Stack Overflow
Stack Overflow

Questions tagged [max-pooling]

For questions about max pooling (as well as average pooling) operation, commonly used in convolutional neural networks for downsampling.

157 questions
0
votes
1 answer

Why does maxpooling select maximum value to represent a range?

Maxpooling is a technique I read about it here https://computersciencewiki.org/index.php/Max-pooling_/_Pooling. I understand, that it is used to approximate the input. Which is to reduce the time a neural network may spend working on it. What I…
whitespace
  • 789
  • 6
  • 13
0
votes
0 answers

maxpooling2d keras does not do pooling at all

I am writing a CNN for text classification. The max pooling2D layer seems does not work as the output shape is same as conv2D. I have attached my code and output shape below. Thanks for helping me! from keras.layers import Dense, Input, Flatten …
Cindy
  • 43
  • 1
  • 7
0
votes
0 answers

CNN non-conventional downsampling

I am new to CNNs and am building a model using Keras to combine inputs from multiple sources. Two of my sources have different dimensions and cannot be scaled by an integer number (i.e., x2 or x3 smaller). Therefore, simply max-pooling will not…
Jeff Lapierre
  • 60
  • 5
0
votes
1 answer

Extract patches similar to that of max pooling or separable convolution

I am trying to create a custom layer that is similar to Max Pooling or the first step of a separable convolution. For example with a 2-Tensor in which I want to extract the non-overlapping 2x2 patches: if I have the [4,4] tensor [[ 0, 1, 2, 3], […
Ross
  • 567
  • 1
  • 4
  • 8
0
votes
1 answer

How can I overcome that my output shape decreases as I keep on Maxpooling per layer?

I am building a 1D Convolutional Neural Network (CNN). From many sources I have understood that performance of the CNN increases if more layers are added. However, at each pooling layer, my output shape is 50% smaller than my input (because I use a…
Emil
  • 1,531
  • 3
  • 22
  • 47
0
votes
1 answer

Modifying maxpooling layer in Resnet50 keras.applications

I am working on a segmentation project and was wondering if there is a way to modify the resent50 maxpooling layer in keras.application. I'm using keras.application in a Kaggle kernel and was wondering if I could update the layer through code. x =…
Green
  • 695
  • 2
  • 9
  • 21
0
votes
1 answer

Has anyone written weldon pooling for keras?

Has the Weldon pooling [1] been implemented in Keras? I can see that it has been implemented in pytorch by the authors [2] but cannot find a keras equivalent. [1] T. Durand, N. Thome, and M. Cord. Weldon: Weakly su- pervised learning of deep…
biogeek
  • 561
  • 1
  • 4
  • 13
0
votes
1 answer

How to improve the performance of my model with Keras Conv1D and Maxpooling1D

I work on the data of Facebook Babi Task, and after using the model with LSTM (as defined on this github https://github.com/fchollet/keras/blob/master/examples/babi_rnn.py ). Now I want to use a model with convolution and Maxpooling to learn. But…
asmiou
  • 1
  • 6
0
votes
0 answers

Problems with layers dimensions in CNN

I took this neural network configuration from https://arxiv.org/pdf/1603.01068.pdf and I do not understand why Matlab says that layer 8 cannot accept the data from layer 7 due to dimensions problems. These are the layers: layers = [ …
Luca Di Liello
  • 1,486
  • 2
  • 17
  • 34
0
votes
1 answer

maxpooling error in Tenssoflow ;Check failed: dnnPoolingCreateForward_F32(..) == E_SUCCESS (-127 vs. 0)

I am learning tesnorflow from this blog: http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/ The code i am running is : https://github.com/dennybritz/cnn-text-classification-tf/blob/master/train.py I have…
rakeshKM
  • 53
  • 6
0
votes
1 answer

How can I get D averages from a HxWxD tensor

How can I create a graph element in Deeplearnjs which turns my [h, w, d] shape tensor in to one which is [d] shape where each is the max of that layer. If h and w are the same, this can be done with the maxpool function. If like the same for mean.…
MattD
  • 1,324
  • 4
  • 14
  • 28
0
votes
1 answer

In Torch/Lua can I split/concat tensors as they flow through a network?

I'm a novice with Lua/Torch. I have an existing model that includes a max pooling layer. I want to take the input into that layer and split it into chunks, feeding each chunk into a new max pooling layer. I have written a stand-alone Lua script…
stu176
  • 33
  • 1
  • 4
0
votes
0 answers

how is the dimension of the activation being as an input to the pooling layer

I am using alexnet, you can see the structure of the network as following: Alexnet structure with outputs I used the activations function in Matlab to get the features of my data from the output of conv5 layer. The output is a feature vector with a…
Meme
  • 55
  • 1
  • 7
0
votes
2 answers

Understanding Tensorflow maxpooling

I am unable to understand why tensorflow maxpooling with my parameters. When performed a maxpool with ksize=2 and strides=2 i get the following output with both padding SAME and padding VALID input : (?, 28, 28, 1) conv2d_out : (?, 28, 28,…
Ansh David
  • 654
  • 1
  • 10
  • 26
0
votes
1 answer

TensorFlow max_pool2d wrong output size

I'm trying to use a max pool layer with filter size 2x2, so I expect the output size to be roughly half the input size. The input size is 9x14x64, but for some reason the output size is 7x12x64 (see the attached TensorBoard graph). Here is the…
doetensor
  • 1
1 2 3
…
10
11