def)
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 2508, in create_op
set_shapes_for_outputs(ret)
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1873, in set_shapes_for_outputs
shapes = shape_func(op)
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1823, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 610, in call_cpp_shape_fn
debug_python_shape_fn, require_shape_fn)
File "C:\Users\jindongwang\Anaconda3\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 676, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].

Process finished with exit code 1`

What can I do?

I am interested in your work and i had run your code of cmd successfully but i still have two problems.

1. the total accuracy on office31, am->wc, wc ->am, etc are lower than your paper results.
   my: acc-tst=0.5597484278229048; acc-tst-dr=0.6503144648090099
   yours:acc-tst = .676 +-006 ; acc-tst-dr= .770 +- 006
2. i use tensorflow==0.12.1 and other same as you, how can i put it on GPU
   (i use keras function: from keras.utils.multi_gpu_utils import multi_gpu_model,
   with no err but run it i got ModuleNotFoundError: No module named 'keras.utils.multi_gpu_utils')

Exception: Need to call set_layer on ActivityRegularizer instance before calling the instance.

Hi Werner Zellinger:
something wrong happens while running exp_amazon_review.py
error happens while run amazon_review_mmatch.py

encoded_s = encoding(input_s)
encoded_t = encoding(input_t)

I know that domain_regularizer need run set_layer. However,I did not find any code about set_layer.

Can you please link to the paper's openreview page in the README?