不兼容的形状：[84,6] 与 [128,6]。 第一个纪元结束时出错

Question

This is the model that I built. Please do help me understand if the problem with my model or any other problem I am facing this issue. The error occurs after this:

Train on 63828 samples, validate on 95743 samples
Epoch 1/1
63744/63828 [============================>.] - ETA: 2s - loss: 0.3427 - acc: 0.9943

The error occurs at the end. So I removed the avlidation set during training.

from tensorflow.python.keras.layers import Embedding, Input
from tensorflow.python.keras.layers import LSTM, Bidirectional, GlobalMaxPool1D, Dropout

embedding_layer = Embedding(num_of_words, EMBEDDING_DIM, weights=[embedding_matrix], input_length=MAX_SEQUENCE_LENGTH, trainable=False)
#building the model
#INPUT LAYER
input_layer = Input((MAX_SEQUENCE_LENGTH,))
#EMBEDDING LAYER
embedding_layer = embedding_layer(input_layer)
#BI-LSTM LAYER
lstm_layer_output = Bidirectional(LSTM(128, return_sequences=True))(embedding_layer)

lstm, forward_h, forward_c, backward_h, backward_c = Bidirectional \
    (LSTM
     (128,
      dropout=0.2,
      return_sequences=True,
      return_state=True,
      recurrent_activation='relu',
      recurrent_initializer='glorot_uniform'))(embedding_layer)




from tensorflow.python.keras import backend as K
#CNN LAYER WITH KERNELS 3,4,5
from tensorflow.python.keras.layers import Conv1D, MaxPooling1D
first_conv_layer = Conv1D(128, 3, activation='relu')(lstm_layer_output)
first_max_pooling_layer = MaxPooling1D(3)(first_conv_layer)
second_conv_layer = Conv1D(128, 4, activation='relu')(first_max_pooling_layer)
second_max_pooling_layer = MaxPooling1D(4)(second_conv_layer)
third_conv_layer = Conv1D(128, 5, activation='relu')(second_max_pooling_layer)
#third_max_pooling_layer = MaxPooling1D(5)(third_conv_layer)
global_max_pooling = GlobalMaxPool1D()(third_conv_layer)



#from tensorflow.python.keras.layers import Concatenate
#merged_pooling_layers = Concatenate(axis=1)([first_max_pooling_layer,second_max_pooling_layer,third_max_pooling_layer])
#global_max_pooling = GlobalMaxPool1D()(merged_pooling_layers)


#implementing attentionlayer manually
from tensorflow.python.keras.layers import Add
rnn_output = Add()([forward_h,backward_h])

hidden_size = int(lstm.shape[2])
from tensorflow.python.keras.layers import Lambda
hsf = Lambda(lambda x: x[:, -1], output_shape=(hidden_size,), name='last_hidden_state_forward')(rnn_output)
from tensorflow.python.keras.layers import Multiply
from tensorflow.python.keras.layers import Lambda
def norm(m):
    return K.transpose(m)

u_t = Multiply()([Lambda(norm)(rnn_output),hsf])
context_vector = Multiply()([u_t,global_max_pooling])




def ex(m):
    return K.exp(context_vector)
exp_u_t = Lambda(ex)(context_vector)

from tensorflow.python.keras.layers import Dense
attention_vector = Dense(128,activation='softmax')(exp_u_t)
x = Dense(64,activation="softmax")(weighted_input)
output_layer = Dense(6,activation="softmax")(x)

from tensorflow.python.keras.models import Model
from tensorflow.python.keras.optimizers import Adam
model = Model(input_layer,output_layer)
from tensorflow.python.keras import optimizers

model.compile(
        loss='categorical_crossentropy',
        optimizer='sgd',
        metrics=['accuracy']
        )



print('Training model...')
r = model.fit(
            data,
            target_values,
            batch_size=128,
            epochs=1,
            validation_split=0.0     
            )

The error I got is this:

InvalidArgumentError (see above for traceback): Incompatible shapes: [84,6] vs. [128,6]
     [[Node: training/SGD/gradients/loss/dense_3_loss/mul_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _class=["loc:@training/SGD/gradients/loss/dense_3_loss/mul_grad/Reshape_1"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](training/SGD/gradients/loss/dense_3_loss/mul_grad/Shape, training/SGD/gradients/loss/dense_3_loss/mul_grad/Shape_1)]]

Please help me fix this problem.Thank you

Edit: This is the traceback of the error

Epoch 1/1
31872/31914 [============================>.] - ETA: 1s - loss: 0.2419   Traceback (most recent call last):

  File "<ipython-input-1-a7cc2e59a772>", line 165, in <module>
    validation_split=0.8

  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\engine\training.py", line 1216, in fit
    validation_steps=validation_steps)

  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\engine\training_arrays.py", line 245, in fit_loop
    outs = f(ins_batch)

