Ceci est une ancienne révision du document !
Mise en forme d'un post de stackoverflow.com non traduit en français, car très technique ce qui ne se comprend qu'en anglais.
For any Keras layer (Layer class), can someone explain how to understand the difference between input_shape, units, dim, etc.?
For example the doc says units specify the output shape of a layer. In the image of the neural net below hidden layer1 has 4 units.
Does this directly translate to the units attribute of the Layer object? Or does units in Keras equal the shape of every weight in the hidden layer times the number of units? In short how does one understand/visualize the attributes of the model - in particular the layers - with the image below?
The amount of “neurons”, or “cells”, or whatever the layer has inside it.
It's a property of each layer, and yes, it's related to the output shape (as we will see later). In your picture, except for the input layer, which is conceptually different from other layers, you have:
Shapes are consequences of the model's configuration. Shapes are tuples representing how many elements an array or tensor has in each dimension.
Ex: a shape (30,4,10) means an array or tensor with 3 dimensions, containing 30 elements in the first dimension, 4 in the second and 10 in the third, totaling 30*4*10 = 1200 elements or numbers.
What flows between layers are tensors. Tensors can be seen as matrices, with shapes.
In Keras, the input layer itself is not a layer, but a tensor. It's the starting tensor you send to the first hidden layer. This tensor must have the same shape as your training data.
Example: if you have 30 images of 50×50 pixels in RGB (3 channels), the shape of your input data is (30,50,50,3). Then your input layer tensor, must have this shape (see Shapes in Keras).
Each type of layer requires the input with a certain number of dimensions:
Now, the input shape is the only one you must define, because your model cannot know it. Only you know that, based on your training data.
All the other shapes are calculated automatically based on the units and particularities of each layer.
Given the input shape, all other shapes are results of layers calculations.
The “units” of each layer will define the output shape (the shape of the tensor that is produced by the layer and that will be the input of the next layer).
Each type of layer works in a particular way. Dense layers have output shape based on “units”, convolutional layers have output shape based on “filters”. But it's always based on some layer property. (See the documentation for what each layer outputs)
Let's show what happens with “Dense” layers, which is the type shown in your graph.
A dense layer has an output shape of (batch_size,units). So, yes, units, the property of the layer, also defines the output shape.
Weights will be entirely automatically calculated based on the input and the output shapes. Again, each type of layer works in a certain way. But the weights will be a matrix capable of transforming the input shape into the output shape by some mathematical operation.
In a dense layer, weights multiply all inputs. It's a matrix with one column per input and one row per unit, but this is often not important for basic works.
In the image, if each arrow had a multiplication number on it, all numbers together would form the weight matrix.
Earlier, I gave an example of 30 images, 50×50 pixels and 3 channels, having an input shape of (30,50,50,3).
Since the input shape is the only one you need to define, Keras will demand it in the first layer. But in this definition, Keras ignores the first dimension, which is the batch size. Your model should be able to deal with any batch size, so you define only the other dimensions:
input_shape = (50,50,3) # regardless of how many images I have, each image has this shape
Optionally, or when it's required by certain kinds of models, you can pass the shape containing the batch size via batch_input_shape=(30,50,50,3) or batch_shape=(30,50,50,3). This limits your training possibilities to this unique batch size, so it should be used only when really required.
Either way you choose, tensors in the model will have the batch dimension.
So, even if you used input_shape=(50,50,3), when keras sends you messages, or when you print the model summary, it will show (None,50,50,3).
The first dimension is the batch size, it's None because it can vary depending on how many examples you give for training. (If you defined the batch size explicitly, then the number you defined will appear instead of None)
Also, in advanced works, when you actually operate directly on the tensors (inside Lambda layers or in the loss function, for instance), the batch size dimension will be there.
And in the end, what is dim?
If your input shape has only one dimension, you don't need to give it as a tuple, you give input_dim as a scalar number.
So, in your model, where your input layer has 3 elements, you can use any of these two:
But when dealing directly with the tensors, often dim will refer to how many dimensions a tensor has. For instance a tensor with shape (25,10909) has 2 dimensions.
Keras has two ways of doing it, Sequential models, or the functional API Model. I don't like using the sequential model, later you will have to forget it anyway because you will want models with branches. PS: here I ignored other aspects, such as activation functions. With the Sequential model:
from keras.models import Sequential from keras.layers import * model = Sequential() # Start from the first hidden layer, since the input is not actually a layer # but inform the shape of the input, with 3 elements. model.add(Dense(units=4,input_shape=(3,))) # hidden layer 1 with input # Further layers: model.add(Dense(units=4)) # hidden layer 2 model.add(Dense(units=1)) # output layer
With the functional API Model:
from keras.models import Model from keras.layers import * # Start defining the input tensor: inpTensor = Input((3,)) # Create the layers and pass them the input tensor to get the output tensor: hidden1Out = Dense(units=4)(inpTensor) hidden2Out = Dense(units=4)(hidden1Out) finalOut = Dense(units=1)(hidden2Out) # Define the model's start and end points model = Model(inpTensor, finalOut)
Remember you ignore batch sizes when defining layers, so set it to None:
To which dimension the first value of the argument refers? I see things like input_shape=(728, ), so in my mind the first argument refers to columns (fixed) and second to rows (free to vary). But how does this sit with Python's row-major order of arrays?
Could you please elaborate a little bit what the difference between “input elements” and “dimensions” are? I would think that the graph above had a three-dimensional input layer, thus making dim=3, so I'm wondering what I'm missing here, because I see you write that the input is 1-dimensional…
But when dealing directly with the tensors, often dim will refer to how many dimensions a tensor has. So for 1-dimensional 3-length input, input_dim=3, but for 2-dimensional input of shape (25,10909), input_dim=2?
You said if you have 30 images of 50×50 pixels in RGB (3 channels), the shape of your input data is (30,50,50,3) how do you get the intuition behind this? Shouldn't it be(30*3*50*50) 50*50 for each image then *3 for RGB then *30 for examples. OR is it that the dimensions don't matter and using any one convention will do?
“or (batch_size, optional,…,optional, input_size)” - in what circumstances would you pass the optional data items here? What are they?
It (the word dimension alone) can refer to:
Keras has its input_dim refers to the Dimension of Input Layer / Number of Input Feature
model = Sequential() model.add(Dense(32, input_dim=784)) #or 3 in the current posted example above model.add(Activation('relu'))
In Keras LSTM, it refers to the total Time Steps
The term has been very confusing, is correct and we live in a very confusing world!!
I find one of the challenge in Machine Learning is to deal with different languages or dialects and terminologies (like if you have 5-8 highly different versions of English, then you need to very high proficiency to converse with different speakers). Probably this is the same in programming languages too.