def train(dataloader, parameters, device):
model = AutoEncoder(input_dim=1900,
nlayers=parameters.get('nlayers', 5),
latent=100)
model = model.to(device)
model.train()
train_loss = 0
optimizer = torch.optim.Adam(model.parameters(),
lr=parameters.get('lr', 1e-5),
weight_decay=parameters.get(
'weight_decay', 0.))
loss_func = torch.nn.MSELoss()
for epoch in range(parameters.get('epochs', 1000)):
for index, (data, ) in enumerate(dataloader, 1):
optimizer.zero_grad()
output = model(data)
loss = loss_func(output, data)
train_loss += loss.item()
loss.backward()
optimizer.step()
return model
def main(opt):
device = 'cuda' if torch.cuda.is_available() else 'cpu'
# Dataset
print('Dataset....')
transform = transforms.Compose([
transforms.Resize((600, 600)),
transforms.Grayscale(3),
transforms.ToTensor()
])
train_set = myDataset(image_path=opt.train_path, transform=transform)
val_set = myDataset(image_path=opt.val_path, transform=transform)
train_loader = DataLoader(train_set, batch_size=opt.train_batch_size)
val_loader = DataLoader(val_set, batch_size=opt.val_batch_size)
# Model
print('Model....')
model = AutoEncoder()
model.to(device)
# Optimizer
optimizer = optim.Adam(model.parameters(), lr=opt.lr)
loss_func = nn.MSELoss()
# Train
print('Training....')
train_epoch_loss = []
val_epoch_loss = []
train_iter_losses = []
val_iter_losses = []
for e in range(opt.epoch):
train_iter_loss = train(opt, model, train_loader, optimizer, loss_func,
device, e)
train_iter_losses += train_iter_loss
train_epoch_loss.append(sum(train_iter_loss))
val_iter_loss = val(opt, model, val_loader, loss_func, device, e)
val_iter_losses += val_iter_loss
val_epoch_loss.append(sum(val_iter_loss))
# save model
best = 10000
if val_epoch_loss[-1] < best:
print('Saving Model....')
torch.save(model, 'weights/AutoEncoder_try1.pth')
best = val_epoch_loss[-1]
print('Saving Result')
plt.figure(figsize=(10, 10))
plt.plot(train_iter_losses)
plt.plot(val_iter_losses)
plt.legend(['Train_loss', 'Val_loss'])
plt.savefig('Result.jpg')
def train(output_filename, model_type, hidden_size, loss_type, norm_type,
sigma_noise):
train_data = torchvision.datasets.MNIST(
root='datasets/mnist/',
train=True,
transform=torchvision.transforms.ToTensor(),
download=False,
)
train_loader = Data.DataLoader(dataset=train_data,
batch_size=BATCH_SIZE,
shuffle=True)
if loss_type == 'l2':
loss_func = nn.MSELoss()
elif loss_type == 'cross_entropy':
loss_func = F.binary_cross_entropy
if model_type == 'AE':
model = AutoEncoder(hidden_size).cuda()
elif model_type == 'LTAE':
model = LatentAutoEncoder(hidden_size, norm_type,
sigma=sigma_noise).cuda()
model.set_device()
elif model_type == 'VAE':
model = VariationalAE(hidden_size).cuda()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
model.train()
for epoch in range(EPOCH):
for step, (x, _) in enumerate(train_loader):
optimizer.zero_grad()
x_batch = x.view(-1, 28 * 28).cuda()
y_batch = x.view(-1, 28 * 28).cuda()
if model_type == 'AE':
_, decoded = model(x_batch)
loss = loss_func(decoded, y_batch)
elif model_type == 'LTAE':
_, latent, transformed, decoded = model(x_batch)
loss = loss_func(decoded, y_batch)
loss += torch.nn.functional.mse_loss(transformed, latent)
elif model_type == 'VAE':
decoded, mu, logvar = model(x_batch)
loss = loss_func_vae(decoded, x_batch, mu, logvar, loss_type)
loss.backward()
optimizer.step()
if epoch % 10 == 0:
print('Epoch: ', epoch, '| train loss: %.4f' % loss.detach().cpu())
torch.save({'state_dict': model.state_dict()},
f'./saved_models/{output_filename}')
def main():
use_cuda = args.use_cuda
train_data = UnlabeledContact(data=args.data_dir)
print('Number of samples: {}'.format(len(train_data)))
trainloader = DataLoader(train_data, batch_size=args.batch_size)
# Contact matrices are 21x21
input_size = 441
img_height = 21
img_width = 21
vae = AutoEncoder(code_size=20,
imgsize=input_size,
height=img_height,
width=img_width)
criterion = nn.BCEWithLogitsLoss()
if use_cuda:
#vae = nn.DataParallel(vae)
vae = vae.cuda() #.half()
criterion = criterion.cuda()
optimizer = optim.SGD(vae.parameters(), lr=0.01)
clock = AverageMeter(name='clock32single', rank=0)
epoch_loss = 0
total_loss = 0
end = time.time()
for epoch in range(15):
for batch_idx, data in enumerate(trainloader):
inputs = data['cont_matrix']
inputs = inputs.resize_(args.batch_size, 1, 21, 21)
inputs = inputs.float()
if use_cuda:
inputs = inputs.cuda() #.half()
inputs = Variable(inputs)
optimizer.zero_grad()
output, code = vae(inputs)
loss = criterion(output, inputs)
loss.backward()
optimizer.step()
epoch_loss += loss.data[0]
clock.update(time.time() - end)
end = time.time()
if batch_idx % args.log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(trainloader.dataset),
100. * batch_idx / len(trainloader), loss.data[0]))
clock.save(
path=
'/home/ygx/libraries/mds/molecules/molecules/conv_autoencoder/runtimes'
)
def main(args):
device = torch.device(
'cuda' if torch.cuda.is_available() and not args.cpu else 'cpu')
