Styjun

Why is c4 bad when playing the London against a King's Indian?

Funtion to extract float from different price patterns

Java guess the number

Secure offsite backup, even in the case of hacker root access

Does the "6 seconds per round" rule apply to speaking/roleplaying during combat situations?

Working in the USA for living expenses only; allowed on VWP?

What happens if you do emergency landing on a US base in middle of the ocean?

Building a road to escape Earth's gravity by making a pyramid on Antartica

Sharing one invocation list between multiple events on the same object in C#

Are there cubesats in GEO?

Is it a problem that pull requests are approved without any comments

What is the right way to float a home lab?

In this example, which path would a monster affected by the Dissonant Whispers spell take?

Did thousands of women die every year due to illegal abortions before Roe v. Wade?

On the Twin Paradox Again

Smooth switching between 12v batteries, with toggle switch

Will TSA allow me to carry a Continuous Positive Airway Pressure (CPAP)/sleep apnea device?

Dynamically loading CSS files based on URL or URI in PHP

X-shaped crossword

When writing an error prompt, should we end the sentence with a exclamation mark or a dot?

Can a 2nd-level sorcerer use sorcery points to create a 2nd-level spell slot?

How can Iron Man's suit withstand this?

Why don't B747s start takeoffs with full throttle?

How do I calculate APR from monthly instalments?

ValueError: Input 0 is incompatible with layer batch_normalization_1: expected ndim=3, found ndim=2

Incompatible dense layer error in kerasConcatenation of Keras parallel layers changes wanted target shapeKeras ValueError: Input 0 is incompatible with layer conv2d_2: expected ndim=4, found ndim=2“ValueError: Input 0 is incompatible with layer cropping2d_1: expected ndim=4, found ndim=3”Keras ConvLSTM2D: ValueError on output layerConcatening Attention layer with decoder input seq2seq model on KerasKERAS: Get a SLICE of RNN timesteps with return_sequence = TrueInput 0 is incompatible with layer flatten_5: expected min_ndim=3, found ndim=2Keras - LSTM on embedding - dense layersValueError: Input 0 is incompatible with layer conv1d_1: expected ndim=3, found ndim=2

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty height:90px;width:728px;box-sizing:border-box;

0

I am trying to use the implementetion of DeepTriage which is a deep learning approach for bug triaging. This website includes dataset, source code and paper. I know that is a very specific area, but I'll try to make it simple.

In the source code they define their approach "DBRNN-A: Deep Bidirectional Recurrent Neural Network with Attention mechanism and with Long Short-Term Memory units (LSTM)" with this code part:

input = Input(shape=(max_sentence_len,), dtype='int32')
sequence_embed = Embedding(vocab_size, embed_size_word2vec, input_length=max_sentence_len)(input)

forwards_1 = LSTM(1024, return_sequences=True, dropout_U=0.2)(sequence_embed)
attention_1 = SoftAttentionConcat()(forwards_1)
after_dp_forward_5 = BatchNormalization()(attention_1)

backwards_1 = LSTM(1024, return_sequences=True, dropout_U=0.2, go_backwards=True)(sequence_embed)
attention_2 = SoftAttentionConcat()(backwards_1)
after_dp_backward_5 = BatchNormalization()(attention_2)

merged = merge([after_dp_forward_5, after_dp_backward_5], mode='concat', concat_axis=-1)
after_merge = Dense(1000, activation='relu')(merged)
after_dp = Dropout(0.4)(after_merge)
output = Dense(len(train_label), activation='softmax')(after_dp) 
model = Model(input=input, output=output)
model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=1e-4), metrics=['accuracy']) 

SoftAttentionConcat implementation is from here. Rest of the functions are from keras. Also, in the paper they share the structure as:

In the first batch normalization line, it throws this error:

ValueError: Input 0 is incompatible with layer batch_normalization_1: expected ndim=3, found ndim=2

When I use max_sentence_len=50 and max_sentence_len=200 I look at the dimension until the error point, I see these shapes:

Input -> (None, 50)
Embedding -> (None, 50, 200)
LSTM -> (None, None, 1024)
SoftAttentionConcat -> (None, 2048) 

So, is there anybody seeing the problem here?

python tensorflow keras

share|improve this question

asked Mar 24 at 14:24

AlperenAlperen

1,4431822

add a comment | 

0

I am trying to use the implementetion of DeepTriage which is a deep learning approach for bug triaging. This website includes dataset, source code and paper. I know that is a very specific area, but I'll try to make it simple.

