I'm working on a regression problem in pytorch. My target values can be either between 0 to 100 or 0 to 1 (they represent % or % divided by 100).
The data is unbalanced, I have much more data with lower targets.
I've noticed that when I run the model with targets in the range 0-100, it doesn't learn - the validation loss doesn't improve, and the loss on the 25% large targets is very big, much bigger than the std in this group.
However, when I run the model with targets in the range 0-1, it does learn and I get good results.
If anyone can explain why this happens, and if using the ranges 0-1 is "cheating", that will be great.
Also - should I scale the targets? (either if I use the larger or the smaller range).
Some additional info - I'm trying to fine tune bert for a specific task. I use MSEloss.
Thanks!
I think your observation relates to batch normalization. There is a paper written on the subject, an numerous medium/towardsdatascience posts, which i will not list here. Idea is that if you have a no non-linearities in your model and loss function, it doesn't matter. But even in MSE you do have non-linearity, which makes it sensitive to scaling of both target and source data. You can experiment with inserting Batch Normalization Layers into your models, after dense or convolutional layers. In my experience it often improves accuracy.
Related
I'm training a CNN (one using a series of ConvTranspose2D in pytorch) that uses input data from JSON to constitute an image. Unlike natural language, the input data can be in any order, as it contains info about various sprites in a scene.
In my first attempts to train the model, I didn't change the order of the input data (meaning, on each epoch, each sprite was represented in the same place in the input data). The model learned for about 10 epochs, but then there started to be divergence between the training loss (which continued to go down) and the test loss. So classic overfitting.
I tried to solve this by doing a form of data augmentation where the output data (in this case an image) stayed the same but I shuffled the order of the input data. As I have around 400 sprites, the maximum shuffling is 400!, so theoretically this can vastly expand the amount of training data. For example, instead of 100k JSON documents corresponding to 100K images, by shuffling the order of sprites in the input data, you have 400!*100000 training data points. In practice of course this amount of data is impractical, so I went with around 2m data points for an initial test. The issue I ran into here was that the model was not learning at all - after getting to a certain loss very quickly (after the first few mini-batches), it didn't learn at all for around 4 epochs. So classic underfitting.
Like Goldilocks, I'd like to find "just right" between the initial overfitting and subsequent underfitting. I'm wondering other strategies I could try out. One idea I had was letting the model train on a predetermined order of sprites (the overfitting case) and then, once overfitting starts (ie two straight epochs with divergence between the test and training loss) shuffling the data. I can also play with changing the model, although it can only be so big because of constraints with the hardware and the fact that inference needs to happen in under 20ms.
Are there any papers or techniques that are recommended in this scenario where data augmentation can lead to vastly more data points but results in a model ceasing to learn? Thanks in advance for any tips!
I have a simple regression problem with two independent variables and one dependent one. I tried linear regression from statsmodels and sk-learn, but I get the best results (R ^ 2 and RMSE) with XGBoost regressor.
On the new data set, RMSE is still in line with earlier results, but individual predictions are very different.
For example, the RMSE is 1000, and individual predictions vary from 20 to 3000. Thus, predictions are either almost perfectly accurate or strongly deviate in a few cases, but i don't know why is that.
My question is what is the cause of such variations in individual predictions?
When testing your model with new data, it's normal to get some of the predictions wrong. Since RMSE is 1000 it means that, on average, the root of the difference between the actual and predicted values is 1000. You can have values that are predicted very well, as well as values that give a very large squared error. The reason for this could be overfitting. It could also be that the new data set contains data that is very different from the data the model was trained on. But since the RMSE is in line with earlier results, I understand that RMSE was around 1000 on the training set as well. Therefore I don't necessarily see a problem with the test set. What I would do is go through the preprocessing steps for the training data and make sure they're done correctly:
standardize the data and remove possible skewness
check for collinearity between independent variables (you only have 2, so it should be easy to do)
check to see if independent variables have an acceptable variance. If your variables don't vary too much for each new data point it could be that they are useless for explaining the dependent variable.
BTW, what is the R2 score for your regression? It should tell you how much of the variability of the target variable is explained by your model. A low R2 score should indicate that the regressors used aren't very useful in explaining your target variable.
You can use the sklearn function StandardScaler() to standaredize the data.
I am trying to train a neural network to classify words into different categories.
I notice two things:
When I use a smaller batch_size (like 8,16,32) the loss is not decreasing, but rather sporadically varying. When I use a larger batch_size (like 128, 256), the loss is going going down, but very slowly.
More importantly, when I use a larger EPOCH value, my model does a good job at reducing the loss. However I'm using a really large value (EPOCHS = 10000).
Question:
How to get the optimal EPOCH and batch_size values?
There is no way to decide on these values based on some rules. Unfortunately, the best choices depend on the problem and the task. However, I can give you some insights.
When you train a network, you calculate a gradient which would reduce the loss. In order to do that, you need to backpropagate the loss. Now, ideally, you compute the loss based on all of the samples in your data because then you consider basically every sample and you come up with a gradient that would capture all of your samples. In practice, this is not possible due to the computational complexity of calculating gradient on all samples. Because for every update, you have to compute forward-pass for all your samples. That case would be batch_size = N, where N is the total number of data points you have.
Therefore, we use small batch_size as an approximation! The idea is instead of considering all the samples, we say I compute the gradient based on some small set of samples but the thing is I am losing information regarding the gradient.
Rule of thumb:
Smaller batch sizes give noise gradients but they converge faster because per epoch you have more updates. If your batch size is 1 you will have N updates per epoch. If it is N, you will only have 1 update per epoch. On the other hand, larger batch sizes give a more informative gradient but they convergence slower.
