chicobentojr

A Recipe for Training Neural Networks - Andrej Karpathy

thomwolf

model.zero_grad()                                   # Reset gradients tensors
for i, (inputs, labels) in enumerate(training_set):
    predictions = model(inputs)                     # Forward pass
    loss = loss_function(predictions, labels)       # Compute loss function
    loss = loss / accumulation_steps                # Normalize our loss (if averaged)
    loss.backward()                                 # Backward pass
    if (i+1) % accumulation_steps == 0:             # Wait for several backward steps
        optimizer.step()                            # Now we can do an optimizer step
        model.zero_grad()                           # Reset gradients tensors
        if (i+1) % evaluation_steps == 0:           # Evaluate the model when we...

stevekm

from here: http://stackoverflow.com/questions/5597836/embed-create-an-interactive-python-shell-inside-a-python-program

paste this inside your script for debugging, to start a Python interactive terminal shell session at that point in the script, super useful for debugging since it lets you explore the Python environment and access objects and variables as they are at that point in the script.

import readline # optional, will allow Up/Down/History in the console
import code
vars = globals().copy()
vars.update(locals())

FND

#!/usr/bin/env python

def handler(environ, start_response):
    method = environ["REQUEST_METHOD"]
    origin = environ.get("HTTP_ORIGIN")
    cookie = environ.get("HTTP_COOKIE", "N/A")
    print ""
    print method, environ["PATH_INFO"]
    print "Origin:", origin
    print "Cookie:", cookie