print('Using %s device.' % device)
world_size = int(
os.environ[args.env_size]) if args.env_size in os.environ else 1
local_rank = int(
os.environ[args.env_rank]) if args.env_rank in os.environ else 0
if local_rank == 0:
print(vars(args))
if world_size > 1:
print('rank: {}/{}'.format(local_rank + 1, world_size))
torch.distributed.init_process_group(backend='gloo',
init_method='file://%s' %
args.tmpname,
rank=local_rank,
world_size=world_size)
train_dataloader, test_dataloader = load_dataset(args, device, world_size)
net = AutoEncoder(input_dim=1900, nlayers=args.nlayers,
latent=100).to(device)
if world_size > 1:
net = torch.nn.parallel.DistributedDataParallel(net)
if args.modelfile:
net.load_state_dict(torch.load(args.modelfile))
# define our optimizer and loss function
optimizer = torch.optim.Adam(net.parameters(),
lr=args.lr,
weight_decay=args.weight_decay)
loss_func = nn.MSELoss(reduction='mean')
test_losses = []
for epoch in range(args.epochs):
epoch_start = timeit.default_timer()
train(train_dataloader, net, optimizer, loss_func, epoch)
test_loss = test(test_dataloader, net, loss_func)
print(' %5.2f sec' % (timeit.default_timer() - epoch_start))
test_losses.append(test_loss)
if test_loss <= min(test_losses):
torch.save(net.state_dict(), 'model/%5.3f.pth' % min(test_losses))
download=True)
test_set = datasets.MNIST(root='./data',
train=False,
transform=transforms.ToTensor(),
download=True)
train_loader = torch.utils.data.DataLoader(dataset=train_set,
batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_set,
batch_size=batch_size,
shuffle=False)
model = AutoEncoder(input_size=input_size)
model.cuda()
optimizer = optim.Adam(
model.parameters(),
lr=LR,
betas=(0.9, 0.999),
eps=1e-08,
weight_decay=WD,
amsgrad=False) # write so many arguments to get a clear view
criterion = nn.MSELoss()
losses_adam = []
for i in range(EP):
loss_ep = 0
idx = 0
for batch_idx, (inputs, targets) in enumerate(
train_loader): # Notice that we will not use target here.
inputs = inputs.view([-1, 28 * 28]).cuda()
def train_autoencoder(train_matrix, test_set):
num_users, num_items = train_matrix.shape
weight_matrix = log_surplus_confidence_matrix(train_matrix,
alpha=args.alpha,
epsilon=args.epsilon)
train_matrix[train_matrix > 0] = 1.0
place_correlation = scipy.sparse.load_npz(
'Foursquare/place_correlation_gamma60.npz')
assert num_items == place_correlation.shape[0]
print(train_matrix.shape)
# Construct the model by instantiating the class defined in model.py
model = AutoEncoder(num_items,
args.inner_layers,
num_items,
da=args.num_attention,
dropout_rate=args.dropout_rate)
if torch.cuda.is_available():
model.cuda()
criterion = torch.nn.MSELoss(size_average=False, reduce=False)
optimizer = torch.optim.Adam(model.parameters(),
lr=args.learning_rate,
weight_decay=args.weight_decay)
batch_size = args.batch_size
user_indexes = np.arange(num_users)
model.train()
torch.load('model.pkl')
# Evaluation
model.eval()
topk = 20
recommended_list = []
for user_id in range(num_users):
user_rating_vector = train_matrix.getrow(user_id).toarray()
pred_rating_vector = model([train_matrix.getrow(user_id).indices],
place_correlation)
pred_rating_vector = pred_rating_vector.cpu().data.numpy()
user_rating_vector = user_rating_vector[0]
pred_rating_vector = pred_rating_vector[0]
pred_rating_vector[user_rating_vector > 0] = 0
item_recommended_dict = dict()
for item_inner_id, score in enumerate(pred_rating_vector):
item_recommended_dict[item_inner_id] = score
sorted_item = heapq.nlargest(topk,
item_recommended_dict,
key=item_recommended_dict.get)
recommended_list.append(sorted_item)
print(test_set[user_id], sorted_item[:topk])
print(pred_rating_vector[sorted_item[0]],
pred_rating_vector[sorted_item[1]],
pred_rating_vector[sorted_item[2]],
pred_rating_vector[sorted_item[3]],
pred_rating_vector[sorted_item[4]])
print("user:%d, precision@5:%f, precision@10:%f" %
(user_id,
eval_metrics.precision_at_k_per_sample(test_set[user_id],
sorted_item[:5], 5),
eval_metrics.precision_at_k_per_sample(
test_set[user_id], sorted_item[:topk], topk)))
precision, recall, MAP = [], [], []
for k in [5, 10, 15, 20]:
precision.append(
eval_metrics.precision_at_k(test_set, recommended_list, k))
recall.append(eval_metrics.recall_at_k(test_set, recommended_list, k))
MAP.append(eval_metrics.mapk(test_set, recommended_list, k))
print(precision)
print(recall)
print(MAP)
from model import AutoEncoder
from visualize import *
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
algo_name = 'AE'
max_episodes = 100
batch_size = 128
lr = 1e-3 # play with this value
# load dataset from MNIST, save to ../datasets
dataset = MNIST('../datasets', transform=transforms.ToTensor(), download=True)
dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True)
DeCiPhEr = AutoEncoder()
optimizer = optim.Adam(DeCiPhEr.parameters(), lr=lr)
for episode in range(max_episodes):
for data in dataloader:
img, _ = data
img = img.view(img.size(0), -1) # squash to 1D
output = DeCiPhEr(img)