That is the reason why for smaller batch sizes, you observe varying losses because the gradient is noisy. And for larger batch sizes, your gradient is informative but you need a lot of epochs since you update less frequently.
The ideal batch size should be the one that gives you informative gradients but also small enough so that you can train the network efficiently. You can only find it by trying actually.
Currently I am using the convolutional neural networks to solve the binary classification problem. The data I use is 2D-images and the number of training data is only about 20,000-30,000. In deep learning, it is generally known that overfitting problems can arise if the model is too complex relative to the amount of the training data. So, to prevent overfitting, the simplified model or transfer learning is used.
Previous developers in the same field did not use high-capacity models (high-capacity means a large number of model parameters) due to the small amount of training data. Most of them used small-capacity models and transfer learning.
But, when I was trying to train the data on high-capacity models (based on ResNet50, InceptionV3, DenseNet101) from scratch, which have about 10 million to 20 million parameters in, I got a high accuracy in the test set.
(Note that the training set and the test set were exclusively separated, and I used early stopping to prevent overfitting)
In the ImageNet image classification task, the training data is about 10 million. So, I also think that the amount of my training data is very small compared to the model capacity.
Here I have two questions.
1) Even though I got high accuracy, is there any reason why I should not use a small amount of data on the high-capacity model?
2) Why does it perform well? Even if there is a (very) large gap between the amount of data and the number of model parameters, the techniques like early stopping overcome the problems?
1) You're completely right that small amounts of training data can be problematic when working with a large model. Given that your ultimate goal is to achieve a "high accuracy" this theoretical limitation shouldn't bother you too much if the practical performance is satisfactory for you. Of course, you might always do better but I don't see a problem with your workflow if the score on the test data is legit and you're happy with it.
2) First of all, I believe ImageNet consists of 1.X million images so that puts you a little closer in terms of data. Here are a few ideas I can think of:
Your problem is easier to solve than ImageNet
You use image augmentation to synthetically increase your image data
Your test data is very similar to the training data
Also, don't forget that 30,000 samples means (30,000 * 224 * 224 * 3 =) 4.5 billion values. That should make it quite hard for a 10 million parameter network to simply memorize your data.
3) Welcome to StackOverflow
The following is how I understand the point of parameter sharing in RNNs:
In regular feed-forward neural networks, every input unit is assigned an individual parameter, which means that the number of input units (features) corresponds to the number of parameters to learn. In processing e.g. image data, the number of input units is the same over all training examples (usually constant pixel size * pixel size * rgb frames).
However, sequential input data like sentences can come in highly varying lengths, which means that the number of parameters will not be the same depending on which example sentence is processed. That is why parameter sharing is necessary for efficiently processing sequential data: it makes sure that the model always has the same input size regardless of the sequence length, as it is specified in terms of transition from one state to another. It is thus possible to use the same transition function with the same weights (input to hidden weights, hidden to output weights, hidden to hidden weights) at every time step. The big advantage is that it allows generalization to sequence lengths that did not appear in the training set.
My questions are:
Is my understanding of RNNs, as summarized above, correct?
In the actual code example in Keras I looked at for LSTMs, they padded the sentences to equal lengths before all. By doing so, doesn't this wash away the whole purpose of parameter sharing in RNNs?
Parameter Sharing
Being able to efficiently process sequences of varying length is not the only advantage of parameter sharing. As you said, you can achieve that with padding. The main purpose of parameter sharing is a reduction of the parameters that the model has to learn. This is the whole purpose of using a RNN.
If you would learn a different network for each time step and feed the output of the first model to the second etc. you would end up with a regular feed-forward network. For a number of 20 time steps, you would have 20 models to learn. In Convolutional Nets, parameters are shared by the Convolutional Filters because when we can assume that there are similar interesting patterns in different regions of the picture (for example a simple edge). This drastically reduces the number of parameters we have to learn. Analogously, in sequence learning we can often assume that there are similar patterns at different time steps. Compare 'Yesterday I ate an apple' and 'I ate an apple yesterday'. These two sentences mean the same, but the 'I ate an apple' part occurs on different time steps. By sharing parameters, you only have to learn what that part means once. Otherwise, you'd have to learn it for every time step, where it could occur in your model.
There is a drawback to sharing the parameters. Because our model applies the same transformation to the input at every time step, it now has to learn a transformation that makes sense for all time steps. So, it has to remember, what word came in which time step, i.e. 'chocolate milk' should not lead to the same hidden and memory state as 'milk chocolate'. But this drawback is small compared to using a large feed-forward network.
Padding
As for padding the sequences: the main purpose is not directly to let the model predict sequences of varying length. Like you said, this can be done by using parameter sharing. Padding is used for efficient training - specifically to keep the computational graph during training low. Without padding, we have two options for training:
We unroll the model for each training sample. So, when we have a sequence of length 7, we unroll the model to 7 time steps, feed the sequence, do back-propagation through the 7 time steps and update the parameters. This seems intuitive in theory. But in practice, this is inefficient, because TensorFlow's computational graphs don't allow recurrency, they are feedforward.
The other option is to create the computational graphs before starting training. We let them share the same weights and create one computational graph for every sequence length in our training data. But when our dataset has 30 different sequence lengths this means 30 different graphs during training, so for large models, this is not feasible.
This is why we need padding. We pad all sequences to the same length and then only need to construct one computational graph before starting training. When you have both very short and very long sequence lengths (5 and 100 for example), you can use bucketing and padding. This means, you pad the sequences to different bucket lengths, for example [5, 20, 50, 100]. Then, you create a computational graph for each bucket. The advantage of this is, that you don't have to pad a sequence of length 5 to 100, as you would waste a lot of time on "learning" the 95 padding tokens in there.