utils.py

import time
import sys
import math
import os
import torch
import torch.nn as nn
import torch.nn.init as init
import csv
import statistics as stat

_, term_width = os.popen('stty size', 'r').read().split()
term_width = int(term_width)
TOTAL_BAR_LENGTH = 86.
last_time = time.time()
begin_time = last_time

def progress_bar(current, total, msg=None):
    global last_time, begin_time
    # Reset for new bar
    if current == 0:
        begin_time = time.time()

    cur_len = int(TOTAL_BAR_LENGTH * current / total)
    rest_len = int(TOTAL_BAR_LENGTH - cur_len) - 1

    sys.stdout.write(' [')
    for i in range(cur_len):
        sys.stdout.write('=')
    sys.stdout.write('>')
    for i in range(rest_len):
        sys.stdout.write('.')
    sys.stdout.write(']')

    cur_time = time.time()
    step_time = cur_time - last_time
    last_time = cur_time
    tot_time = cur_time - begin_time

    L = []
    #L.append('  Step: %s' % format_time(step_time))
    L.append(' Time: %s' % format_time(tot_time))
    if msg:
        L.append(' | ' + msg)

    msg = ''.join(L)
    sys.stdout.write(msg)
    for i in range(term_width-int(TOTAL_BAR_LENGTH)-len(msg)-3):
        sys.stdout.write(' ')

    # Go back to the center of the bar
    for i in range(term_width-int(TOTAL_BAR_LENGTH/2)):
        sys.stdout.write('\b')
    sys.stdout.write(' %d/%d ' % (current+1, total))

    if current < total-1:
        sys.stdout.write('\r')
    else:
        sys.stdout.write('\n')
    sys.stdout.flush()

def format_time(seconds):
    days = int(seconds / 3600/24)
    seconds = seconds - days*3600*24
    hours = int(seconds / 3600)
    seconds = seconds - hours*3600
    minutes = int(seconds / 60)
    seconds = seconds - minutes*60
    secondsf = int(seconds)
    seconds = seconds - secondsf
    millis = int(seconds*1000)

    f = ''
    i = 1
    if days > 0:
        f += str(days) + 'D'
        i += 1
    if hours > 0 and i <= 2:
        f += str(hours) + 'h'
        i += 1
    if minutes > 0 and i <= 2:
        f += str(minutes) + 'm'
        i += 1
    if secondsf > 0 and i <= 2:
        f += str(secondsf) + 's'
        i += 1
    if millis > 0 and i <= 2:
        f += str(millis) + 'ms'
        i += 1
    if f == '':
        f = '0ms'
    return f


def init_params(net):
    # Init layer parameters
    for m in net.modules():
        if isinstance(m, nn.Conv2d):
            init.kaiming_normal(m.weight, mode='fan_out')
            if m.bias:
                init.constant(m.bias, 0)
        elif isinstance(m, nn.BatchNorm2d):
            init.constant(m.weight, 1)
            init.constant(m.bias, 0)
        elif isinstance(m, nn.Linear):
            init.normal(m.weight, std=1e-3)
            if m.bias:
                init.constant(m.bias, 0)


def adjust_lr_steep(lr_0, param_groups, epoch, adj_params):
    steps = adj_params['steps']
    decay_rates = adj_params ['decay_rates']
    for param_group in param_groups:
        lr = lr_0
        for j in range(len(steps)):
            if epoch >= steps[j]:
                lr = lr * decay_rates[j]
        param_group['lr'] = lr
    return param_groups

def adjust_lr_self_steep(lr, param_groups, epoch, accuracy, adj_params):
    ## self adjust the learning rate depends on the statistics of accuracy
    decay_rates = adj_params ['decay_rates']
    for param_group in param_groups:
        if  acc_stat(accuracy) < 1e-1:
            lr = lr * decay_rates
        param_group['lr'] = lr
    return param_groups

def acc_stat(accuracy):
    length = 10
    a = accuracy[-length]
    a_stat = [(temp- stat.mean(a))/stat.stdev(a) for temp in a]
    return sum(1 for temp in a_stat if abs(temp) > 1)/length < 0.5

def log_row(logname, row):
    with open(logname, 'a') as logfile:
        logwriter = csv.writer(logfile, delimiter=',')
        logwriter.writerow(row)