# calculate loss and update acc.
loss = torch.pow(img - output, 2).mean()
optimizer.zero_grad()
loss.backward()
optimizer.step()
if episode % 10 == 0:
img = img.view(output.size(0), 1, 28, 28)
def train(args):
print('Start')
if torch.cuda.is_available():
device = 'cuda'
torch.set_default_tensor_type('torch.cuda.FloatTensor')
else:
device = 'cpu'
train_epoch = args.train_epoch
lr = args.lr
beta1 = args.beta1
beta2 = args.beta2
batch_size = args.batch_size
noise_var = args.noise_var
h_dim = args.h_dim
images_path = glob.glob(args.data_dir+'/face_images/*/*.png')
random.shuffle(images_path)
split_num = int(len(images_path)*0.8)
train_path = images_path[:split_num]
test_path = images_path[split_num:]
result_path = images_path[-15:]
train_dataset = MyDataset(train_path)
train_dataloader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_dataset = MyDataset(test_path)
test_dataloader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=True)
result_dataset = MyDataset(result_path)
result_dataloader = torch.utils.data.DataLoader(result_dataset, batch_size=result_dataset.__len__(), shuffle=False)
result_images = next(iter(result_dataloader))
model = AutoEncoder(h_dim=h_dim).to(device)
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr, (beta1, beta2))
out_path = args.model_dir
train_loss_list = []
test_loss_list = []
for epoch in range(train_epoch):
model.to(device)
loss_train = 0
for x in train_dataloader:
noised_x = add_noise(x, noise_var)
recon_x = model(noised_x)
loss = criterion(recon_x, x)
optimizer.zero_grad()
loss.backward()
optimizer.step()
loss_train += loss.item()
loss_train /= train_dataloader.__len__()
train_loss_list.append(loss_train)
if epoch % 1 == 0:
with torch.no_grad():
model.eval()
loss_test = 0
for x_test in test_dataloader:
recon_x_test = model(x_test)
loss_test += criterion(recon_x_test, x_test).item()
loss_test /= test_dataloader.__len__()
test_loss_list.append(loss_test)
np.save(os.path.join(out_path, 'train_loss.npy'), np.array(train_loss_list))
np.save(os.path.join(out_path, 'test_loss.npy'), np.array(test_loss_list))
model.train()
def main(args):
# ensures that weight initializations are all the same
torch.manual_seed(args.seed)
np.random.seed(args.seed)
torch.cuda.manual_seed(args.seed)
torch.cuda.manual_seed_all(args.seed)
logging = utils.Logger(args.global_rank, args.save)
writer = utils.Writer(args.global_rank, args.save)
# Get data loaders.
train_queue, valid_queue, num_classes, _ = datasets.get_loaders(args)
args.num_total_iter = len(train_queue) * args.epochs
warmup_iters = len(train_queue) * args.warmup_epochs
swa_start = len(train_queue) * (args.epochs - 1)
arch_instance = utils.get_arch_cells(args.arch_instance)
model = AutoEncoder(args, writer, arch_instance)
model = model.cuda()
logging.info('args = %s', args)
logging.info('param size = %fM ', utils.count_parameters_in_M(model))
logging.info('groups per scale: %s, total_groups: %d',
model.groups_per_scale, sum(model.groups_per_scale))
if args.fast_adamax:
# Fast adamax has the same functionality as torch.optim.Adamax, except it is faster.
cnn_optimizer = Adamax(model.parameters(),
args.learning_rate,
weight_decay=args.weight_decay,
eps=1e-3)
else:
cnn_optimizer = torch.optim.Adamax(model.parameters(),
args.learning_rate,
weight_decay=args.weight_decay,
eps=1e-3)
cnn_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
cnn_optimizer,
float(args.epochs - args.warmup_epochs - 1),
eta_min=args.learning_rate_min)
grad_scalar = GradScaler(2**10)
num_output = utils.num_output(args.dataset, args)
bpd_coeff = 1. / np.log(2.) / num_output
# if load
checkpoint_file = os.path.join(args.save, 'checkpoint.pt')
if args.cont_training:
logging.info('loading the model.')
checkpoint = torch.load(checkpoint_file, map_location='cpu')
init_epoch = checkpoint['epoch']
model.load_state_dict(checkpoint['state_dict'])
model = model.cuda()
cnn_optimizer.load_state_dict(checkpoint['optimizer'])
grad_scalar.load_state_dict(checkpoint['grad_scalar'])
cnn_scheduler.load_state_dict(checkpoint['scheduler'])
global_step = checkpoint['global_step']
else:
global_step, init_epoch = 0, 0
for epoch in range(init_epoch, args.epochs):
# update lrs.
if args.distributed:
train_queue.sampler.set_epoch(global_step + args.seed)
valid_queue.sampler.set_epoch(0)
if epoch > args.warmup_epochs:
cnn_scheduler.step()
# Logging.
logging.info('epoch %d', epoch)
# Training.
train_nelbo, global_step = train(train_queue, model, cnn_optimizer,
grad_scalar, global_step,
warmup_iters, writer, logging)
logging.info('train_nelbo %f', train_nelbo)
writer.add_scalar('train/nelbo', train_nelbo, global_step)
model.eval()
# generate samples less frequently
eval_freq = 1 if args.epochs <= 50 else 20
if epoch % eval_freq == 0 or epoch == (args.epochs - 1):
with torch.no_grad():
num_samples = 16
n = int(np.floor(np.sqrt(num_samples)))
for t in [0.7, 0.8, 0.9, 1.0]:
logits = model.sample(num_samples, t)
output = model.decoder_output(logits)
output_img = output.mean if isinstance(
output, torch.distributions.bernoulli.Bernoulli
) else output.sample(t)
output_tiled = utils.tile_image(output_img, n)
writer.add_image('generated_%0.1f' % t, output_tiled,
global_step)
valid_neg_log_p, valid_nelbo = test(valid_queue,
model,
num_samples=10,
args=args,
logging=logging)
logging.info('valid_nelbo %f', valid_nelbo)
logging.info('valid neg log p %f', valid_neg_log_p)
logging.info('valid bpd elbo %f', valid_nelbo * bpd_coeff)
logging.info('valid bpd log p %f', valid_neg_log_p * bpd_coeff)
writer.add_scalar('val/neg_log_p', valid_neg_log_p, epoch)
writer.add_scalar('val/nelbo', valid_nelbo, epoch)
writer.add_scalar('val/bpd_log_p', valid_neg_log_p * bpd_coeff,
epoch)
writer.add_scalar('val/bpd_elbo', valid_nelbo * bpd_coeff, epoch)
save_freq = int(np.ceil(args.epochs / 100))
if epoch % save_freq == 0 or epoch == (args.epochs - 1):
if args.global_rank == 0:
logging.info('saving the model.')
