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.

122 questions
51
votes
2 answers

What is the difference between Keras' MaxPooling1D and GlobalMaxPooling1D functions?

Both MaxPooling1D and GlobalMaxPooling1D are described as a max pooling operation for temporal data. keras.layers.pooling.MaxPooling1D(pool_size=2, strides=None, padding='valid') I understand that GlobalMaxPooling1D takes no input parameters.…
KayBay
  • 669
  • 1
  • 5
  • 9
44
votes
5 answers

how to perform max/mean pooling on a 2d array using numpy

Given a 2D(M x N) matrix, and a 2D Kernel(K x L), how do i return a matrix that is the result of max or mean pooling using the given kernel over the image? I'd like to use numpy if possible. Note: M, N, K, L can be both even or odd and they need not…
rapidclock
  • 1,346
  • 2
  • 14
  • 28
33
votes
1 answer

Max pool layer vs Convolution with stride performance

In most of the architectures, conv layers are being followed by a pooling layer (max / avg etc.). As those pooling layers are just selecting the output of previous layer (i.e. conv), can we just use convolution with stride 2 and expect the similar…
Deniz Beker
  • 1,474
  • 1
  • 15
  • 21
15
votes
7 answers

numpy create array of the max of consecutive pairs in another array

I have a numpy array: A = np.array([8, 2, 33, 4, 3, 6]) What I want is to create another array B where each element is the pairwise max of 2 consecutive pairs in A, so I get: B = np.array([8, 33, 33, 4, 6]) Any ideas on how to implement? Any ideas…
GalSuchetzky
  • 740
  • 17
12
votes
2 answers

Pooling vs Pooling-over-time

I understand conceptually what is happening in a max/sum pool as a CNN layer operation, but I see this term "max pool over time", or "sum pool over time" thrown around (e.g., "Convolutional Neural Networks for Sentence Classification" paper by Yoon…
Matt
  • 1,159
  • 3
  • 16
  • 29
9
votes
2 answers

TensorFlow: Why does avg_pool ignore one stride dimension?

I am attempting to stride over the channel dimension, and the following code exhibits surprising behaviour. It is my expectation that tf.nn.max_pool and tf.nn.avg_pool should produce tensors of identical shape when fed the exact same arguments. This…
oarfish
  • 3,240
  • 4
  • 25
  • 54
8
votes
1 answer

In PyTorch's "MaxPool2D", is padding added depending on "ceil_mode"?

In MaxPool2D the padding is by default set to 0 and the ceil_mode is also set to False. Now, if I have an input of size 7x7 with kernel=2,stride=2 the output shape becomes 3x3, but when I use ceil_mode=True, it becomes 4x4, which makes sense because…
paul-shuvo
  • 1,532
  • 2
  • 23
  • 35
8
votes
0 answers

Backpropagation for Max-Pooling Layers: Multiple Maximum Values

I am currently implementing a CNN in plain numpy and have a brief question regarding a special case of the backpropagation for a max-pool layer: While it is clear that the gradient with respect to non-maximum values vanishes, I am not sure about the…
x3t2h
  • 81
  • 3
8
votes
2 answers

What is output tensor of Max Pooling 2D Layer in TensorFlow?

I was trying to understand some basics about the tensorflow and I got stuck while reading documentation for max pooling 2D layer: https://www.tensorflow.org/tutorials/layers#pooling_layer_1 This is how max_pooling2d is specified: pool1 =…
Nikola Stojiljkovic
  • 633
  • 1
  • 5
  • 10
7
votes
1 answer

Keras Model with Maxpooling1D and channel_first

I have a problem with my current attempt to build a sequential model for time series classification in Keras. I want to work with channels_first data, because it is more convenient from a perprocessing perspective (I only work with one channel,…
Gretel_f
  • 175
  • 6
6
votes
2 answers

hybrid of max pooling and average pooling

While tweaking a deep convolutional net using Keras (with the TensorFlow backend) I would like to try out a hybrid between MaxPooling2D and AveragePooling2D, because both strategies seem to improve two different aspects regarding my objective. I'm…
Tobias Hermann
  • 7,574
  • 4
  • 37
  • 93
5
votes
2 answers

Does MaxPooling reduce overfitting?

I have trained the following CNN model with a smaller data set, therefore it does overfitting: model = Sequential() model.add(Conv2D(32, kernel_size=(3,3), input_shape=(28,28,1),…
Code Now
  • 511
  • 5
  • 14
4
votes
1 answer

Is maxpooling on odd number possible?

I am going through the Udacity DeepLearning Nanodegree and working on the autoencoder mini project. I do not understand the solution, nor how to check it myself. So this is 2 questions. We start with 28*28 images. These are fed through 3…
James Oliver
  • 397
  • 2
  • 11
4
votes
1 answer

How to select top-k elements of a keras dense layer?

I'm trying to perform a k-max pooling in order to select top-k elements of a dense with shape (None, 30). I tried a MaxPooling1D layer but it doesn't work, since keras pooling layers require at least a 2d input shape. I'm using the following Lambda…
Belkacem Thiziri
  • 483
  • 1
  • 6
  • 23
3
votes
2 answers

Pytorch: a similar process to reverse pooling and replicate padding?

I have a tensor A that has shape (batch_size, width, height). Assume that it has these values: A = torch.tensor([[[0, 1], [1, 0]]]) I am also given a number K that is a positive integer. Let K=2 in this case. I want to do a…
AerysS
  • 1,165
  • 6
  • 18
1
2 3
…
8 9