search

wglassly / CID_ATTCNN

For paper “Chemical-induced Disease Extraction via Convolutional Neural Networks ”
2 stars 1 forks source link

shape error in pooling attention #2

Open yimingli90 opened 5 years ago

yimingli90 commented 5 years ago

Hi, I'm trying to use the code you post in the previous issue and it seems that there is an shape error in def attention_pooling Traceback (most recent call last):

File "", line 1, in runfile('/home/yli/Documents/CID_CNN_ATTENTION/distance_pos_fea_cnn_rnn_v1.py', wdir='/home/yli/Documents/CID_CNN_ATTENTION')

File "/home/yli/tensorflow/lib/python3.6/site-packages/spyder_kernels/customize/spydercustomize.py", line 827, in runfile execfile(filename, namespace)

File "/home/yli/tensorflow/lib/python3.6/site-packages/spyder_kernels/customize/spydercustomize.py", line 110, in execfile exec(compile(f.read(), filename, 'exec'), namespace)

File "/home/yli/Documents/CID_CNN_ATTENTION/distance_pos_fea_cnn_rnn_v1.py", line 746, in processing(trainfile, testfile,train_feature_file, test_feature_file)

File "/home/yli/Documents/CID_CNN_ATTENTION/distance_pos_fea_cnn_rnn_v1.py", line 723, in processing model = RExtractionModel(max_lengths=sum(max_lengths),index = train_split, embedding_weights=embedding_weights, vocabulary=vocabulary, manual_length = manual_length, bag_size = bag_size)

File "/home/yli/Documents/CID_CNN_ATTENTION/distance_pos_fea_cnn_rnn_v1.py", line 377, in init self.h_pool_attention.append(self.attention_pooling(x = pool , attention_dim = attention_dim, num_filters = num_filters))

File "/home/yli/Documents/CID_CNN_ATTENTION/distance_pos_fea_cnn_rnn_v1.py", line 433, in attention_pooling return tf.matmul(x,A)

File "/home/yli/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 2455, in matmul a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)

File "/home/yli/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 5333, in mat_mul name=name)

File "/home/yli/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper op_def=op_def)

File "/home/yli/tensorflow/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func return func(*args, **kwargs)

File "/home/yli/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3300, in create_op op_def=op_def)

File "/home/yli/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1823, in init control_input_ops)

File "/home/yli/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1662, in _create_c_op raise ValueError(str(e))

ValueError: Shape must be rank 2 but is rank 4 for 'pooling-attention-0/MatMul_1' (op: 'MatMul') with input shapes: [?,1,1,300], [?,100].

I will appreciate if you can help me to figure it out