  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\backend.py", line 2824, in __call__
    fetches=fetches, feed_dict=feed_dict, **self.session_kwargs)

  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 900, in run
    run_metadata_ptr)

  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1135, in _run
    feed_dict_tensor, options, run_metadata)

  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1316, in _do_run
    run_metadata)

  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1335, in _do_call
    raise type(e)(node_def, op, message)

InvalidArgumentError: Incompatible shapes: [128,6] vs. [42,6]
     [[Node: training/SGD/gradients/loss/dense_3_loss/logistic_loss/mul_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _class=["loc:@training/SGD/gradients/loss/dense_3_loss/logistic_loss/mul_grad/Reshape"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](training/SGD/gradients/loss/dense_3_loss/logistic_loss/mul_grad/Shape, training/SGD/gradients/loss/dense_3_loss/logistic_loss/mul_grad/Shape_1)]]

Caused by op 'training/SGD/gradients/loss/dense_3_loss/logistic_loss/mul_grad/BroadcastGradientArgs', defined at:
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 268, in <module>
    main()
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 264, in main
    kernel.start()
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 478, in start
    self.io_loop.start()
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\zmq\eventloop\ioloop.py", line 177, in start
    super(ZMQIOLoop, self).start()
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tornado\ioloop.py", line 888, in start
    handler_func(fd_obj, events)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 283, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 233, in dispatch_shell
    handler(stream, idents, msg)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 399, in execute_request
    user_expressions, allow_stdin)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 208, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 537, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2728, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2850, in run_ast_nodes
    if self.run_code(code, result):
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2910, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-1-a7cc2e59a772>", line 165, in <module>
    validation_split=0.8
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\engine\training.py", line 1216, in fit
    validation_steps=validation_steps)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\engine\training_arrays.py", line 90, in fit_loop
    model._make_train_function()
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\engine\training.py", line 572, in _make_train_function
    params=self._collected_trainable_weights, loss=self.total_loss)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\optimizers.py", line 208, in get_updates
    grads = self.get_gradients(loss, params)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\optimizers.py", line 114, in get_gradients
    grads = K.gradients(loss, params)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\backend.py", line 2866, in gradients
    loss, variables, colocate_gradients_with_ops=True)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\ops\gradients_impl.py", line 494, in gradients
    gate_gradients, aggregation_method, stop_gradients)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\ops\gradients_impl.py", line 636, in _GradientsHelper
    lambda: grad_fn(op, *out_grads))
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\ops\gradients_impl.py", line 385, in _MaybeCompile
    return grad_fn()  # Exit early
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\ops\gradients_impl.py", line 636, in <lambda>
    lambda: grad_fn(op, *out_grads))
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\ops\math_grad.py", line 874, in _MulGrad
    rx, ry = gen_array_ops.broadcast_gradient_args(sx, sy)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 673, in broadcast_gradient_args
    "BroadcastGradientArgs", s0=s0, s1=s1, name=name)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3392, in create_op
    op_def=op_def)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1718, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

...which was originally created as op 'loss/dense_3_loss/logistic_loss/mul', defined at:
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 268, in <module>
    main()
[elided 16 identical lines from previous traceback]
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2910, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-1-a7cc2e59a772>", line 153, in <module>
    optimizer='sgd',
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\engine\training.py", line 428, in compile
    output_loss = weighted_loss(y_true, y_pred, sample_weight, mask)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\engine\training_utils.py", line 438, in weighted
    score_array = fn(y_true, y_pred)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\losses.py", line 116, in binary_crossentropy
    return K.mean(K.binary_crossentropy(y_true, y_pred), axis=-1)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\keras\_impl\keras\backend.py", line 3448, in binary_crossentropy
    return nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\ops\nn_impl.py", line 181, in sigmoid_cross_entropy_with_logits
    relu_logits - logits * labels,
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\ops\math_ops.py", line 979, in binary_op_wrapper
    return func(x, y, name=name)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\ops\math_ops.py", line 1211, in _mul_dispatch
    return gen_math_ops.mul(x, y, name=name)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 4758, in mul
    "Mul", x=x, y=y, name=name)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3392, in create_op
    op_def=op_def)
  File "C:\Users\JCMat\New\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1718, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): Incompatible shapes: [128,6] vs. [42,6]
     [[Node: training/SGD/gradients/loss/dense_3_loss/logistic_loss/mul_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _class=["loc:@training/SGD/gradients/loss/dense_3_loss/logistic_loss/mul_grad/Reshape"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](training/SGD/gradients/loss/dense_3_loss/logistic_loss/mul_grad/Shape, training/SGD/gradients/loss/dense_3_loss/logistic_loss/mul_grad/Shape_1)]]

Answer 1

The issue is that your last batch doesn't contain 128 rows, but only 84, since the length of your dataset isn't divisible without a remainder. Either try to adjust your code to allow for dynamic rows, or maybe try padding the last batch.