In the source code they define their approach "DBRNN-A: Deep Bidirectional Recurrent Neural Network with Attention mechanism and with Long Short-Term Memory units (LSTM)" with this code part:

input = Input(shape=(max_sentence_len,), dtype='int32')
sequence_embed = Embedding(vocab_size, embed_size_word2vec, input_length=max_sentence_len)(input)

forwards_1 = LSTM(1024, return_sequences=True, dropout_U=0.2)(sequence_embed)
attention_1 = SoftAttentionConcat()(forwards_1)
after_dp_forward_5 = BatchNormalization()(attention_1)

backwards_1 = LSTM(1024, return_sequences=True, dropout_U=0.2, go_backwards=True)(sequence_embed)
attention_2 = SoftAttentionConcat()(backwards_1)
after_dp_backward_5 = BatchNormalization()(attention_2)

merged = merge([after_dp_forward_5, after_dp_backward_5], mode='concat', concat_axis=-1)
after_merge = Dense(1000, activation='relu')(merged)
after_dp = Dropout(0.4)(after_merge)
output = Dense(len(train_label), activation='softmax')(after_dp) 
model = Model(input=input, output=output)
model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=1e-4), metrics=['accuracy']) 

SoftAttentionConcat implementation is from here. Rest of the functions are from keras. Also, in the paper they share the structure as:

In the first batch normalization line, it throws this error:

ValueError: Input 0 is incompatible with layer batch_normalization_1: expected ndim=3, found ndim=2

When I use max_sentence_len=50 and max_sentence_len=200 I look at the dimension until the error point, I see these shapes:

Input -> (None, 50)
Embedding -> (None, 50, 200)
LSTM -> (None, None, 1024)
SoftAttentionConcat -> (None, 2048) 

So, is there anybody seeing the problem here?

python tensorflow keras

share|improve this question

asked Mar 24 at 14:24

AlperenAlperen

1,4431822

add a comment | 

I am trying to use the implementetion of DeepTriage which is a deep learning approach for bug triaging. This website includes dataset, source code and paper. I know that is a very specific area, but I'll try to make it simple.

In the source code they define their approach "DBRNN-A: Deep Bidirectional Recurrent Neural Network with Attention mechanism and with Long Short-Term Memory units (LSTM)" with this code part:

input = Input(shape=(max_sentence_len,), dtype='int32')
sequence_embed = Embedding(vocab_size, embed_size_word2vec, input_length=max_sentence_len)(input)

forwards_1 = LSTM(1024, return_sequences=True, dropout_U=0.2)(sequence_embed)
attention_1 = SoftAttentionConcat()(forwards_1)
after_dp_forward_5 = BatchNormalization()(attention_1)

backwards_1 = LSTM(1024, return_sequences=True, dropout_U=0.2, go_backwards=True)(sequence_embed)
attention_2 = SoftAttentionConcat()(backwards_1)
after_dp_backward_5 = BatchNormalization()(attention_2)

merged = merge([after_dp_forward_5, after_dp_backward_5], mode='concat', concat_axis=-1)
after_merge = Dense(1000, activation='relu')(merged)
after_dp = Dropout(0.4)(after_merge)
output = Dense(len(train_label), activation='softmax')(after_dp) 
model = Model(input=input, output=output)
model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=1e-4), metrics=['accuracy']) 

SoftAttentionConcat implementation is from here. Rest of the functions are from keras. Also, in the paper they share the structure as:

In the first batch normalization line, it throws this error:

ValueError: Input 0 is incompatible with layer batch_normalization_1: expected ndim=3, found ndim=2

When I use max_sentence_len=50 and max_sentence_len=200 I look at the dimension until the error point, I see these shapes:

Input -> (None, 50)
Embedding -> (None, 50, 200)
LSTM -> (None, None, 1024)
SoftAttentionConcat -> (None, 2048) 

So, is there anybody seeing the problem here?

python tensorflow keras

share|improve this question

asked Mar 24 at 14:24

AlperenAlperen

1,4431822

input = Input(shape=(max_sentence_len,), dtype='int32')
sequence_embed = Embedding(vocab_size, embed_size_word2vec, input_length=max_sentence_len)(input)

forwards_1 = LSTM(1024, return_sequences=True, dropout_U=0.2)(sequence_embed)
attention_1 = SoftAttentionConcat()(forwards_1)
after_dp_forward_5 = BatchNormalization()(attention_1)

backwards_1 = LSTM(1024, return_sequences=True, dropout_U=0.2, go_backwards=True)(sequence_embed)
attention_2 = SoftAttentionConcat()(backwards_1)
after_dp_backward_5 = BatchNormalization()(attention_2)

merged = merge([after_dp_forward_5, after_dp_backward_5], mode='concat', concat_axis=-1)
after_merge = Dense(1000, activation='relu')(merged)
after_dp = Dropout(0.4)(after_merge)
output = Dense(len(train_label), activation='softmax')(after_dp) 
model = Model(input=input, output=output)
model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=1e-4), metrics=['accuracy']) 

ValueError: Input 0 is incompatible with layer batch_normalization_1: expected ndim=3, found ndim=2

Input -> (None, 50)
Embedding -> (None, 50, 200)
LSTM -> (None, None, 1024)
SoftAttentionConcat -> (None, 2048) 

share|improve this question

asked Mar 24 at 14:24

AlperenAlperen

1,4431822

share|improve this question

asked Mar 24 at 14:24

AlperenAlperen

1,4431822

asked Mar 24 at 14:24

AlperenAlperen

1,4431822

asked Mar 24 at 14:24

AlperenAlperen

1,4431822