torch.save(
{
'epoch': epoch + 1,
'state_dict': model.state_dict(),
'optimizer': cnn_optimizer.state_dict(),
'global_step': global_step,
'args': args,
'arch_instance': arch_instance,
'scheduler': cnn_scheduler.state_dict(),
'grad_scalar': grad_scalar.state_dict()
}, checkpoint_file)
# Final validation
valid_neg_log_p, valid_nelbo = test(valid_queue,
model,
num_samples=1000,
args=args,
logging=logging)
logging.info('final valid nelbo %f', valid_nelbo)
logging.info('final valid neg log p %f', valid_neg_log_p)
writer.add_scalar('val/neg_log_p', valid_neg_log_p, epoch + 1)
writer.add_scalar('val/nelbo', valid_nelbo, epoch + 1)
writer.add_scalar('val/bpd_log_p', valid_neg_log_p * bpd_coeff, epoch + 1)
writer.add_scalar('val/bpd_elbo', valid_nelbo * bpd_coeff, epoch + 1)
writer.close()
trainloader = torch.utils.data.DataLoader(video,
batch_size=32,
shuffle=True,
pin_memory=True)
print("数据集准备完毕")
from model import AutoEncoder, BAN_decoder, Sine_decoder
autoencoder = AutoEncoder().cuda()
sin_decoder = Sine_decoder().cuda()
ban_decoder = BAN_decoder().cuda()
autoencoder.decoder = ban_decoder
criterion = nn.MSELoss().cuda()
optimizer = optim.Adam(autoencoder.parameters(), lr=0.001)
print("开始训练 training GeneralConv...")
stime = time.time()
for epoch in range(20):
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
optimizer.zero_grad()
Tensordata = data.float().cuda()
_, output = autoencoder(Tensordata)
loss = criterion(output, Tensordata)
loss.backward()
optimizer.step()
running_loss += loss.item()
if i % 50 == 49:
class Trainer(object):
def __init__(self, train_loader, test_loader, config):
self.train_loader = train_loader
self.test_loader = test_loader
self.config = config
self.device = torch.device(
"cuda:0" if torch.cuda.is_available() else "cpu")
self.num_epochs = config.num_epochs
self.lr = config.lr
self.in_channel = config.in_channel
self.image_size = config.image_size
self.hidden_dim = config.hidden_dim
self.output_dim = config.output_dim
self.log_interval = config.log_interval
self.sample_interval = config.sample_interval
self.ckpt_interval = config.ckpt_interval
self.sample_folder = config.sample_folder
self.ckpt_folder = config.ckpt_folder
self.build_net()
self.vis = Visualizer()
def build_net(self):
# define network
self.net = AutoEncoder(self.in_channel, self.image_size,
self.hidden_dim, self.output_dim)
if self.config.mode == 'test' and self.config.training_path == '':
print("[*] Enter model path!")
exit()
# if training model exists
if self.config.training_path != '':
self.net.load_state_dict(
torch.load(self.config.training_path,
map_location=lambda storage, loc: storage))
print("[*] Load weight from {}!".format(self.config.training_path))
self.net.to(self.device)
# add noise to image
def add_noise(self, imgs):
noise = torch.randn(imgs.size()) * 0.4
noisy_imgs = noise + imgs
return noisy_imgs
def train(self):
# define loss function
bce_criterion = nn.BCELoss().to(self.device)
mse_criterion = nn.MSELoss().to(self.device)
# define optimizer
optimizer = Adam(self.net.parameters(), self.lr)
step = 0
print("[*] Learning started!")
# get fixed sample
temp_iter = iter(self.train_loader)
fixed_imgs, _ = next(temp_iter)
fixed_imgs = fixed_imgs.to(self.device)
# save fixed sample image
x_path = os.path.join(self.sample_folder, 'fixed_input.png')
save_image(fixed_imgs, x_path, normalize=True)
print("[*] Save fixed input image!")
# make fixed noisy sample and save
fixed_noisy_imgs = self.add_noise(fixed_imgs)
noisy_x_path = os.path.join(self.sample_folder,
'fixed_noisy_input.png')
save_image(fixed_noisy_imgs, noisy_x_path, normalize=True)
print("[*] Save fixed noisy input image!")
