Open MuruganR96 opened 4 years ago
The input image size can be changed here: https://github.com/iamhankai/attribute-aware-attention/blob/4b4cf873d6e398f1e64891dbc34ccb8fbd891f30/cub_demo.py#L51
solved the issue. the problem is didn't get the right output feature map shape for _activation49
Traceback (most recent call last):
File "cub_demo.py", line 102, in <module>
share_fea_map = Reshape((final_dim, L), name='reshape_layer')(share_fea_map)
while doing Reshape, _activation49 shape mismatching with (final_dim, L) shape.
right requirements: pip install keras==1.2.1 pip install tensorflow==1.2.0 --ignore-installed
activation_49 (Activation) (None, 14, 14, 2048) 0 merge_16[0][0]
____________________________________________________________________________________________________
avg_pool (AveragePooling2D) (None, 2, 2, 2048) 0 activation_49[0][0]
====================================================================================================
Total params: 23,587,712
Trainable params: 23,534,592
Non-trainable params: 53,120
what was wrong here is, requirements pip install theano==0.9.0
activation_49 (Activation) (None, 0, 14, 2048) 0 merge_16[0][0]
____________________________________________________________________________________________________
avg_pool (AveragePooling2D) (None, 0, 2, 2048) 0 activation_49[0][0]
====================================================================================================
Total params: 23,587,712
Trainable params: 23,534,592
Non-trainable params: 53,120
Traceback (most recent call last):
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 671, in _call_cpp_shape_fn_impl
input_tensors_as_shapes, status)
File "/usr/lib/python3.6/contextlib.py", line 88, in __exit__
next(self.gen)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/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: Shape must be rank 2 but is rank 3 for 'MatMul_29' (op: 'MatMul') with input shapes: [?,196,512], [?,512].
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "cub_demo.py", line 104, in <module>
attn1 = merge([id_fea_map,attr_fea_list[i]], mode='dot', dot_axes=(2,1))
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/keras/engine/topology.py", line 1680, in merge
name=name)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/keras/engine/topology.py", line 1301, in __init__
self.add_inbound_node(layers, node_indices, tensor_indices)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/keras/engine/topology.py", line 635, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/keras/engine/topology.py", line 172, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors, mask=input_masks))
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/keras/engine/topology.py", line 1409, in call
output = K.batch_dot(l1, l2, self.dot_axes)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 884, in batch_dot
out = tf.matmul(x, y, adjoint_a=adj_x, adjoint_b=adj_y)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 1816, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 1217, in _mat_mul
transpose_b=transpose_b, name=name)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2508, in create_op
set_shapes_for_outputs(ret)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1873, in set_shapes_for_outputs
shapes = shape_func(op)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1823, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 610, in call_cpp_shape_fn
debug_python_shape_fn, require_shape_fn)
File "/home/dell/Videos/Object_Tracking/env_a3mv2/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 676, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Shape must be rank 2 but is rank 3 for 'MatMul_29' (op: 'MatMul') with input shapes: [?,196,512], [?,512].
How to solve this issue @iamhankai, sir? please help me to solve it.
Running Command:
Requirements:
added additionally, for backend set as 'theano'
Error 1: ImportError: cannot import name inplace_increment
Deleting the cache manually worked. rm -rf ~/.theano
Error 2: AttributeError: 'module' object has no attribute 'ifelse'
Your version of theano is probably too new for that version of Keras. You should try downgrading theano to 0.9.x, pip install theano==0.9.0
Error 3: ValueError: Negative dimension size caused by subtracting 3 from 2 for 'MaxPool' (op: 'MaxPool') with input shapes: [?,2,2240,64].
i followed @iamhankai sir suggestion . changed "image_data_format" to "channels_first". sudo gedit $HOME/.keras/keras.json
Error 4: ValueError: total size of new array must be unchanged
I saw @iamhankai suggestion for this issue. but not understand clearly. I have few doubts, please help me @iamhankai @muneeb699 sir. it is my request.
Please guide me to solve this issue @iamhankai, sir.
Thanks and Regards Murugan Rajenthiran