utils.py

'''Some helper functions for PyTorch, including:
    - get_mean_and_std: calculate the mean and std value of dataset.
    - msr_init: net parameter initialization.
    - progress_bar: progress bar mimic xlua.progress.
    - tensorboard visualizations

    Disclaimer: Most code copited from offcial documentation.
'''
import os
import sys
import time
import matplotlib.pyplot as plt
import torch.nn as nn
import torch.nn.init as init
import torch
import torch.nn.functional as F
import numpy as np
import shutil
import pathlib
from tqdm import tqdm
from os.path import join


class AverageMeter(object):
    """Computes and stores the average and current value"""
    def __init__(self):
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        self.val = val
        self.sum += val * n
        self.count += n
        self.avg = self.sum / self.count


def train(train_loader, model, criterion, optimizer, opt):
    losses = AverageMeter()
    top1 = AverageMeter()
    top5 = AverageMeter()

    # switch to train mode
    model.train()

    for _, (input, target) in enumerate(tqdm(train_loader, dynamic_ncols=True, unit='batch')):
        if opt.cuda:
            target = target.cuda() # use of async=True is deprecated in cuda param.
            input = input.cuda()
        input_var = torch.autograd.Variable(input)
        target_var = torch.autograd.Variable(target)

        # compute output
        output = model(input_var)
        loss = criterion(output, target_var)

        # measure accuracy and record loss
        prec1, prec5 = accuracy(output.data, target, topk=(1, 5))
        losses.update(loss.item(), input.size(0))
        top1.update(prec1.item(), input.size(0))
        top5.update(prec5.item(), input.size(0))

        # compute gradient and do SGD step
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        print(' * Training Prec@1 {top1.avg:.3f}\t Prec@5 {top5.avg:.3f}'.format(top1=top1, top5=top5))

def validate(val_loader, model, criterion, opt, print_freq=10):
    batch_time = AverageMeter()
    losses = AverageMeter()
    top1 = AverageMeter()
    top5 = AverageMeter()

    # switch to evaluate mode
    model.eval()
    end = time.time()
    for i, (input, target) in enumerate(tqdm(val_loader, dynamic_ncols=True, unit='batch')):
        if opt.cuda:
            target = target.cuda() # use of async=True is deprecated in cuda param.
            input = input.cuda()

        with torch.no_grad():
            input_var = torch.autograd.Variable(input)
            target_var = torch.autograd.Variable(target)

        # compute output
        output = model(input_var)
        loss = criterion(output, target_var).cuda()

        # measure accuracy and record loss
        prec1, prec5 = accuracy(output.data, target, topk=(1, 5))
        losses.update(loss.item(), input.size(0))
        top1.update(prec1.item(), input.size(0))
        top5.update(prec5.item(), input.size(0))

        # measure elapsed time
        batch_time.update(time.time() - end)
        end = time.time()

        if i % print_freq == 0:
            print('Test: [{0}/{1}]\t'
                  'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
                  'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
                  'Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t'
                  'Prec@5 {top5.val:.3f} ({top5.avg:.3f})'.format(
                i, len(val_loader), batch_time=batch_time, loss=losses,
                top1=top1, top5=top5))

    return top1.avg#, top5.avg


def save_model(dir_path,state, epoch, is_best):
    #dir_path = model/model_name/image_type
    if not os.path.exists(dir_path):
        os.makedirs(dir_path)
    pathlib.Path(dir_path).mkdir(exist_ok=True)

    model_file = join(dir_path, "ckpt_epoch_{}.pth".format(epoch))
    #torch.save(state, os.path.join(filepath, 'checkpoint.pth.tar'))
    torch.save(state, model_file)
    if is_best:
        shutil.copyfile(model_file, os.path.join(dir_path,'ckpt_best.pth'))

    
    
#     dir_path = "model/" + model_name
#     if not os.path.exists(dir_path):
#         os.makedirs(dir_path)
#     pathlib.Path(dir_path).mkdir(exist_ok=True)

#     model_file = join(dir_path, "ckpt_epoch_{}.pth".format(epoch))

#     if is_best:
# #         'shutil.copyfile( os.path.join(model_file, 'ckpt_best.pth'))
#         shutil.rmtree(dir_path)
#         pathlib.Path(dir_path).mkdir(exist_ok=True)

#         torch.save(state, model_file)
#         shutil.copyfile(model_file, 'ckpt_best.pth')
#     else:
#         torch.save(state, model_file)


def adjust_learning_rate(optimizer, epoch, lr):
    """Sets the learning rate to the initial LR decayed by 10 every 50 epochs"""
    lr = lr * (0.1 ** (epoch // 50))
    # lr = opt.lr * (0.98 ** epoch)
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr


def accuracy(output, target, topk=(1,)):
    """Computes the precision@k for the specified values of k"""
    maxk = max(topk)
    batch_size = target.size(0)

    _, pred = output.topk(maxk, 1, True, True)
    pred = pred.t()
    correct = pred.eq(target.view(1, -1).expand_as(pred))

    res = []
    for k in topk:
        correct_k = correct[:k].view(-1).float().sum(0)
        res.append(correct_k.mul_(100.0 / batch_size))

    return res


def get_mean_and_std(dataset):
    '''Compute the mean and std value of dataset.'''
    dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=2)
    mean = torch.zeros(3)
    std = torch.zeros(3)
    print('==> Computing mean and std..')
    for inputs, targets in dataloader:
        for i in range(3):
            mean[i] += inputs[:,i,:,:].mean()
            std[i] += inputs[:,i,:,:].std()
    mean.div_(len(dataset))
    std.div_(len(dataset))
    return mean, std


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)


_, term_width = os.popen('stty size', 'r').read().split()
term_width = int(term_width)

TOTAL_BAR_LENGTH = 65.
last_time = time.time()
begin_time = last_time


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

    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(' | Tot: %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)+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

# helper functions

def images_to_probs(net, images):
    '''
    Generates predictions and corresponding probabilities from a trained
    network and a list of images
    '''
    output = net(images)
    # convert output probabilities to predicted class
    _, preds_tensor = torch.max(output, 1)
    preds = np.squeeze(preds_tensor.cpu())
    return preds, [F.softmax(el, dim=0)[i].item() for i, el in zip(preds, output)]


# helper function to show an image
# (used in the `plot_classes_preds` function below)
def matplotlib_imshow(img, one_channel=False):
    if one_channel:
        img = img.mean(dim=0)
    img = img / 2 + 0.5     # unnormalize
    npimg = img.cpu()
    if one_channel:
        plt.imshow(npimg, cmap="Greys")
    else:
        plt.imshow(np.transpose(npimg, (1, 2, 0)))


def plot_classes_preds(net, images, labels, classes):
    '''
    Generates matplotlib Figure using a trained network, along with images
    and labels from a batch, that shows the network's top prediction along
    with its probability, alongside the actual label, coloring this
    information based on whether the prediction was correct or not.
    Uses the "images_to_probs" function.
    '''
    preds, probs = images_to_probs(net, images)
    # plot the images in the batch, along with predicted and true labels
    fig = plt.figure(figsize=(12, 48))
    for idx in np.arange(4):
        ax = fig.add_subplot(1, 4, idx+1, xticks=[], yticks=[])
        matplotlib_imshow(images[idx], one_channel=True)
        ax.set_title("{0}, {1:.1f}%\n(label: {2})".format(
            classes[preds[idx]],
            probs[idx] * 100.0,
            classes[labels[idx]]),
                    color=("green" if preds[idx]==labels[idx].item() else "red"))
    return fig