# flatten data tensors
fixed_imgs = fixed_imgs.view(fixed_imgs.size(0), -1)
fixed_noisy_imgs = fixed_noisy_imgs.view(fixed_imgs.size(0), -1)
for epoch in range(self.num_epochs):
for i, (imgs, _) in enumerate(self.train_loader):
self.net.train()
imgs = imgs.view(imgs.size(0), -1) # original images
noisy_imgs = self.add_noise(imgs) # add noise
noisy_imgs = noisy_imgs.to(self.device)
# forwarding
outputs = self.net(noisy_imgs) # use noisy image as input
bce_loss = bce_criterion(outputs, imgs)
mse_loss = mse_criterion(outputs, imgs)
# backwarding
optimizer.zero_grad()
bce_loss.backward() # backward BCE loss
optimizer.step()
# do logging
if (step + 1) % self.log_interval == 0:
print("[{}/{}] [{}/{}] BCE loss: {:3f}, MSE loss:{:3f}".
format(epoch + 1, self.num_epochs, i + 1,
len(self.train_loader),
bce_loss.item() / len(imgs),
mse_loss.item() / len(imgs)))
self.vis.plot("BCE Loss plot", bce_loss.item() / len(imgs))
self.vis.plot("MSE Loss plot", mse_loss.item() / len(imgs))
# do sampling
if (step + 1) % self.sample_interval == 0:
outputs = self.net(fixed_noisy_imgs)
x_hat = outputs.cpu().data.view(outputs.size(0), -1,
self.image_size,
self.image_size)
x_hat_path = os.path.join(
self.sample_folder,
'output_epoch{}.png'.format(epoch + 1))
save_image(x_hat, x_hat_path, normalize=True)
print("[*] Save sample images!")
step += 1
if (epoch + 1) % self.ckpt_interval == 0:
ckpt_path = os.path.join(self.ckpt_folder,
'ckpt_epoch{}.pth'.format(epoch + 1))
torch.save(self.net.state_dict(), ckpt_path)
print("[*] Checkpoint saved!")
print("[*] Learning finished!")
ckpt_path = os.path.join(self.ckpt_folder, 'final_model.pth')
torch.save(self.net.state_dict(), ckpt_path)
print("[*] Final weight saved!")
from tqdm import tqdm
from torch import nn
import torch
import random
from hdf5_data import HDF5DatasetGenerator
from model import AutoEncoder
batch_size = 128
learning_rate = 0.01
train_gen = HDF5DatasetGenerator(db_path="train.hdf5", batch_size=batch_size)
test_gen = HDF5DatasetGenerator(db_path="test.hdf5", batch_size=batch_size)
network = AutoEncoder().cuda()
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(network.parameters(), lr=learning_rate,
weight_decay=1e-5)
for epoch in range(500):
network.train()
min_audios = 0
max_audios = 0
min_labels = 0
max_labels = 0
total_loss = 0
total = 0
with tqdm(total=train_gen.get_total_samples() / batch_size) as pbar:
for audios, labels in train_gen.generator():
indexs = np.random.permutation(audios.shape[0])
audios = audios[indexs]
help='batch size')
parser.add_argument('--epoch', type=int, default=1, help='epoch size')
opt = parser.parse_args()
# 超参数
LR = opt.lr
BATCH_SIZE = opt.batch_size
EPOCHES = opt.epoch
LOG_INTERVAL = 5
# 获取gpu是不是可用
cuda_available = torch.cuda.is_available()
# 实例化网络
auto = AutoEncoder()
if cuda_available:
auto.cuda()
# 定义优化器和损失函数
optimizer = torch.optim.Adam(auto.parameters(), lr=LR)
# 数据准备
root_dir = "./celeba_select"
image_files = os.listdir(root_dir)
train_dataset = CelebaDataset(root_dir, image_files, (64, 64),
transforms.Compose([ToTensor()]))
train_loader = DataLoader(train_dataset,
batch_size=32,
num_workers=1,
shuffle=True)
for i in range(EPOCHES):
# 打乱数据
auto.train()
train_loss = 0
for batch_idx, data in enumerate(train_loader):
data = Variable(data.type(torch.FloatTensor))
if smoothed_loss < best_loss or batch_num == 1:
best_loss = smoothed_loss
losses.append(smoothed_loss)
log_lrs.append(math.log10(lr))
optimizer.zero_grad()
loss.backward()
optimizer.step()
lr *= mult
optimizer.param_groups[0]['lr'] = lr
sys.stdout.write('\r[ %d/%d] LR: %f' % (i, len(data_loader), lr))
return log_lrs, losses
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AutoEncoder().to(device)
optimizer = Adam(model.parameters(), lr=0.01, weight_decay=0.0001)
# optimizer = AdamW(model.parameters(), lr=0.01, weight_decay=0.0001)
# optimizer = SGD(model.parameters(), lr=0.05)
# loss_fn = nn.CrossEntropyLoss()
loss_fn = nn.MSELoss()
data_loader_train = load_data('./data', 128)
logs, losses = find_lr(model=model,
data_loader=data_loader_train,
device=device)
plt.plot(logs[10:-5], losses[10:-5])
plt.show()
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
val_dataloader = torch.utils.data.DataLoader(val_dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.num_workers)
network = AutoEncoder()
if args.model is not None:
print('Loaded trained model from {}.'.format(args.model))
network.load_state_dict(torch.load(args.model))
else:
print('Begin training new model.')
