bayesiancnn/stopping_crit.py

# import math
import pickle
from time import sleep

from gpu_power_func import total_watt_consumed

with open("configuration.pkl", "rb") as file:
    while True:
        try:
            cfg = pickle.load(file)
        except EOFError:
            break


def non_decreasing(lst: list):
    """
    Check that a list is non decreasing
    """
    return all(x <= y for x, y in zip(lst, lst[1:]))


def non_increasing(lst):
    """
    Check that a list is non inreasing
    """
    return all(x >= y for x, y in zip(lst, lst[1:]))


def monotonic(lst):
    """
    Check that a list is monotonic
    """
    return non_decreasing(lst) or non_increasing(lst)


def strictly_increasing(lst):
    """
    Check that a list is strictly inreasing
    """
    return all(x < y for x, y in zip(lst, lst[1:]))


def strictly_decreasing(lst):
    """
    Check that a list is strictly decreasing
    """
    return all(x > y for x, y in zip(lst, lst[1:]))


def strictly_monotonic(lst):
    """
    Check that a list is strictly monotonic
    """
    return strictly_increasing(lst) or strictly_decreasing(lst)


def count_parameters(model):
    """Counts model amount of trainable parameters"""
    return sum(p.numel() for p in model.parameters() if p.requires_grad)


def efficiency_stop(model, accuracy, batch, sensitivity=0.001):
    """
    This function stops when a certain amount of generalization takes place
    taking into account the model efficiency
    """
    try:
        energy = total_watt_consumed(cfg["pickle_path"])
    except Exception as e:
        sleep(3)
        energy = total_watt_consumed(cfg["pickle_path"])
    efficiency = accuracy / energy
    print(f"Current Efficiency: {1 - efficiency}")
    no_parameters = count_parameters(model)
    if (efficiency * no_parameters / (batch / 2) >= sensitivity) and (accuracy >= 0.5):
        return 1
    return 0


def e_stop(
    early_stopping: list,
    train_acc: float,
    epoch: int,
    patience: int = 4,
    sensitivity: float = 1e-9,
):
    """
    This function stops training early
    """
    early_stopping.append(train_acc)
    if patience in (0, 1):
        print("Stopping Early")
        return 1
    if epoch % patience == 0 and epoch > 0:
        early_stopping = early_stopping[-patience : len(early_stopping)]
        ini = early_stopping.pop(0)
        early_stopping = list(map(lambda x: x - sensitivity, early_stopping))
        early_stopping.insert(0, ini)
        values = ""
        for i, v in enumerate(early_stopping):
            values += f"Value {i+1}: {v} > "
        print(values)
        if (train_acc > 0.5) and not strictly_increasing(early_stopping):
            print("Stopping Early")
            return 1
        del early_stopping[:]
    return 0


def energy_bound(threshold: float = 100000.0):
    """Stops training when a specified amount of energy is consumed"""
    try:
        energy = total_watt_consumed(cfg["pickle_path"])
    except Exception as e:
        sleep(3)
        energy = total_watt_consumed(cfg["pickle_path"])
    print(f"Energy used: {energy}")
    if energy > threshold:
        print("Energy bound achieved")
        return 1
    return 0


def accuracy_bound(train_acc: float, threshold: float = 0.99):
    """Stops training when a specified amount of accuracy is achieved"""
    if train_acc >= threshold:
        print("Accuracy bound achieved")
        return 1
    return 0