|
|
50鱼币
复现train.py的时候报错 我个人认为可能是ymal文件的路径没有被读取 去options.py设置完好像依然找不到路径 我在网上看的读ymal文件的代码写法和作者有点出入 所以不太懂了 希望大神们不吝赐教- import os
- import math
- import argparse
- import random
- import logging
- import torch
- import torch.distributed as dist
- import torch.multiprocessing as mp
- from data.data_sampler import DistIterSampler
- import options.options as option
- from utils import util
- from data import create_dataloader, create_dataset
- from models import create_model
- def init_dist(backend='nccl', **kwargs):
- ''' initialization for distributed training'''
- # if mp.get_start_method(allow_none=True) is None:
- if mp.get_start_method(allow_none=True) != 'spawn':
- mp.set_start_method('spawn')
- rank = int(os.environ['RANK'])
- num_gpus = torch.cuda.device_count()
- torch.cuda.set_device(rank % num_gpus)
- dist.init_process_group(backend=backend, **kwargs)
- def main():
- #### options
- parser = argparse.ArgumentParser()
- parser.add_argument('-opt', type=str, help='Path to option YMAL file.')
- parser.add_argument('--launcher', choices=['none', 'pytorch'], default='none',
- help='job launcher')
- parser.add_argument('--local_rank', type=int, default=0)
- args = parser.parse_args()
- opt = option.parse(args.opt, is_train=True)
- #### distributed training settings
- if args.launcher == 'none': # disabled distributed training
- opt['dist'] = False
- rank = -1
- print('Disabled distributed training.')
- else:
- opt['dist'] = True
- init_dist()
- world_size = torch.distributed.get_world_size()
- rank = torch.distributed.get_rank()
- #### loading resume state if exists
- if opt['path'].get('resume_state', None):
- # distributed resuming: all load into default GPU
- device_id = torch.cuda.current_device()
- resume_state = torch.load(opt['path']['resume_state'],
- map_location=lambda storage, loc: storage.cuda(device_id))
- option.check_resume(opt, resume_state['iter']) # check resume options
- else:
- resume_state = None
- #### mkdir and loggers
- if rank <= 0: # normal training (rank -1) OR distributed training (rank 0)
- if resume_state is None:
- util.mkdir_and_rename(
- opt['path']['experiments_root']) # rename experiment folder if exists
- util.mkdirs((path for key, path in opt['path'].items() if not key == 'experiments_root'
- and 'pretrain_model' not in key and 'resume' not in key))
- # config loggers. Before it, the log will not work
- util.setup_logger('base', opt['path']['log'], 'train_' + opt['name'], level=logging.INFO,
- screen=True, tofile=True)
- util.setup_logger('val', opt['path']['log'], 'val_' + opt['name'], level=logging.INFO,
- screen=True, tofile=True)
- logger = logging.getLogger('base')
- logger.info(option.dict2str(opt))
- # tensorboard logger
- if opt['use_tb_logger'] and 'debug' not in opt['name']:
- version = float(torch.__version__[0:3])
- if version >= 1.1: # PyTorch 1.1
- from torch.utils.tensorboard import SummaryWriter
- else:
- logger.info(
- 'You are using PyTorch {}. Tensorboard will use [tensorboardX]'.format(version))
- from tensorboardX import SummaryWriter
- tb_logger = SummaryWriter(log_dir='../tb_logger/' + opt['name'])
- else:
- util.setup_logger('base', opt['path']['log'], 'train', level=logging.INFO, screen=True)
- logger = logging.getLogger('base')
- # convert to NoneDict, which returns None for missing keys
- opt = option.dict_to_nonedict(opt)
- #### random seed
- seed = opt['train']['manual_seed']
- if seed is None:
- seed = random.randint(1, 10000)
- if rank <= 0:
- logger.info('Random seed: {}'.format(seed))
- util.set_random_seed(seed)
- torch.backends.cudnn.benchmark = True
- # torch.backends.cudnn.deterministic = True
- #### create train and val dataloader
- dataset_ratio = 200 # enlarge the size of each epoch
- for phase, dataset_opt in opt['datasets'].items():
- if phase == 'train':
- train_set = create_dataset(dataset_opt)
- train_size = int(math.ceil(len(train_set) / dataset_opt['batch_size']))
- total_iters = int(opt['train']['niter'])
- total_epochs = int(math.ceil(total_iters / train_size))
- if opt['dist']:
- train_sampler = DistIterSampler(train_set, world_size, rank, dataset_ratio)
- total_epochs = int(math.ceil(total_iters / (train_size * dataset_ratio)))
- else:
- train_sampler = None
- train_loader = create_dataloader(train_set, dataset_opt, opt, train_sampler)
- if rank <= 0:
