Tensorflow/TFLearn 中的数据结构差异

Question

我有两个数据集，就像：

input:
array([[[ 0.99309823],
           ...
        [ 0.        ]]])

shape : (1, 2501)

output:
array([[0, 0, 0, ..., 0, 0, 1],
       ..., 
       [0, 0, 0, ..., 0, 0, 0]])
shape : (2501, 9)

然后我用TFLearn处理了它；作为

input_layer = tflearn.input_data(shape=[None,2501])
hidden1 = tflearn.fully_connected(input_layer,1205,activation='ReLU', regularizer='L2', weight_decay=0.001)
dropout1 = tflearn.dropout(hidden1,0.8)

hidden2 = tflearn.fully_connected(dropout1,1205,activation='ReLU', regularizer='L2', weight_decay=0.001)
dropout2 = tflearn.dropout(hidden2,0.8)
softmax = tflearn.fully_connected(dropout2,9,activation='softmax')

# Regression with SGD
sgd = tflearn.SGD(learning_rate=0.1,lr_decay=0.96, decay_step=1000)
top_k=tflearn.metrics.Top_k(3)
net = tflearn.regression(softmax,optimizer=sgd,metric=top_k,loss='categorical_crossentropy')

model = tflearn.DNN(net)
model.fit(input,output,n_epoch=10,show_metric=True, run_id='dense_model')

它有效，但不是我想要的方式。这是一个 DNN 模型。我希望当我输入 0.95 时，模型必须给我相应的预测，例如 [0,0,0,0,0,0,0,0,1]。但是，当我想输入0.95时，它说，

ValueError: Cannot feed value of shape (1,) for Tensor 'InputData/X:0', which has shape '(?, 2501)'

当我试图理解时，我意识到我需要 (1,2501) 形状的数据来预测我基于错误的模型。

我想要的是针对输入中的每个元素，预测输出中对应的元素。可以看到，在实例数据集中，

对于[0.99309823]，对应的输出为[0,0,0,0,0,0,0,0,1]。我想让 tflearn 像这样训练自己。

我可能有错误的结构化数据或模型（可能是数据集），我解释了所有事情，我需要帮助我真的疯了。

Answer 1

您的输入数据应为 Nx1（N = 样本数）维以存档此转换（[0.99309823] --> [0,0, 0,0,0,0,0,0,1]）。根据您的输入数据形状，它看起来更有可能包含 1 个 2501 维的样本。

ValueError: Cannot feed value of shape (1,) for Tensor 'InputData/X:0', which has shape '(?, 2501)' 此错误意味着 tensorflow 期望您提供形状为 (,2501) 的向量，但您正在为网络提供形状为 (1,).
带有虚拟数据的示例修改代码：

import numpy as np
import tflearn

#creating dummy data
input_data = np.random.rand(1, 2501)
input_data = np.transpose(input_data) # now shape is (2501,1)
output_data = np.random.randint(8, size=2501)
n_values = 9
output_data = np.eye(n_values)[output_data]

# checking the shapes
print input_data.shape #(2501,1)
print output_data.shape #(2501,9)

input_layer = tflearn.input_data(shape=[None,1]) # now network is expecting ( Nx1 )
hidden1 = tflearn.fully_connected(input_layer,1205,activation='ReLU', regularizer='L2', weight_decay=0.001)
dropout1 = tflearn.dropout(hidden1,0.8)

hidden2 = tflearn.fully_connected(dropout1,1205,activation='ReLU', regularizer='L2', weight_decay=0.001)
dropout2 = tflearn.dropout(hidden2,0.8)
softmax = tflearn.fully_connected(dropout2,9,activation='softmax')

# Regression with SGD
sgd = tflearn.SGD(learning_rate=0.1,lr_decay=0.96, decay_step=1000)
top_k=tflearn.metrics.Top_k(3)
net = tflearn.regression(softmax,optimizer=sgd,metric=top_k,loss='categorical_crossentropy')
model = tflearn.DNN(net)
model.fit(input_data, output_data, n_epoch=10,show_metric=True, run_id='dense_model')

Answer 2

我的朋友也警告过我关于 rcmalli 的同样事情。他说重塑：

input = tf.reshape(input, (2501,1))

改变

input_layer = tflearn.input_data(shape=[None,2501])

到

input_layer = tflearn.input_data(shape=[None, 1])

可变维度必须是 "None"。在你的错误情况下，2501 是你的数据集的幅度（或其他东西，我从另一个语言翻译而来，但你明白了）。 1 是恒定输入幅度。

Tensorflow/TFLearn 中的数据结构差异

Data Structure Discrepancy in Tensorflow/TFLearn

python

neural-network

deep-learning

tensorflow

tflearn