My CNN-based deep learning model is fluctuating in validation accuracy at certain epochs. I learned the deep learning model from frequency domain images. Do I need to normalize or not?
And then, the training loss does not decrease and is stable. I tried 80 epochs. The training loss and validation accuracy are still stuck in epoch 20. There are no improvements.
I have already tried tuning hyperparameters such as learning rate. I also added regularization parameters.
I have used the Transformer model to train the time series dataset, but there is always a gap between training and validation in my loss curve. I have tried using different learning rates, batch sizes, dropout, heads, dim_feedforward, and layers, but they don't work. Can anyone give me some ideas on reducing the gap between them?
I also tried to ask the question on the Pytorch forum but didn't get any reply.
How to design a decoder for time series regression in Transformer?
Since you are overfitting your model here
1.Try using more data.
2.Try to add dropOut layers
3. Try using lasso or Ridge
I am a student and currently studying deep learning by myself. Here I would like to ask for clarification regarding the transfer learning.
For example MobileNetv2 (https://keras.io/api/applications/mobilenet/#mobilenetv2-function), if the weights parameter is set to None, then I am not doing transfer learning as the weights are random initialized. If I would like to do transfer learning, then I should set the weights parameter to imagenet. Is this concept correct?
Clarification and explanation regarding deep learning
Yes, when you initialize the weights with random values, you are just using the architecture and training the model from scratch. The goal of transfer learning is to use the previously gained knowledge by another trained model to get better results or to use less computational resources.
There are different ways to use transfer learning:
You can freeze the learned weights of the base model and replace the last layer of the model base on your problem and just train the last layer
You can start with the learned weights and fine-tune them (let them change in the learning process). Many people do that because sometimes it makes the training faster and gives better results because the weights already contain so much information.
You can use the first layers to extract basic features like colors, edges, circles... and add your desired layers after them. In this way, you can use your resources to learn high-level features.
There are more cases, but I hope it could give you an idea.
I am trying to use Hinge loss with densenet on the CIFAR 100 dataset. The learning converges to some point and after that there is no learning. The accuracy is much less than Densenet with CrossEntropy loss function. I tried with different learning rates and weight decays.
Any ideas on why I am unable to train properly Densenet with Hinge loss? I am able to use Hinge loss with Resnet without any problem.
I am a beginner, and I am very confused about how we can choose a pre-trained model that will improve my model.
I am trying to create a cat breed classifier using pre-trained weights of a model, lets say VGG16 trained on digits dataset, will that improve the performance of the model? or if I train my model just on the database without using any other weights will be better, or will both be the same as those pre-trained weights will be just a starting point.
Also if I use weights of the VGG16 trained for cat vs dog data as a starting point of my cat breed classification model will that help me in improving the model?
Since you've mentioned that you are a beginner I'll try to be a bit more verbose than normal so please bear with me.
How neural models recognise images
The layers in a pre-trained model store multiple aspects of the images they were trained on like patterns(lines, curves), colours within the image which it uses to decide if an image is of a specific class or not
With each layer the complexity of what it can store increases initially it captures lines or dots or simple curves but with each layer, the representation power increases and it starts capturing features like cat ears, dog face, curves in a number etc.
The image below from Keras blog shows how initial layers learn to represent simple things like dots and lines and as we go deeper they start to learn to represent more complex patterns.
Read more about Conv net Filters at keras's blog here
How does using a pretrained model give better results ?
When we train a model we waste a lot of compute and time initially creating these representations and in order to get to those representations we need quite a lot of data too else we might not be able to capture all relevant features and our model might not be as accurate.
So when we say we want to use a pre-trained model we want to use these representations so if we use a model trained on imagenet which has lots of cat pics we can be sure that the model already has representations to identify important features required to identify a cat and will converge to a better point than if we used random weights.
How to use pre-trained weights
So when we say to use pre-trained weights we mean use the layers which hold the representations to identify cats but discard the last layer (dense and output) and instead add fresh dense and output layers with random weights. So our predictions can make use of the representations already learned.
In real life we freeze our pretrained weights during the initial training as we do not want our random weights at the bottom to ruin the learned representations. we only unfreeze the representations in the end after we have a good classification accuracy to fine-tune them, and that too with a very small learning rate.
Which kind of pre-trained model to use
Always choose those pretrained weights that you know has the most amount of representations which can help you in identifying the class you are interested in.
So will using a mnist digits trained weights give relatively bad results when compared with one trained on image net?
Yes, but given that the initial layers have already learned simple patterns like lines and curves for digits using these weights will still put you at an advantage when compared to starting from scratch in most of the cases.
Sane weight initialization
The pre-trained weights to choose depends upon the type of classes you wish to classify. Since, you wish to classify Cat Breeds, use pre-trained weights from a classifier that is trained on similar task. As mentioned by the above answers the initial layers learn things like edges, horizontal or vertical lines, blobs, etc. As you go deeper, the model starts learning problem specific features. So for generic tasks you can use say imagenet & then fine-tune it for the problem at hand.
However, having a pre-trained model which closely resembles your training data helps immensely. A while ago, I had participated in Scene Classification Challenge where we initialized our model with the ResNet50 weights trained on Places365 dataset. Since, the classes in the above challenge were all present in the Places365 dataset, we used the weights available here and fine-tuned our model. This gave us a great boost in our accuracy & we ended up at top positions on the leaderboard.
You can find some more details about it in this blog
Also, understand that the one of the advantages of transfer learning is saving computations. Using a model with randomly initialized weights is like training a neural net from scratch. If you use VGG16 weights trained on digits dataset, then it might have already learned something, so it will definitely save some training time. If you train a model from scratch then it will eventually learn all the patterns which using a pre-trained digits classifier weights would have learnt.
On the other hand using weights from a Dog-vs-Cat classifier should give you better performance as it already has learned features to detect say paws, ears, nose or whiskers.
Could you provide more information, what do you want to classify exactly? I see you wish to classify images, which type of images (containing what?) and in which classes?
As a general remark : If you use a trained model, it must fit your need, of course. Keep in mind that a model which was trained on a given dataset, learned only the information contained in that dataset and can classify / indentify information analogous to the one in the training dataset.
If you want to classify an image containing an animal with a Y/N (binary) classifier, (cat or not cat) you should use a model trained on different animals, cats among them.
If you want to classify an image of a cat into classes corresponding to cat races, let's say, you should use a model trained only on cats images.
I should say you should use a pipeline, containing steps 1. followed by 2.
it really depends on the size of the dataset you have at hand and how related the task and data that the model was pretrained on to your task and data. Read more about Transfer Learning http://cs231n.github.io/transfer-learning/ or Domain Adaptation if your task is the same.
I am trying to create a cat breed classifier using pre-trained weights of a model, lets say VGG16 trained on digits dataset, will that improve the performance of the model?
There are general characteristics that are still learned from digits like edge detection that could be useful for your target task, so the answer here is maybe. You can here try just training the top layers which is common in computer vision applications.
Also if I use weights of the VGG16 trained for cat vs dog data as a starting point of my cat breed classification model will that help me in improving the model?
Your chances should be better if the task and data are more related and similar