- logger.info('Number of train images: {:,d}, iters: {:,d}'.format(
- len(train_set), train_size))
- logger.info('Total epochs needed: {:d} for iters {:,d}'.format(
- total_epochs, total_iters))
- elif phase == 'val':
- val_set = create_dataset(dataset_opt)
- val_loader = create_dataloader(val_set, dataset_opt, opt, None)
- if rank <= 0:
- logger.info('Number of val images in [{:s}]: {:d}'.format(
- dataset_opt['name'], len(val_set)))
- else:
- raise NotImplementedError('Phase [{:s}] is not recognized.'.format(phase))
- assert train_loader is not None
- #### create model
- model = create_model(opt)
- #### resume training
- if resume_state:
- logger.info('Resuming training from epoch: {}, iter: {}.'.format(
- resume_state['epoch'], resume_state['iter']))
- start_epoch = resume_state['epoch']
- current_step = resume_state['iter']
- model.resume_training(resume_state) # handle optimizers and schedulers
- else:
- current_step = 0
- start_epoch = 0
- #### training
- logger.info('Start training from epoch: {:d}, iter: {:d}'.format(start_epoch, current_step))
- for epoch in range(start_epoch, total_epochs + 1):
- if opt['dist']:
- train_sampler.set_epoch(epoch)
- for _, train_data in enumerate(train_loader):
- current_step += 1
- if current_step > total_iters:
- break
- #### update learning rate
- model.update_learning_rate(current_step, warmup_iter=opt['train']['warmup_iter'])
- #### training
- model.feed_data(train_data)
- model.optimize_parameters(current_step)
- #### log
- if current_step % opt['logger']['print_freq'] == 0:
- logs = model.get_current_log()
- message = '<epoch:{:3d}, iter:{:8,d}, lr:{:.3e}> '.format(
- epoch, current_step, model.get_current_learning_rate())
- for k, v in logs.items():
- message += '{:s}: {:.4e} '.format(k, v)
- # tensorboard logger
- if opt['use_tb_logger'] and 'debug' not in opt['name']:
- if rank <= 0:
- tb_logger.add_scalar(k, v, current_step)
- if rank <= 0:
- logger.info(message)
- # validation
- if current_step % opt['train']['val_freq'] == 0 and rank <= 0:
- avg_psnr = 0.0
- idx = 0
- for val_data in val_loader:
- idx += 1
- img_name = os.path.splitext(os.path.basename(val_data['LQ_path'][0]))[0]
- img_dir = os.path.join(opt['path']['val_images'], img_name)
- util.mkdir(img_dir)
- model.feed_data(val_data)
- model.test()
- visuals = model.get_current_visuals()
- sr_img = util.tensor2img(visuals['SR']) # uint8
- gt_img = util.tensor2img(visuals['GT']) # uint8
- # Save SR images for reference
- save_img_path = os.path.join(img_dir,
- '{:s}_{:d}.png'.format(img_name, current_step))
- util.save_img(sr_img, save_img_path)
- # calculate PSNR
- crop_size = opt['scale']
- gt_img = gt_img / 255.
- sr_img = sr_img / 255.
- cropped_sr_img = sr_img[crop_size:-crop_size, crop_size:-crop_size, :]
- cropped_gt_img = gt_img[crop_size:-crop_size, crop_size:-crop_size, :]
- avg_psnr += util.calculate_psnr(cropped_sr_img * 255, cropped_gt_img * 255)
- avg_psnr = avg_psnr / idx
- # log
- logger.info('# Validation # PSNR: {:.4e}'.format(avg_psnr))
- logger_val = logging.getLogger('val') # validation logger
- logger_val.info('<epoch:{:3d}, iter:{:8,d}> psnr: {:.4e}'.format(
- epoch, current_step, avg_psnr))
- # tensorboard logger
- if opt['use_tb_logger'] and 'debug' not in opt['name']:
- tb_logger.add_scalar('psnr', avg_psnr, current_step)
- #### save models and training states
- if current_step % opt['logger']['save_checkpoint_freq'] == 0:
- if rank <= 0:
- logger.info('Saving models and training states.')
- model.save(current_step)
- model.save_training_state(epoch, current_step)
- if rank <= 0:
- logger.info('Saving the final model.')
- model.save('latest')
- logger.info('End of training.')
- if __name__ == '__main__':
- main()
这是train.py的代码
你的电脑上是没有配置任何的深度学习环境么？比如说cuda cudnn pytorch等环境？
这种代码都不是网上查一个库 下载下来就直接能用的，
（第0步，确定你电脑的gpu还可以，必须是英伟达的显卡，1060起步）
首先你需要先配置一个pytorch环境，网上有很多的教程。
然后跑一个“hello world”程序，测试你的pytorch环境是否安装成功。
之后才是根据你下载的代码进行运行测试，如果你是从github下载的代码，一般会在readme.md中介绍这个代码怎么运行，跟着他的说明，一步一步的再把代码跑起来。
|
-
报错
最佳答案
查看完整内容
你的电脑上是没有配置任何的深度学习环境么？比如说cuda cudnn pytorch等环境？
这种代码都不是网上查一个库 下载下来就直接能用的，
（第0步，确定你电脑的gpu还可以，必须是英伟达的显卡，1060起步）
首先你需要先配置一个pytorch环境，网上有很多的教程。
然后跑一个“hello world”程序，测试你的pytorch环境是否安装成功。
之后才是根据你下载的代码进行运行测试，如果你是从github下载的代码，一般会在readme.md中 ...
|
( 粤ICP备18085999号-1 | 粤公网安备 44051102000585号)
狗仔卡
发表于 2020-2-23 07:45:08
置顶卡
千斤顶
显身卡
发表于 2020-2-23 07:45:09
楼主
