Fatal编程技术网
  • python/
  • Python kears Conv1D上的负维度大小

Python kears Conv1D上的负维度大小

python keras

Python kears Conv1D上的负维度大小,python,keras,convolutional-neural-network,Python,Keras,Convolutional Neural Network,我正在使用Keras的模型api对大小为20的输入1D向量应用1D卷积。我要五粒，每粒3号。输入将为形状（无，1,20）（大小为20的1D向量的可变数量） 该模型的摘要如下： _________________________________________________________________ Layer (type) Output Shape Param # ==============================

我正在使用Keras的模型api对大小为20的输入1D向量应用1D卷积。我要五粒，每粒3号。输入将为形状
（无，1,20）
（大小为20的1D向量的可变数量）

该模型的摘要如下：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         (None, None, 20)          0         
_________________________________________________________________
conv1d_1 (Conv1D)            (None, None, 5)           305       
_________________________________________________________________
dense_1 (Dense)              (None, None, 1)           6         
=================================================================
Total params: 311
Trainable params: 311
Non-trainable params: 0

train\u x
的形状为
（无，1，20）
，
train\u标签的形状为
（无，1）

错误来自卷积层-


    Caused by op 'conv1d_1/convolution/Conv2D', defined at:
  File "/home/user/Desktop/hack/imlhack2018/conv_nn.py", line 72, in <module>
    main()
  File "/home/user/Desktop/hack/imlhack2018/conv_nn.py", line 42, in main
    conv = Conv1D(filters=5, kernel_size=3, activation=keras.activations.relu, input_shape=(None,20, 1))(input)
  File "/home/user/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py", line 596, in __call__
    output = self.call(inputs, **kwargs)
  File "/home/user/anaconda3/lib/python3.6/site-packages/keras/layers/convolutional.py", line 156, in call
    dilation_rate=self.dilation_rate[0])
  File "/home/user/anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 3116, in conv1d
    data_format=tf_data_format)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 670, in convolution
    op=op)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 338, in with_space_to_batch
    return op(input, num_spatial_dims, padding)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 662, in op
    name=name)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 116, in _non_atrous_convolution
    name=scope)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 2010, in conv1d
    data_format=data_format)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 399, in conv2d
    data_format=data_format, name=name)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
    op_def=op_def)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2506, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1269, in __init__
    self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): computed output size would be negative
     [[Node: conv1d_1/convolution/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/cpu:0"](conv1d_1/convolution/ExpandDims, conv1d_1/convolution/ExpandDims_1)]]



由op'conv1d_1/卷积/Conv2D'引起，定义于：
文件“/home/user/Desktop/hack/imlhack2018/conv_nn.py”，第72行，在
main（）
文件“/home/user/Desktop/hack/imlhack2018/conv_nn.py”，主文件第42行
conv=Conv1D（filters=5，kernel_size=3，activation=keras.activations.relu，input_shape=（无，20，1））（输入）
文件“/home/user/anaconda3/lib/python3.6/site packages/keras/engine/topology.py”，第596行，在调用中__
输出=自调用（输入，**kwargs）
文件“/home/user/anaconda3/lib/python3.6/site packages/keras/layers/convolutional.py”，第156行，调用中
膨胀率=自膨胀率[0]）
conv1d中的文件“/home/user/anaconda3/lib/python3.6/site packages/keras/backend/tensorflow_backend.py”，第3116行
数据_格式=tf_数据_格式）
文件“/home/user/anaconda3/lib/python3.6/site packages/tensorflow/python/ops/nn_ops.py”，第670行，卷积格式
op=op）
文件“/home/user/anaconda3/lib/python3.6/site packages/tensorflow/python/ops/nn_ops.py”，第338行，带批处理空间
返回操作（输入、数字空间、填充）
文件“/home/user/anaconda3/lib/python3.6/site packages/tensorflow/python/ops/nn_ops.py”，第662行，op
名称=名称）
文件“/home/user/anaconda3/lib/python3.6/site packages/tensorflow/python/ops/nn_ops.py”，第116行，在非阿托拉斯卷积中
名称=范围）
文件“/home/user/anaconda3/lib/python3.6/site packages/tensorflow/python/ops/nn_ops.py”，第2010行，conv1d格式
数据格式=数据格式）
conv2d中的第399行文件“/home/user/anaconda3/lib/python3.6/site packages/tensorflow/python/ops/gen_nn_ops.py”
数据格式=数据格式，名称=名称）
文件“/home/user/anaconda3/lib/python3.6/site packages/tensorflow/python/framework/op_def_library.py”，第767行，在apply_op
op_def=op_def）
文件“/home/user/anaconda3/lib/python3.6/site packages/tensorflow/python/framework/ops.py”，第2506行，在create_op中
初始值=自身值。\默认值\初始值，初始值=初始值）
文件“/home/user/anaconda3/lib/python3.6/site packages/tensorflow/python/framework/ops.py”，第1269行，在__
self.\u traceback=\u extract\u stack（）
InvalidArgumentError（回溯见上文）：计算的输出大小为负数
[[Node:conv1d_1/Conv2D/Conv2D=Conv2D[T=DT_FLOAT，data_format=“NHWC”，padding=“VALID”，strips=[1,1,1,1]，在/u gpu=true上使用/u cudnn\u，\u device=“/job:localhost/replica:0/任务：0/cpu:0”]（conv1d_1/卷积/ExpandDims，conv1d_1/卷积/ExpandDims\u 1）]]


当我将
padding=“same”
添加到卷积层时，一切似乎都正常工作。这种行为的原因是什么？
您的输入形状是（1，20），它被解释为1个宽度，20个通道的数组。您可能需要相反的宽度，即宽度20和1通道。由于数组只有一个元素，在不填充相同元素的情况下执行卷积将导致负维度，从而产生错误


请注意，卷积总是在空间维度上执行，对于Conv1D，它是形状数组中倒数第二个维度。最后一个维度表示通道。
在正式文档中，它写道“当将此层用作模型的第一层时，提供一个输入形状参数（整数元组或无元组，不包括批处理轴）”。我很困惑，为什么它在输入层中声明了conv1D的输入形状，问题是？还包括model.summary（）@MatiasValdenegro的输出问题当然是如何解决错误

    Caused by op 'conv1d_1/convolution/Conv2D', defined at:
  File "/home/user/Desktop/hack/imlhack2018/conv_nn.py", line 72, in <module>
    main()
  File "/home/user/Desktop/hack/imlhack2018/conv_nn.py", line 42, in main
    conv = Conv1D(filters=5, kernel_size=3, activation=keras.activations.relu, input_shape=(None,20, 1))(input)
  File "/home/user/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py", line 596, in __call__
    output = self.call(inputs, **kwargs)
  File "/home/user/anaconda3/lib/python3.6/site-packages/keras/layers/convolutional.py", line 156, in call
    dilation_rate=self.dilation_rate[0])
  File "/home/user/anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 3116, in conv1d
    data_format=tf_data_format)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 670, in convolution
    op=op)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 338, in with_space_to_batch
    return op(input, num_spatial_dims, padding)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 662, in op
    name=name)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 116, in _non_atrous_convolution
    name=scope)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 2010, in conv1d
    data_format=data_format)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 399, in conv2d
    data_format=data_format, name=name)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
    op_def=op_def)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2506, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/home/user/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1269, in __init__
    self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): computed output size would be negative
     [[Node: conv1d_1/convolution/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/cpu:0"](conv1d_1/convolution/ExpandDims, conv1d_1/convolution/ExpandDims_1)]]