Optimizers | Tensorflow Optimizers | Machine Learning library

Just use the tf.keras.callbacks.CSVLogger and any regression metric you want to log during training:

If the hyperspectral dataset is given to you as a large image with many channels, I suppose that the classification of each pixel should depend on the pixels around it (otherwise I would not format the data as an image, i.e. without grid structure). Given this assumption, breaking up the input picture into 1x1 parts is not a good idea as you are loosing the grid structure.

I further suppose that the order of the channels is arbitrary, which implies that convolution over the channels is probably not meaningful (which you however did not plan to do anyways).

Instead of reformatting the data the way you did, you may want to create a model that takes an image as input and also outputs an "image" containing the classifications for each pixel. I.e. if you have 10 classes and take a (145, 145, 200) image as input, your model would output a (145, 145, 10) image. In that architecture you would not have any fully-connected layers. Your output layer would also be a convolutional layer.

That however means that you will not be able to keep your current architecture. That is because the tasks for MNIST/CIFAR10 and your hyperspectral dataset are not the same. For MNIST/CIFAR10 you want to classify an image in it's entirety, while for the other dataset you want to assign a class to each pixel (while most likely also using the pixels around each pixel).

Some further ideas:

• If you want to turn the pixel classification task on the hyperspectral dataset into a classification task for an entire image, maybe you can reformulate that task as "classifying a hyperspectral image as the class of it's center (or top-left, or bottom-right, or (21th, 104th), or whatever) pixel". To obtain the data from your single hyperspectral image, for each pixel, I would shift the image such that the target pixel is at the desired location (e.g. the center). All pixels that "fall off" the border could be inserted at the other side of the image.
• If you want to stick with a pixel classification task but need more data, maybe split up the single hyperspectral image you have into many smaller images (e.g. 10x10x200). You may even want to use images of many different sizes. If you model only has convolution and pooling layers and you make sure to maintain the sizes of the image, that should work out.

using OneHotEncoder is not the way to go here, it's better to extract the features from the column time as separate features like year, month, day, hour, minutes etc... and give these columns as input to your model.

Make sure that the metric callback is listed before the modelcheckpoint callback.

Change the axis dimension in expand_dims to 1 and slice your data like this, since it is 2D:

Mean squared error (MSE) is the most commonly used loss function for regression. The loss is the mean overseen data of the squared differences between true and predicted values, or writing it as a formula.

You can use MSE when doing regression, believing that your target, conditioned on the input, is normally distributed, and want large errors to be significantly (quadratically) more penalized than small ones.

According to your example , and as mentioned in the image above :

y_true is y and y_pred is the same as y~i , so it will calculate the loss every epoch in order to get the minimum value that means , y_true will be somehow closer to y_pred

Add the smallest value (in this case is negative) so that everything is >= 0. Then use Poisson.

I believe the last layer in your network is outputting 10 values, when it should be 1.

TensorFlow has 2 execution modes: eager execution, and graph mode. TensorFlow default behavior, since version 2, is to default to eager execution. Eager execution is great as it enables you to write code close to how you would write standard python. It's easier to write, and it's easier to debug. Unfortunately, it's really not as fast as graph mode.

So the idea is, once the function is prototyped in eager mode, to make TensorFlow execute it in graph mode. For that you can use tf.function. tf.function compiles a callable into a TensorFlow graph. Once the function is compiled into a graph, the performance gain is usually quite important. The recommended approach when developing in TensorFlow is the following:

• Debug in eager mode, then decorate with @tf.function.
• Don't rely on Python side effects like object mutation or list appends.
• tf.function works best with TensorFlow ops; NumPy and Python calls are converted to constants.

I would add: think about the critical parts of your program, and which ones should be converted first into graph mode. It's usually the parts where you call a model to get a result. It's where you will see the best improvements.

You can find more information in the following guides:

• Better performance with tf.function
• Introduction to graphs and tf.function

So, there are at least two things you can change in your code to make it run quite faster:

1. The first one is to not use model.predict on a small amount of data. The function is made to work on a huge dataset or on a generator. (See this comment on Github). Instead, you should call the model directly, and for performance enhancement, you can wrap the call to the model in a tf.function.

Model.predict is a top-level API designed for batch-predicting outside of any loops, with the fully-features of the Keras APIs.

1. The second one is to make your training step a separate function, and to decorate that function with @tf.function.

So, I would declare the following things before your training loop: