同一模型架构的Keras模型和Caffe模型的输出形状不同

时间:2018-08-24 09:20:26

标签: python tensorflow keras deep-learning caffe

在Keras中,应用Convolution2D图层后,​​图像的输出形状会改变1,但是当我们对Caffe应用相同的模型时,该图像的输出形状会起作用。我正在复制IS&T 2017论文的结果。在那篇论文中,他们正在使用具有类似模型的Caffe。

Model Summary

我的模型摘要:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 61, 61, 32)        1568      
_________________________________________________________________
**max_pooling2d_1 (MaxPooling2 (None, 30, 30, 32)        0**         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 26, 26, 48)        38448     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 13, 13, 48)        0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 9, 9, 64)          76864     
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 4, 4, 64)          0         

---------------------------------------------------------------------

这会导致此错误

ValueError: Negative dimension size caused by subtracting 5 from 4 for 'conv2d_4/convolution' (op: 'Conv2D') with input shapes: [?,4,4,64], [5,5,64,128].

所有尺寸和补丁大小均相同。

0 个答案:

没有答案