network.to(DEVICE)
optimizer = optim.Adam(network.parameters(),
lr=args.lr,
weight_decay=args.weight_decay)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=20, gamma=0.7)
max_iter = int(len(train_dataset) / args.batch_size + 0.5)
minimum_loss = 1e4
best_epoch = 0
for epoch in range(1, args.epochs + 1):
# training
network.train()
total_loss, iter_count = 0, 0
for i, data in enumerate(train_dataloader, 1):
partial_input, coarse_gt, dense_gt = data
partial_input = partial_input.to(DEVICE)
from torch.utils.data import TensorDataset, DataLoader
from model import AutoEncoder
import torch.nn as nn
import torch
import numpy as np
from tqdm import tqdm
from torch.utils.tensorboard import SummaryWriter
writer = SummaryWriter("./runs/")
model = AutoEncoder().cuda()
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)
with open("../agent_code/rule_based_agent_auto_encode/states.npy", "rb") as f:
data = np.load(f, allow_pickle=False)
data = data[:2_500_000]
data_t = torch.Tensor(data)
data_t = data_t.cuda()
dataset = TensorDataset(data_t)
train_len = int(0.7 * len(dataset))
valid_len = (len(dataset) - train_len) // 2
test_len = len(dataset) - train_len - valid_len
train_dataset, valid_dataset, test_dataset = torch.utils.data.random_split(
dataset, [train_len, valid_len, test_len],
generator=torch.Generator().manual_seed(42))
batch_size = 32
def main():
parser = argparse.ArgumentParser(description='AvatarNet by Pytorch')
parser.add_argument('--batch_size',
'-b',
type=int,
default=4,
help='Number of images in each mini-batch')
parser.add_argument('--epoch',
'-e',
type=int,
default=2,
help='Number of sweeps over the dataset to train')
parser.add_argument('--patch_size',
'-p',
type=int,
default=5,
help='Size of extracted patches from style features')
parser.add_argument('--alpha',
'-a',
type=float,
default=0.8,
help='alpha control the fusion degree')
parser.add_argument('--lam1',
type=float,
default=0.01,
help='lambda1 for perceptual loss')
parser.add_argument('--lam2',
type=float,
default=0.01,
help='lambda2 for tv loss')
parser.add_argument('--gpu',
'-g',
type=int,
default=0,
help='GPU ID(nagative value indicate CPU)')
parser.add_argument('--learning_rate',
'-lr',
type=float,
default=1e-4,
help='learning rate for Adam')
parser.add_argument('--snapshot_interval',
type=int,
default=10,
help='Interval of snapshot to generate image')
parser.add_argument('--train_content_dir',
type=str,
default='/data/chen/content',
help='content images directory for train')
parser.add_argument('--train_style_dir',
type=str,
default='/data/chen/style',
help='style images directory for train')
parser.add_argument('--test_content_dir',
type=str,
default='/data/chen/content',
help='content images directory for test')
parser.add_argument('--test_style_dir',
type=str,
default='/data/chen/style',
help='style images directory for test')
parser.add_argument('--save_dir',
type=str,
default='result',
help='save directory for result and loss')
parser.add_argument('--reuse',
default=None,
help='model state path to load for reuse')
args = parser.parse_args()
# create directory to save
if not os.path.exists(args.save_dir):
os.mkdir(args.save_dir)
loss_dir = f'{args.save_dir}/loss'
model_state_dir = f'{args.save_dir}/model_state'
image_dir = f'{args.save_dir}/image'
if not os.path.exists(loss_dir):
os.mkdir(loss_dir)
os.mkdir(model_state_dir)
os.mkdir(image_dir)
# set device on GPU if available, else CPU
if torch.cuda.is_available() and args.gpu >= 0:
device = torch.device(f'cuda:{args.gpu}')
print(f'# CUDA available: {torch.cuda.get_device_name(0)}')
else:
device = 'cpu'
print(f'# Minibatch-size: {args.batch_size}')
print(f'# epoch: {args.epoch}')
print('')
# prepare dataset and dataLoader
train_dataset = PreprocessDataset(args.train_content_dir,
args.train_style_dir)
test_dataset = PreprocessDataset(args.test_content_dir,
args.test_style_dir)
iters = len(train_dataset)
print(f'Length of train image pairs: {iters}')
train_loader = DataLoader(train_dataset,
batch_size=args.batch_size,
shuffle=True)
test_loader = DataLoader(test_dataset,
batch_size=args.batch_size,
shuffle=False)
test_iter = iter(test_loader)
# set model and optimizer
model = AutoEncoder().to(device)
if args.reuse is not None:
model.load_state_dict(torch.load(args.reuse))
optimizer = Adam(model.parameters(), lr=args.learning_rate)
# start training
loss_list = []
for e in range(1, args.epoch + 1):
print(f'Start {e} epoch')
for i, (content, style) in tqdm(enumerate(train_loader, 1)):
content = content.to(device)
style = style.to(device)
loss = model(content, style, args.patch_size, args.alpha,
args.lam1, args.lam2)
loss_list.append(loss.item())
optimizer.zero_grad()
loss.backward()
optimizer.step()
print(
f'[{e}/total {args.epoch} epoch],[{i} /'
f'total {round(iters/args.batch_size)} iteration]: {loss.item()}'
)
if i % args.snapshot_interval == 0:
content, style = next(test_iter)
content = content.to(device)
style = style.to(device)
with torch.no_grad():
out = model.generate(content, style, args.patch_size,
args.alpha)
content = denorm(content, device)
style = denorm(style, device)
out = denorm(out, device)
res = torch.cat([content, style, out], dim=0)
res = res.to('cpu')
save_image(res,
f'{image_dir}/{e}_epoch_{i}_iteration.png',
nrow=args.batch_size)
torch.save(model.state_dict(), f'{model_state_dir}/{e}_epoch.pth')
plt.plot(range(len(loss_list)), loss_list)
plt.xlabel('iteration')
plt.ylabel('loss')
plt.title('train loss')
plt.savefig(f'{loss_dir}/train_loss.png')
with open(f'{loss_dir}/loss_log.txt', 'w') as f:
for l in loss_list:
f.write(f'{l}\n')
print(f'Loss saved in {loss_dir}')
def train_autoencoder(train_matrix, test_set):
num_users, num_items = train_matrix.shape
weight_matrix = log_surplus_confidence_matrix(train_matrix,
alpha=args.alpha,
epsilon=args.epsilon)
train_matrix[train_matrix > 0] = 1.0
place_correlation = scipy.sparse.load_npz(
'./data/Foursquare/place_correlation_gamma60.npz')
assert num_items == place_correlation.shape[0]
print(train_matrix.shape)
# Construct the model by instantiating the class defined in model.py
model = AutoEncoder(num_items,
args.inner_layers,
num_items,
da=args.num_attention,
dropout_rate=args.dropout_rate)
if torch.cuda.is_available():
model.cuda()
criterion = torch.nn.MSELoss(size_average=False, reduce=False)
optimizer = torch.optim.Adam(model.parameters(),
lr=args.learning_rate,
weight_decay=args.weight_decay)
batch_size = args.batch_size
user_indexes = np.arange(num_users)
model.train()
for t in range(args.epoch):
print("epoch:{}".format(t))
np.random.shuffle(user_indexes)
avg_cost = 0.
for batchID in range(int(num_users / batch_size)):
start = batchID * batch_size
end = start + batch_size
batch_user_index = user_indexes[start:end]
batch_x, batch_x_weight, batch_item_index = get_mini_batch(
train_matrix, weight_matrix, batch_user_index)
batch_x_weight += 1
batch_x = Variable(torch.from_numpy(batch_x).type(T.FloatTensor),
requires_grad=False)
y_pred = model(batch_item_index, place_correlation)
# Compute and print loss
batch_x_weight = Variable(torch.from_numpy(batch_x_weight).type(
T.FloatTensor),
requires_grad=False)
loss = (batch_x_weight *
criterion(y_pred, batch_x)).sum() / batch_size
print(batchID, loss.data)
# Zero gradients, perform a backward pass, and update the weights.
optimizer.zero_grad()
loss.backward()
optimizer.step()
avg_cost += loss / num_users * batch_size
print("Avg loss:{}".format(avg_cost))
# print the prediction score for the user 0
print(
model([train_matrix.getrow(0).indices], place_correlation)
[:,
T.LongTensor(train_matrix.getrow(0).indices.astype(np.int32))])
print(model([train_matrix.getrow(0).indices], place_correlation))
# Evaluation
model.eval()
topk = 20
recommended_list = []
for user_id in range(num_users):
user_rating_vector = train_matrix.getrow(user_id).toarray()
pred_rating_vector = model([train_matrix.getrow(user_id).indices],
place_correlation)
pred_rating_vector = pred_rating_vector.cpu().data.numpy()
user_rating_vector = user_rating_vector[0]
pred_rating_vector = pred_rating_vector[0]
pred_rating_vector[user_rating_vector > 0] = 0
item_recommended_dict = dict()
for item_inner_id, score in enumerate(pred_rating_vector):
item_recommended_dict[item_inner_id] = score
sorted_item = heapq.nlargest(topk,
item_recommended_dict,
key=item_recommended_dict.get)
recommended_list.append(sorted_item)
print(test_set[user_id], sorted_item[:topk])
print(pred_rating_vector[sorted_item[0]],
pred_rating_vector[sorted_item[1]],
pred_rating_vector[sorted_item[2]],
pred_rating_vector[sorted_item[3]],
pred_rating_vector[sorted_item[4]])
print("user:%d, precision@5:%f, precision@10:%f" %
(user_id,
eval_metrics.precision_at_k_per_sample(test_set[user_id],
sorted_item[:5], 5),
eval_metrics.precision_at_k_per_sample(
test_set[user_id], sorted_item[:topk], topk)))
precision, recall, MAP = [], [], []
for k in [5, 10, 15, 20]:
precision.append(
eval_metrics.precision_at_k(test_set, recommended_list, k))
recall.append(eval_metrics.recall_at_k(test_set, recommended_list, k))
MAP.append(eval_metrics.mapk(test_set, recommended_list, k))
print(precision)
print(recall)
print(MAP)
help='upper epoch limit')
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
print(json.dumps(args.__dict__, sort_keys=True, indent=4) + '\n')
args.device = torch.device("cuda" if args.cuda else "cpu")
# Set random seed
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed_all(args.seed)
# Load pre-trained model
model = AutoEncoder().to(args.device)
optimizer = Adam(model.parameters(), lr=0.001, weight_decay=0.0001)
# optimizer = AdamW(model.parameters(), lr=0.001, weight_decay=0.0001)
# optimizer = SGD(model.parameters(), lr=0.01)
# exp_lr_scheduler = lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.25)
exp_lr_scheduler = lr_scheduler.ReduceLROnPlateau(optimizer,
mode='min',
factor=0.5,
patience=2,
verbose=True,
min_lr=0.001)
loss_fn = nn.MSELoss()
# loss_fn = nn.BCELoss()
torch.backends.cudnn.benchmark = True
print('n parameters: %d' % sum([m.numel() for m in model.parameters()]))
torch.backends.cudnn.deterministic = DEBUG
torch.backends.cudnn.benchmark = not DEBUG
print(f'Using device {DEVICE}')
# Data loaders
train_ds = PPFDataset(**TRAIN_DS_ARGS)
train_dl = DataLoader(train_ds, **TRAIN_DL_ARGS)
val_ds = PPFDataset(**VAL_DS_ARGS)
val_dl = DataLoader(val_ds, **VAL_DL_ARGS)
print('Training set: {} Validation set: {}\n'.format(
train_ds.__len__(), val_ds.__len__()
))
# Model
model = AutoEncoder(NUM_PTS_PER_PATCH)
model.apply(init_weights).to(DEVICE)
loss_func = ChamferLoss()
optimizer = Adam(model.parameters(), LR)
scheduler = OneCycleLR(
optimizer, MAX_LR, total_steps=len(train_dl)*TRAINER_ARGS.num_epochs
)
Path(TRAINER_ARGS.checkpoint_path).parent.mkdir(parents=True, exist_ok=True)
# Training
train(model, loss_func, optimizer, scheduler, (train_dl, val_dl), TRAINER_ARGS)
def train(self, config):
"""Training routine"""
# Initialize datasets for both training and validation
train_data = torchvision.datasets.ImageFolder(
root=os.path.join(config.data_dir, "train"),
transform=torchvision.transforms.ToTensor())
valid_data = torchvision.datasets.ImageFolder(
root=os.path.join(config.data_dir, "valid"),
transform=torchvision.transforms.ToTensor())
# Create data loader for training and validation.
tr_data_loader = torch.utils.data.DataLoader(
dataset=train_data,
batch_size=config.batch_size,
num_workers=config.numWorker,
shuffle=True)
va_data_loader = torch.utils.data.DataLoader(
dataset=valid_data,
batch_size=config.batch_size,
num_workers=config.numWorker,
shuffle=False)
