Deep Learning

When experimenting with various parameters in a model like changing the number of layers, activation function, or neurons, sometimes the model doesn’t perform well while training. We can save training time and other resources by stopping the model when its performance on the validation dataset deteriorates. The process is called early stopping in machine learning. […]

When we are working with GPU accelerated frameworks like PyTorch we tend to face errors related to CUDA which can be a frustrating experience. One such error is RuntimeError: cuda error: cublas_status_not_initialized when calling cublascreate(handle). Knowing the exact cause of error is quite difficult but we can narrow it down to places where we can

Why is normalization necessary? You can consider normalization as a way of scaling and shifting the input data in a particular range. Some common normalization techniques are min-max normalization and z-score  (standardization) normalization. Min max normalization scales data between 0 to 1 whereas standardization scales data to have mean of 0 and stand deviation of 1.

We all are well know with OpenAI   company by their world changing products like ChatGPT,  Whisper  and a recently  launched product called SORA,  which is a text to video AI model only available to few people as of now. In this blog we will discuss about how to get  ChatGPT API key, how to use