utils.py

# --------------------------------------------------------
# Swin Transformer
# Copyright (c) 2021 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ze Liu
# --------------------------------------------------------

import os
import torch
import torch.distributed as dist
from torch._six import inf
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
import numpy as np
import random

def load_checkpoint(config, model, optimizer, lr_scheduler, logger):
    logger.info(f"==============> Resuming form {config.MODEL.RESUME}....................")
    if config.MODEL.RESUME.startswith('https'):
        checkpoint = torch.hub.load_state_dict_from_url(
            config.MODEL.RESUME, map_location='cpu', check_hash=True)
    else:
        checkpoint = torch.load(config.MODEL.RESUME, map_location='cpu')
    msg = model.load_state_dict(checkpoint['model'], strict=False)
    logger.info(msg)
    max_accuracy = [1e6] * 3
    return max_accuracy
    if not config.EVAL_MODE and 'optimizer' in checkpoint and 'lr_scheduler' in checkpoint and 'epoch' in checkpoint:
        optimizer.load_state_dict(checkpoint['optimizer'])
        #lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
        config.defrost()
        config.TRAIN.START_EPOCH = checkpoint['epoch'] + 1
        config.freeze()
        logger.info(f"=> loaded successfully '{config.MODEL.RESUME}' (epoch {checkpoint['epoch']})")
        if 'max_accuracy' in checkpoint:
            max_accuracy = checkpoint['max_accuracy']

    del checkpoint
    torch.cuda.empty_cache()
    return max_accuracy


def save_checkpoint(config, epoch, model, max_accuracy, optimizer, lr_scheduler, logger):
    lrschdict = None
    if lr_scheduler is not None:
        lrschdict = lr_scheduler.state_dict()
    save_state = {'model': model.state_dict(),
                  'optimizer': optimizer.state_dict(),
                  'lr_scheduler': lrschdict,
                  'max_accuracy': max_accuracy,
                  'epoch': epoch,
                  'config': config}
    save_path = os.path.join(config.OUTPUT, f'ckpt_epoch_{epoch}.pth')
    logger.info(f"{save_path} saving......")
    torch.save(save_state, save_path)
    logger.info(f"{save_path} saved !!!")


def get_grad_norm(parameters, norm_type=2):
    if isinstance(parameters, torch.Tensor):
        parameters = [parameters]
    parameters = [p for p in parameters if p.grad is not None]
    norm_type = float(norm_type)
    if len(parameters) == 0:
        return torch.tensor(0.)
    device = parameters[0].grad.device
    if norm_type == inf:
        total_norm = max(p.grad.detach().abs().max().to(device) for p in parameters)
    else:
        total_norm = torch.norm(torch.stack([torch.norm(p.grad.detach(),
                                                        norm_type).to(device) for p in parameters]), norm_type)
    return total_norm

def auto_resume_helper(output_dir):
    checkpoints = os.listdir(output_dir)
    checkpoints = [ckpt for ckpt in checkpoints if ckpt.endswith('pth')]
    print(f"All checkpoints founded in {output_dir}: {checkpoints}")
    if len(checkpoints) > 0:
        latest_checkpoint = max([os.path.join(output_dir, d) for d in checkpoints], key=os.path.getmtime)
        print(f"The latest checkpoint founded: {latest_checkpoint}")
        resume_file = latest_checkpoint
    else:
        resume_file = None
    return resume_file


def reduce_tensor(tensor):
    rt = tensor.clone()
    dist.all_reduce(rt, op=dist.ReduceOp.SUM)
    rt /= dist.get_world_size()
    return rt


def plot_curve(label, epoch, data, savepath):
    fig = plt.figure()
    plt.title(label)
    plt.plot(epoch, data)
    plt.xlabel('Epochs')
    plt.ylabel(label)
    plt.grid(True)
    plt.savefig(savepath)
    plt.close(fig)

def set_seed(seed):
    os.environ['PYTHONHASHSEED'] = str(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)  # if you are using multi-GPU.
    np.random.seed(seed)  # Numpy module.
    random.seed(seed)  # Python random module.
    torch.manual_seed(seed)
    torch.backends.cudnn.benchmark = False
    torch.backends.cudnn.deterministic = True