Spaces:
Build error
Build error
File size: 5,403 Bytes
e78c13e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 |
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import time
from collections import OrderedDict
from options.train_options import TrainOptions
from data.data_loader import CreateDataLoader
from models.models import create_da_model
import util.util as util
from util.visualizer import Visualizer
import os
import numpy as np
import torch
import torchvision.utils as vutils
from torch.autograd import Variable
opt = TrainOptions().parse()
if opt.debug:
opt.display_freq = 1
opt.print_freq = 1
opt.niter = 1
opt.niter_decay = 0
opt.max_dataset_size = 10
data_loader = CreateDataLoader(opt)
dataset = data_loader.load_data()
dataset_size = len(dataset) * opt.batchSize
print('#training images = %d' % dataset_size)
path = os.path.join(opt.checkpoints_dir, opt.name, 'model.txt')
visualizer = Visualizer(opt)
iter_path = os.path.join(opt.checkpoints_dir, opt.name, 'iter.txt')
if opt.continue_train:
try:
start_epoch, epoch_iter = np.loadtxt(iter_path, delimiter=',', dtype=int)
except:
start_epoch, epoch_iter = 1, 0
visualizer.print_save('Resuming from epoch %d at iteration %d' % (start_epoch - 1, epoch_iter))
else:
start_epoch, epoch_iter = 1, 0
# opt.which_epoch=start_epoch-1
model = create_da_model(opt)
fd = open(path, 'w')
fd.write(str(model.module.netG))
fd.write(str(model.module.netD))
fd.close()
total_steps = (start_epoch - 1) * dataset_size + epoch_iter
display_delta = total_steps % opt.display_freq
print_delta = total_steps % opt.print_freq
save_delta = total_steps % opt.save_latest_freq
for epoch in range(start_epoch, opt.niter + opt.niter_decay + 1):
epoch_start_time = time.time()
if epoch != start_epoch:
epoch_iter = epoch_iter % dataset_size
for i, data in enumerate(dataset, start=epoch_iter):
iter_start_time = time.time()
total_steps += opt.batchSize
epoch_iter += opt.batchSize
# whether to collect output images
save_fake = total_steps % opt.display_freq == display_delta
############## Forward Pass ######################
losses, generated = model(Variable(data['label']), Variable(data['inst']),
Variable(data['image']), Variable(data['feat']), infer=save_fake)
# sum per device losses
losses = [torch.mean(x) if not isinstance(x, int) else x for x in losses]
loss_dict = dict(zip(model.module.loss_names, losses))
# calculate final loss scalar
loss_D = (loss_dict['D_fake'] + loss_dict['D_real']) * 0.5
loss_featD=(loss_dict['featD_fake'] + loss_dict['featD_real']) * 0.5
loss_G = loss_dict['G_GAN'] + loss_dict.get('G_GAN_Feat', 0) + loss_dict.get('G_VGG', 0) + loss_dict['G_KL'] + loss_dict['G_featD']
############### Backward Pass ####################
# update generator weights
model.module.optimizer_G.zero_grad()
loss_G.backward()
model.module.optimizer_G.step()
# update discriminator weights
model.module.optimizer_D.zero_grad()
loss_D.backward()
model.module.optimizer_D.step()
model.module.optimizer_featD.zero_grad()
loss_featD.backward()
model.module.optimizer_featD.step()
# call(["nvidia-smi", "--format=csv", "--query-gpu=memory.used,memory.free"])
############## Display results and errors ##########
### print out errors
if total_steps % opt.print_freq == print_delta:
errors = {k: v.data if not isinstance(v, int) else v for k, v in loss_dict.items()}
t = (time.time() - iter_start_time) / opt.batchSize
visualizer.print_current_errors(epoch, epoch_iter, errors, t, model.module.old_lr)
visualizer.plot_current_errors(errors, total_steps)
### display output images
if save_fake:
if not os.path.exists(opt.outputs_dir + opt.name):
os.makedirs(opt.outputs_dir + opt.name)
imgs_num = data['label'].shape[0]
imgs = torch.cat((data['label'], generated.data.cpu(), data['image']), 0)
imgs = (imgs + 1.) / 2.0
try:
image_grid = vutils.save_image(imgs, opt.outputs_dir + opt.name + '/' + str(epoch) + '_' + str(
total_steps) + '.png',
nrow=imgs_num, padding=0, normalize=True)
except OSError as err:
print(err)
if epoch_iter >= dataset_size:
break
# end of epoch
iter_end_time = time.time()
print('End of epoch %d / %d \t Time Taken: %d sec' %
(epoch, opt.niter + opt.niter_decay, time.time() - epoch_start_time))
### save model for this epoch
if epoch % opt.save_epoch_freq == 0:
print('saving the model at the end of epoch %d, iters %d' % (epoch, total_steps))
model.module.save('latest')
model.module.save(epoch)
np.savetxt(iter_path, (epoch + 1, 0), delimiter=',', fmt='%d')
### instead of only training the local enhancer, train the entire network after certain iterations
if (opt.niter_fix_global != 0) and (epoch == opt.niter_fix_global):
model.module.update_fixed_params()
### linearly decay learning rate after certain iterations
if epoch > opt.niter:
model.module.update_learning_rate()
|