Deep-learning - TechnoScripts

deep-learning

Deep learning tutorials in Python covering neural networks, training, and common frameworks.

PyTorch Dataset and DataLoader: The Real Training Loop

You trained your first network on a toy set that fit in one tensor, and it felt easy. Then real data arrives, a CSV with thousands of rows or an image folder too big for memory, and the PyTorch DataLoader is the tool built for exactly that. Here you pair it with a custom Dataset, feed a network from a CSV and an image folder, run the five-step loop from memory, validate honestly, and save a checkpoint you can resume ... Read More

DL: PyTorch GPU Training, Debugging, and Speedups

A model sitting on the GPU and a batch still on the CPU: that one mismatch kills more first runs than any piece of math. PyTorch GPU training is mostly two habits, keeping everything on the same device and reading error messages instead of panicking at them. This post covers device discipline, CUDA out of memory, shape bugs, NaN loss, and mixed precision speedups. “Neural nets fail silently. The code runs, the loss looks plausible, and the bug just quietly ... Read More

Machine Learning Interview Questions: 40-Question Checkpoint

Most ML screens recycle the same forty or so theory fundamentals, just reworded. That is good news: the list is learnable. This checkpoint collects the machine learning interview questions that actually come up, grouped the way real screens group them, each with a spoken-style answer and runnable code that proves the claims people get wrong. Tally your score at the end and turn every miss into a short revisit list. “A model is only as trustworthy as the way you ... Read More