ValueError: Невозможно передать значение shape (2, 4) для Tensor u'InputData / X: 0 ', имеющего shape' (?, 2, 4

Question

Я получил ошибку, ValueError: Невозможно передать значение shape (2, 4) для Tensor u'InputData / X: 0 ', которое имеет форму' (?, 2, 4, 104) '. Я написал коды,

# coding: utf-8
import tensorflow as tf
import tflearn

from tflearn.layers.core import input_data,dropout,fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.estimator import regression

import pandas as pd
import numpy as np
from sklearn import metrics

tf.reset_default_graph()
net = input_data(shape=[2, 4, 104])
net = conv_2d(net, 4, 16, activation='relu')
net = max_pool_2d(net, 1)
net = tflearn.activations.relu(net)
net = dropout(net, 0.5)
net = tflearn.fully_connected(net, 10, activation='softmax')
net = tflearn.regression(net, optimizer='adam', learning_rate=0.5, loss='categorical_crossentropy')

model = tflearn.DNN(net)

trainDataSet = [[0.25,0.25,1,1],[0,0,1,1],[0.25,0.25,1,1]]
trainLabel = [[0,1],[0,1],[1,0]]
model.fit(trainDataSet, trainLabel, n_epoch=100, batch_size=32, validation_set=0.1, show_metric=True)

Traceback говорит

Traceback (most recent call last):
  File "cnn.py", line 16, in <module>
    model.fit(trainDataSet, trainLabel, n_epoch=100, batch_size=32, validation_set=0.1, show_metric=True)
  File "/Users/xxx/anaconda/xxx/lib/python2.7/site-packages/tflearn/models/dnn.py", line 216, in fit
    callbacks=callbacks)
  File "/Users/xxx/anaconda/xxx/lib/python2.7/site-packages/tflearn/helpers/trainer.py", line 339, in fit
    show_metric)
  File "/Users/xxx/anaconda/xxx/lib/python2.7/site-packages/tflearn/helpers/trainer.py", line 818, in _train
    feed_batch)
  File "/Users/xxx/anaconda/xxx/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 929, in run
    run_metadata_ptr)
  File "/Users/xxx/anaconda/xxx/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1128, in _run
    str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (2, 4) for Tensor u'InputData/X:0', which has shape '(?, 2, 4, 104)'

Я переписал в

trainDataSet = np.array([[0.25,0.25,1,1],[0,0,1,1],[0.25,0.25,1,1]])
trainLabel = np.array([[0,1],[0,1],[1,0]])

но такая же ошибка. Что не так в моих кодах? Как это исправить?

Answer 1

Ссылаясь на документацию Tensorflow :

tflearn.layers.conv.conv_2d 

Введите:

Тензор 4-D [партия, высота, ширина, in_channels].

Из другой документации Tensorflow:

tf.nn.conv2d

Вычисляет 2-мерную свертку, заданную 4-D входной и тензор фильтра.

С учетом входного тензора формы [batch, in_height, in_width, in_channels] и тензор формы фильтра / ядра [filter_height, filter_width, in_channels, out_channels], эта операция выполняет следующее:

Ваш набор данных, метка и форма ввода не совпадают, т. Е. Не соответствуют друг другу.

В настоящее время ваш trainDataSet имеет форму (3,4):

import numpy as np
trainDataSet = np.array([[0.25,0.25,1,1],[0,0,1,1],[0.25,0.25,1,1]])
print(trainDataSet.shape)

Из:

(3, 4)

Но вы определили форму ввода как:

net = input_data(shape=[2, 4, 104])

Неопределенно, чего вы действительно хотите достичь, но если вы хотите увидеть простой рабочий пример, ваш код должен выглядеть следующим образом:

import tensorflow as tf
import tflearn

from tflearn.layers.core import input_data,dropout,fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.estimator import regression

import pandas as pd
import numpy as np
from sklearn import metrics

tf.reset_default_graph()
net = input_data(shape=[3, 4, 1])
net = conv_2d(net, 4, 16, activation='relu')
net = max_pool_2d(net, 1)
net = tflearn.activations.relu(net)
net = dropout(net, 0.5)
net = tflearn.fully_connected(net, 2, activation='softmax')
net = tflearn.regression(net, optimizer='adam', learning_rate=0.5, loss='categorical_crossentropy')

model = tflearn.DNN(net)

trainDataSet = [
    [
        [[0.25], [0.25], [1], [1]],
        [[0], [0], [1], [1]],
        [[0.25], [0.25], [1], [1]]
    ],
    [
        [[0.25], [0.25], [1], [1]],
        [[0], [0], [1], [1]],
        [[0.25], [0.25], [1], [1]]
    ],
    [
        [[0.25], [0.25], [1], [1]],
        [[0], [0], [1], [1]],
        [[0.25], [0.25], [1], [1]]
    ]
]

trainLabel = [[0,1],[0,1],[1,0]]
model.fit(trainDataSet, trainLabel, n_epoch=100, batch_size=32, validation_set=0.1, show_metric=True)

Из:

---------------------------------
Run id: NHHJV7
Log directory: /tmp/tflearn_logs/
INFO:tensorflow:Summary name Accuracy/ (raw) is illegal; using Accuracy/__raw_ instead.
---------------------------------
Training samples: 2
Validation samples: 1
--
Training Step: 1  | time: 1.160s
| Adam | epoch: 001 | loss: 0.00000 - acc: 0.0000 | val_loss: 23.02585 - val_acc: 0.0000 -- iter: 2/2
--
Training Step: 2  | total loss: 0.62966 | time: 1.008s
| Adam | epoch: 002 | loss: 0.62966 - acc: 0.0000 | val_loss: 10.76885 - val_acc: 0.0000 -- iter: 2/2
.
.
.
Training Step: 99  | total loss: 0.00000 | time: 1.013s
| Adam | epoch: 099 | loss: 0.00000 - acc: 1.0000 | val_loss: 23.02585 - val_acc: 0.0000 -- iter: 2/2
--
Training Step: 100  | total loss: 0.00000 | time: 1.011s
| Adam | epoch: 100 | loss: 0.00000 - acc: 1.0000 | val_loss: 23.02585 - val_acc: 0.0000 -- iter: 2/2
--