New answers tagged

1

First of all: probably you should not train with the loss you propose, because with MSE you will train to minimize the total error, not to keep the features as they were, which is what CNNs are good at detecting; this is the same problem as what happens when you train an image autoencoder on MSE, that you obtain blurry images. Instead, configure the network ...


1

It is straightforward to stack different neural networks with current deep learning frameworks (i.e., PyTorch or TensorFlow). There is no separate output for $r$, it just one of many layers. It could look like this: You can freeze or not freeze any layers in a stacked neural network. You can decide how far to backpropagate the training updates. The ...


-1

You would need an autoencoder. Here is an example of code: https://www.analyticsvidhya.com/blog/2020/02/what-is-autoencoder-enhance-image-resolution/


1

some questions will help give better answers: When you say underfitting, I assume you mean that the low accuracy is on the train set, correct? I'm asking also because with that amount of parameters for such a small training set I would be far more concerned with overfitting 530 images is very small dataset, I would consider going with a pretrained ...


0

It is very common to use sklearn for cross validation. The most known methods are KFold and cross_val_score imported from sklearn.model_selection. You can then use tf.keras.wrappers.scikit_learn.KerasClassifier to implement the scikit-learn classifier with Keras model.


0

There are several reasons for that. Try increasing your training dataset or begin with smaller initial learning rate.


0

I think group CNN is close. It has rotation and symmetry


0

If you change the image size, you will be able to reuse only part of the original network. Convolutional and pooling layers can be applied to images of any size, so the initial part of the network, which normally consists of convolutions and pooling, will be reusable as-is. However, the dense layers after the convolutional part assume certain input ...


0

As mentioned in the article also, the different groups learn different representations for the data. In a normal convolutional network, each layer learns a unique representation. But, here, in the same layer, we are able to derive different representations. It can also related to the software engineering principle of Separation of Concerns. Since, different ...


1

One way to understand how ELMo's character convolutions work is by directly inspecting the source code. There, in the forward method, you can see that the input to the network is a tensor of dimensions (batch_size, sequence_length, 50), where 50 is the maximum number of characters per word. Therefore, before passing the text to the network, it is segmented ...


1

Requiring a fully connected layer to only accept one dimensional (a vector) makes for a consistent interface between layers. Strict inputs makes the the code more straightforward. Otherwise a fully interconnected layer might have to accept arbitrary inputs (e.g., n-dimensional).


3

First of all, here is the answer to your question: YES You have a beginning of CNN (Convolutional Neural Network) in your code. Just don't forget to add activation functions (usually ReLU) after convolutional layers. Another unconventional thing is you use 2 outputs for your binary classification, which is not the way to go, we would rather use 1 output that ...


0

This is a relatively common phenomena called double descent.


Top 50 recent answers are included