# Create model instance.
#model = Model()
model = AutoEncoder()
# Move model to gpu if cuda is available
if torch.cuda.is_available():
model = model.cuda()
# Make sure that the model is set for training
model.train()
# Create loss objects
data_loss = nn.MSELoss()
# Create optimizier
optimizer = optim.Adam(model.parameters(), lr=config.learn_rate)
# No need to move the optimizer (as of PyTorch 1.0), it lies in the same
# space as the model
# Create summary writer
tr_writer = SummaryWriter(
log_dir=os.path.join(config.log_dir, "train"))
va_writer = SummaryWriter(
log_dir=os.path.join(config.log_dir, "valid"))
# Create log directory and save directory if it does not exist
if not os.path.exists(config.log_dir):
os.makedirs(config.log_dir)
if not os.path.exists(config.save_dir):
os.makedirs(config.save_dir)
# Initialize training
iter_idx = -1 # make counter start at zero
best_va_acc = 0 # to check if best validation accuracy
# Prepare checkpoint file and model file to save and load from
checkpoint_file = os.path.join(config.save_dir, "checkpoint.pth")
bestmodel_file = os.path.join(config.save_dir, "best_model.pth")
# Check for existing training results. If it existst, and the configuration
# is set to resume `config.resume==True`, resume from previous training. If
# not, delete existing checkpoint.
if os.path.exists(checkpoint_file):
if config.resume:
# Use `torch.load` to load the checkpoint file and the load the
# things that are required to continue training. For the model and
# the optimizer, use `load_state_dict`. It's actually a good idea
# to code the saving part first and then code this part.
print("Checkpoint found! Resuming") # TODO proper logging
# Read checkpoint file.
# Fix gpu -> cpu bug
compute_device = 'cuda' if torch.cuda.is_available() else 'cpu'
load_res = torch.load(checkpoint_file,
map_location=compute_device)
# Resume iterations
iter_idx = load_res["iter_idx"]
# Resume best va result
best_va_acc = load_res["best_va_acc"]
# Resume model
model.load_state_dict(load_res["model"])
# Resume optimizer
optimizer.load_state_dict(load_res["optimizer"])
# Note that we do not resume the epoch, since we will never be able
# to properly recover the shuffling, unless we remember the random
# seed, for example. For simplicity, we will simply ignore this,
# and run `config.num_epoch` epochs regardless of resuming.
else:
os.remove(checkpoint_file)
# Training loop
for epoch in range(config.num_epoch):
# For each iteration
prefix = "Training Epoch {:3d}: ".format(epoch)
for data in tqdm(tr_data_loader, desc=prefix):
# Counter
iter_idx += 1
# Split the data
# x is img, y is label
x, y = data
#print(x)
# Send data to GPU if we have one
if torch.cuda.is_available():
x = x.cuda()
y = y.cuda()
# Apply the model to obtain scores (forward pass)
logits = model.forward(x)
# Compute the loss
loss = data_loss(logits, x.float())
# Compute gradients
loss.backward()
# Update parameters
optimizer.step()
# Zero the parameter gradients in the optimizer
optimizer.zero_grad()
# Monitor results every report interval
if iter_idx % config.rep_intv == 0:
# Compute accuracy (No gradients required). We'll wrapp this
# part so that we prevent torch from computing gradients.
with torch.no_grad():
pred = torch.argmax(logits, dim=1)
acc = torch.mean(
torch.eq(pred.view(x.size()), x).float()) * 100.0
# Write loss and accuracy to tensorboard, using keywords `loss`
# and `accuracy`.
tr_writer.add_scalar("loss", loss, global_step=iter_idx)
tr_writer.add_scalar("accuracy", acc, global_step=iter_idx)
# Save
torch.save(
{
"iter_idx": iter_idx,
"best_va_acc": best_va_acc,
"model": model.state_dict(),
"optimizer": optimizer.state_dict(),
"loss": loss,
"epoch": epoch,
"acc": acc
}, checkpoint_file)
# Validate results every validation interval
if iter_idx % config.val_intv == 0:
# List to contain all losses and accuracies for all the
# training batches
va_loss = []
va_acc = []
# Set model for evaluation
model = model.eval()
for data in va_data_loader:
# Split the data
x, y = data
# Send data to GPU if we have one
if torch.cuda.is_available():
x = x.cuda()
y = y.cuda()
# Apply forward pass to compute the losses
# and accuracies for each of the validation batches
with torch.no_grad():
# Compute logits
logits = model.forward(x)
# Compute loss and store as numpy
loss = data_loss(logits, x.float())
va_loss += [loss.cpu().numpy()]
# Compute accuracy and store as numpy
pred = torch.argmax(logits, dim=1)
acc = torch.mean(
torch.eq(pred.view(x.size()),
x).float()) * 100.0
va_acc += [acc.cpu().numpy()]
# Set model back for training
model = model.train()
# Take average
va_loss = np.mean(va_loss)
va_acc = np.mean(va_acc)
# Write to tensorboard using `va_writer`
va_writer.add_scalar("loss", va_loss, global_step=iter_idx)
va_writer.add_scalar("accuracy",
va_acc,
global_step=iter_idx)
# Check if best accuracy
if va_acc > best_va_acc:
best_va_acc = va_acc
# Save best model using torch.save. Similar to previous
# save but at location defined by `bestmodel_file`
torch.save(
{
"iter_idx": iter_idx,
"best_va_acc": best_va_acc,
"model": model.state_dict(),
"optimizer": optimizer.state_dict(),
"loss": loss,
"acc": acc
}, bestmodel_file)