HParams | A thoughtful approach to hyperparameter management | Machine Learning library

I have multiple deep neural networks in my model and want them to have the same input sizes (networks are of different classes). For example, my model is:

I'm trying to build a basic GAN to familiarise myself with Pytorch. I have some (limited) experience with Keras, but since I'm bound to do a larger project in Pytorch, I wanted to explore first using 'basic' networks.

I'm using Pytorch Lightning. I think I've added all necessary components. I tried passing some noise through the generator and the discriminator separately, and I think the output has the expected shape. Nonetheless, I get a runtime error when I try to train the GAN (full traceback below):

RuntimeError: mat1 and mat2 shapes cannot be multiplied (7x9 and 25x1)

I noticed that 7 is the size of the batch (by printing out the batch dimensions), even though I specified batch_size to be 64. Other than that, quite honestly, I don't know where to begin: the error traceback doesn't help me.

Chances are, I made multiple mistakes. However, I'm hoping some of you will be able to spot the current error from the code, since the multiplication error seems to point towards a dimensionality problem somewhere. Here's the code.

I try to train a model object detection and I follow this tutorial: https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/tensorflow-1.14/training.html

But at the end I execute the command in the cmd : python model_main.py --alsologtostderr --model_dir=training/ --pipeline_config_path=training/ssd_inception_v2_coco.config

and it return the following lines:

I got a custom keras Model which I want to optimize for hyperparameters while having a good tracking of whats going on and visualization. Therefor I want to pass hparams to the custom model like this:

I am using CNN for classification problem. I have 3D images (CT scans) of patients and I am trying to predict the binary outcome on the basis of these images. I also have a clinical data and want to include that into the CNN model. I have a custom *Datagenerator (via keras.utils.Sequence) and it generates X, y, and also array of clinical data.

X,y will be used through out the model and would like to add clinical data in my second last dense layer (a layer prior to output layer)

Code for my Data generator

I am using hydra composition with the following structure:

Greetings dear members of the community. I am creating a neural network to predict a multi-label y. Specifically, the neural network takes 5 inputs (list of actors, plot summary, movie features, movie reviews, title) and tries to predict the sequence of movie genres. In the neural network I use Embeddings Layer and Global Max Pooling layers.

However, I recently discovered the Recurrent Layers with Attention, which are a very interesting topic these days in machine learning translation. So, I wondered if I could use one of those layers but only the Plot Summary input. Note that I don't do ml translation but rather text classification.

My neural network in its current state

I currently train my model using GPUs using Pytorch Lightning

I am working with a U-Net in Pytorch Lightning. I am able to train the model successfully but after training when I try to load the model from checkpoint I get this error:

Complete Traceback: