я определяю тестовые и транзитные прогнозы и получаю некоторые ошибки, я их не понимаю
я делаю чат-питон с использованием tenorflow, и я строю модель seq2seq, и я определяю прогнозы обучения и теста, и я получаю эту ошибкупри запуске кода все было в порядке, пока я не начал определять прогнозы обучения и теста, появилась ошибка
может кто-нибудь помочь мне
#### Building SEQ2SEQ Model #####\
### placeholders
def model_inputs():
inputs = tf.placeholder(tf.int32,[None,None],name = 'input')
targets = tf.placeholder(tf.int32,[None,None],name = 'target')
lr = tf.placeholder(tf.float32,name = 'learning_rate')
keep_prob = tf.placeholder(tf.float32,name = 'keep_prob')
return inputs,targets,lr,keep_prob
#### preprocess the targets adding sos
def process_targets(targets,word2int,batch_size):
left_side = tf.fill([batch_size,1],word2int['<SOS>'])
right_side = tf.strided_slice(targets,[0,0],[batch_size,-1],[1,1])
preprocessed_targets = tf.concat([left_side,right_side],1)
return preprocessed_targets
### encoder RNN layer ###
def encoder_rnn(rnn_inputs,rnn_size,num_layers ,keep_prob, sequence_length):
lstm = tf.contrib.rnn.BasicLSTMCell(rnn_size)
lstm_dropout = tf.contrib.rnn.DropoutWrapper(lstm,input_keep_prob = keep_prob)
encoder_cell = tf.contrib.rnn.MultiRNNCell([lstm_dropout] * num_layers)
_, encoder_state = tf.nn.bidirectional_dynamic_rnn(cell_fw = encoder_cell,
cell_bw = encoder_cell,
sequence_length = sequence_length,
inputs = rnn_inputs,
dtype = tf.float32)
return encoder_state
#### decoding thne training set ###
def decode_training_set(encoder_state, decoder_cell,decoder_embedded_input,sequence_length,decoding_scope,output_function,keep_prob,batch_size):
attention_states = tf.zeros([batch_size, 1,decoder_cell.output_size])
attention_keys, attention_values, attention_score_function, attention_construct_function = tf.contrib.seq2seq.prepare_attention(attention_states, attention_option = 'bahdanau', num_units = decoder_cell.output_size)
training_decoder_funtion = tf.contrib.seq2seq.attention_decoder_fn_train(encoder_state[0],
attention_keys,
attention_values,
attention_score_function,
attention_construct_function,
name = "att_dec_train")
decoder_output,decoder_final_state, decoder_final_context_state = tf.contrib.seq2seq.dynamic_rnn_decoder(decoder_cell,
training_decoder_fuction,
decoder_embedded_input,
sequence_length,
scope = decoding_scope)
decoder_output_dropout = tf.nn.dropout(decoder_output, keep_prob)
return output_function(decoder_output_dropout)
#### decoding test/validation set ###
def decode_training_set(encoder_state, decoder_cell,decoder_embedding_matrix,sos_id,eos_id,maximum_length,num_words,sequence_length,decoding_scope,output_function,keep_prob,batch_size):
attention_states = tf.zeros([batch_size, 1,decoder_cell.output_size])
attention_keys, attention_values, attention_score_function, attention_construct_function = tf.contrib.seq2seq.prepare_attention(attention_states, attention_option = 'bahdanau', num_units = decoder_cell.output_size)
test_decoder_funtion = tf.contrib.seq2seq.attention_decoder_fn_inference(output_function,
encoder_state[0],
attention_keys,
attention_values,
attention_score_function,
attention_construct_function,
decoder_embedding_matrix,
sos_id,
eos_id,
maximum_length,
num_words,
name = "att_dec_inf")
test_predictions,decoder_final_state, decoder_final_context_state = tf.contrib.seq2seq.dynamic_rnn_decoder(decoder_cell,
training_decoder_fuction,
scope = decoding_scope)
return test_predictions
## decoder rnn
def decoder_rnn(decoder_embedded_inputs, decoder_embedding_matrix, encoder_state, num_words, sequence_length, rnn_size, num_layers, word2int, keep_prob, batch_size):
with tf.variable_scope("decoding") as decoding_scope:
lstm = tf.contrib.rnn.BasicLSTMCell(rnn_size)
lstm_dropout = tf.contrib.rnn.DropoutWrapper(lstm,input_keep_prob = keep_prob)
decoder_cell = tf.contrib.rnn.MultiRNNCell([lstm_dropout] * num_layers)
weights = tf.truncated_normal_initializer(stdev = 0.1)
biases = tf.zeros_initializer()
output_function = lambda x: tf.contrib.layers.fully_connected(x,
num_words,
None,
scope = decoding_scope,
weights_initializer = weights,
biases_initializer=biases)
training_predictions = decoder_training_set(encoder_state,
decoder_cell,
decoder_embedded_inputs,
sequence_length,
decoding_scope,
output_function,
keep_prob,
batch_size)
decoding_scope.reuse_variables()
test_predictions = decode_test_set(encoder_state,
decoder_cell,
decoder_embedding_matrix,
word2int['<SOS>'],
word2int['<EOS>'],
sequence_length - 1,
num_words,
decoding_scope,
output_function,
keep_prob,
batch_size)
return training_predictions,test_predictions
## building seq2seq model ##
def seq2seq_model(inputs, targets, keep_prob, batch_size, sequence_length, answers_num_words, questions_num_words, encoder_embedding_size, decoder_embedding_size, rnn_size, num_layers, questionsword2int):
encoder_embedded_input = tf.contrib.layers.embed_sequence(inputs,
answers_num_words + 1,
encoder_embedding_size,
initializer = tf.random_uniform_initializer(0,1))
encoder_state = encoder_rnn(encoder_embedded_input, rnn_size, num_layers, keep_prob, sequence_length)
preprocessed_targets = process_targets(targets, questionsword2int, batch_size)
decoder_embeddings_matrix = tf.variables(tf.random_uniform([questions_num_words + 1, decoder_embedding_size], 0,1))
decoder_embedded_inputs = tf.nn.embedding_lookup(decoder_embeddings_matrix, preprocessed_targets)
training_predictions, test_predictions = decoder_rnn(decoder_embedded_inputs,
decoder_ebeddings_matrix,
encoder_state,
questions_num_words,
sequence_length,
rnn_size,
num_layers,
questionwords2int,
keep_prob,
batch_size)
return training_predictions,test_predictions
## training ##
## metrics
epochs = 100
batch_size = 64
rnn_size = 512
num_layers = 3
encoder_embedding_size = 512
decoder_embedding_size = 512
learning_rate = 0.01
learning_rate_decay = 0.9
min_learning_rate = 0.0001
keep_probability = 0.5
## define session
tf.reset_default_graph()
session = tf.InteractiveSession()
## load model inputs ##
inputs, targets, lr, keep_prob = model_inputs()
## setting seq length
sequence_length = tf.placeholder_with_default(25 ,None, name = 'sequence_length')
## getting the shape of the inputs
input_shape = tf.shape(inputs)
##getting trainning and test predictions ##
training_predictions, test_predictions = seq2seq_model(tf.reverse(inputs, [-1]),
targets,
keep_prob,
batch_size,
sequence_length,
len(answerwords2int),
len(questionwords2int),
encoder_embedding_size,
decoder_embedding_size,
rnn_size,
num_layers,
questionwords2int)
##### and here is the error
questionwords2int)
Traceback (most recent call last):
File "<ipython-input-45-e10ed1ff7cf8>", line 12, in <module>
questionwords2int)
File "<ipython-input-38-1f6f97672855>", line 6, in seq2seq_model
encoder_state = encoder_rnn(encoder_embedded_input, rnn_size, num_layers, keep_prob, sequence_length)
File "<ipython-input-21-b9e4092e7b5d>", line 26, in encoder_rnn
dtype = tf.float32)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\rnn.py", line 350, in bidirectional_dynamic_rnn
time_major=time_major, scope=fw_scope)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\rnn.py", line 545, in dynamic_rnn
dtype=dtype)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\rnn.py", line 712, in _dynamic_rnn_loop
swap_memory=swap_memory)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 2626, in while_loop
result = context.BuildLoop(cond, body, loop_vars, shape_invariants)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 2459, in BuildLoop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 2409, in _BuildLoop
body_result = body(*packed_vars_for_body)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\rnn.py", line 695, in _time_step
skip_conditionals=True)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\rnn.py", line 177, in _rnn_step
new_output, new_state = call_cell()
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\rnn.py", line 683, in <lambda>
call_cell = lambda: cell(input_t, state)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\contrib\rnn\python\ops\core_rnn_cell_impl.py", line 655, in __call__
cur_inp, new_state = cell(cur_inp, cur_state)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\contrib\rnn\python\ops\core_rnn_cell_impl.py", line 524, in __call__
output, new_state = self._cell(inputs, state, scope)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\contrib\rnn\python\ops\core_rnn_cell_impl.py", line 179, in __call__
concat = _linear([inputs, h], 4 * self._num_units, True, scope=scope)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\contrib\rnn\python\ops\core_rnn_cell_impl.py", line 747, in _linear
"weights", [total_arg_size, output_size], dtype=dtype)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 988, in get_variable
custom_getter=custom_getter)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 890, in get_variable
custom_getter=custom_getter)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 348, in get_variable
validate_shape=validate_shape)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 333, in _true_getter
caching_device=caching_device, validate_shape=validate_shape)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 639, in _get_single_variable
name, "".join(traceback.format_list(tb))))
ValueError: Variable bidirectional_rnn/fw/multi_rnn_cell/cell_0/basic_lstm_cell/weights already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\framework\ops.py", line 1264, in __init__
self._traceback = _extract_stack()
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\framework\ops.py", line 2395, in create_op
original_op=self._default_original_op, op_def=op_def)
File "C:\Users\Ahmad Al-Bargouthy\Anaconda3\envs\chatbot\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 763, in apply_op
op_def=op_def)