Skip to content

GitLab

Commit 8425bd86 authored by Hang Zhang's avatar Hang Zhang
Browse files

fix typo

parent 0f6efd80
Hide whitespace changes
Inline Side-by-side
Showing with 56 additions and 87 deletions
.gitignore
View file @ 8425bd86
......@@ -9,5 +9,4 @@ docs/html/
encoding/lib/
encoding/_ext/
encoding.egg-info/
experiments/recognition/
experiments/segmentation/
docs/source/experiments/texture.rst
View file @ 8425bd86
......@@ -19,7 +19,7 @@ Test Pre-trained Model
git clone git@github.com:zhanghang1989/PyTorch-Encoding.git
- Download the `MINC-2500 <http://opensurfaces.cs.cornell.edu/publications/minc/>`_ dataset to ``$HOME/data/minc`` folder. Download pre-trained model (training `curve`_ as bellow, pre-trained on train-1 split using single training size of 224, with an error rate of :math:`19.98\%` using single crop on test-1 set)::
- Download the `MINC-2500 <http://opensurfaces.cs.cornell.edu/publications/minc/>`_ dataset to ``$HOME/data/minc-2500/`` folder. Download pre-trained model (training `curve`_ as bellow, pre-trained on train-1 split using single training size of 224, with an error rate of :math:`19.98\%` using single crop on test-1 set)::
cd PyTorch-Encoding/experiments
bash model/download_models.sh
......@@ -31,7 +31,7 @@ Test Pre-trained Model
- Test pre-trained model on MINC-2500::
>>> python main.py --dataset minc --model encodingnet --resume model/minc.pth.tar --eval
>>> python main.py --dataset minc --model deepten --nclass 23 --resume model/minc.pth.tar --eval
# Teriminal Output:
#[======================================== 23/23 ===================================>...] Step: 104ms | Tot: 3s256ms | Loss: 0.719 | Err: 19.983% (1149/5750)
......@@ -41,7 +41,7 @@ Train Your Own Model
- Example training command for training above model::
python main.py --dataset minc --model encodingnet --batch-size 64 --lr 0.01 --epochs 60
python main.py --model deepten --nclass 23 --model encodingnet --batch-size 64 --lr 0.01 --epochs 60
- Training options::
......
encoding/nn/encoding.py
View file @ 8425bd86
......@@ -93,8 +93,8 @@ class Encoding(Module):
X = X.view(B,D,-1).transpose(1,2).contiguous()
else:
raise RuntimeError('Encoding Layer unknown input dims!')
# assignment weights
A = F.softmax(scaledL2(X, self.codewords, self.scale), dim=2)
# assignment weights NxKxD
A = F.softmax(scaledL2(X, self.codewords, self.scale), dim=1)
# aggregate
E = aggregate(A, X, self.codewords)
return E
......@@ -146,7 +146,7 @@ class EncodingShake(Module):
# shake
self.shake()
# assignment weights
A = F.softmax(scaledL2(X, self.codewords, self.scale), dim=2)
A = F.softmax(scaledL2(X, self.codewords, self.scale), dim=1)
# aggregate
E = aggregate(A, X, self.codewords)
# shake
......
encoding/utils.py
View file @ 8425bd86
......@@ -68,7 +68,7 @@ class LR_Scheduler(object):
self.N = args.epochs * niters
self.epoch = -1
def __call__(self, optimizer, i, epoch):
def __call__(self, optimizer, i, epoch, best_pred):
if self.mode == 'cos':
T = (epoch - 1) * self.niters + i
lr = 0.5 * self.lr * (1 + math.cos(1.0 * T / self.N * math.pi))
......@@ -80,8 +80,9 @@ class LR_Scheduler(object):
else:
raise RuntimeError('Unknown LR scheduler!')
if epoch > self.epoch:
print('\n=>Epoches %i, learning rate = %.4f' % (
epoch, lr))
print('\n=>Epoches %i, learning rate = %.4f, \
previous best = %.4f' % (
epoch, lr, best_pred))
self.epoch = epoch
self._adjust_learning_rate(optimizer, lr)
......
experiments/main.py → experiments/recognition/main.py
View file @ 8425bd86
......@@ -10,6 +10,7 @@
from __future__ import print_function
import os
import matplotlib.pyplot as plot
import importlib
......@@ -22,29 +23,13 @@ from torch.autograd import Variable
from option import Options
from encoding.utils import *
from tqdm import tqdm
# global variable
best_pred = 100.0
errlist_train = []
errlist_val = []
def adjust_learning_rate(optimizer, args, epoch, best_pred):
if epoch <= 60:
lr = args.lr * (0.1 ** ((epoch - 1) // 40))
else:
lr = 1e-4
print('=>Epochs %i, learning rate = %.4f, previous best = %.3f%%' % (
epoch, lr, best_pred))
if len(optimizer.param_groups) == 1:
optimizer.param_groups[0]['lr'] = lr
elif len(optimizer.param_groups) == 2:
# enlarge the lr at the head
optimizer.param_groups[0]['lr'] = lr
optimizer.param_groups[1]['lr'] = lr * 10
else:
raise RuntimeError('unsupported number of param groups: {}' \
.format(len(optimizer.param_groups)))
def main():
# init the args
global best_pred, errlist_train, errlist_val
......@@ -64,19 +49,15 @@ def main():
train_loader, test_loader = Dataloder(args).getloader()
# init the model
models = importlib.import_module('model.'+args.model)
model = models.Net()
model = models.Net(args)
print(model)
# criterion and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = get_optimizer(args, model)
optimizer = get_optimizer(args, model, False)
if args.cuda:
model.cuda()
# Please use CUDA_VISIBLE_DEVICES to control the number of gpus
model = torch.nn.DataParallel(model)
"""
optim.SGD(model.parameters(), lr=args.lr, momentum=
args.momentum, weight_decay=args.weight_decay)
"""
# check point
if args.resume is not None:
if os.path.isfile(args.resume):
......@@ -93,14 +74,15 @@ def main():
else:
print("=> no resume checkpoint found at '{}'".\
format(args.resume))
#scheduler = CosLR_Scheduler(args, len(train_loader))
scheduler = LR_Scheduler(args, len(train_loader))
def train(epoch):
model.train()
global best_pred, errlist_train
train_loss, correct, total = 0,0,0
adjust_learning_rate(optimizer, args, epoch, best_pred)
for batch_idx, (data, target) in enumerate(train_loader):
#scheduler(optimizer, batch_idx, epoch, best_pred)
#adjust_learning_rate(optimizer, args, epoch, best_pred)
tbar = tqdm(train_loader, desc='\r')
for batch_idx, (data, target) in enumerate(tbar):
scheduler(optimizer, batch_idx, epoch, best_pred)
if args.cuda:
data, target = data.cuda(), target.cuda()
data, target = Variable(data), Variable(target)
......@@ -115,10 +97,9 @@ def main():
correct += pred.eq(target.data).cpu().sum()
total += target.size(0)
err = 100-100.*correct/total
progress_bar(batch_idx, len(train_loader),
'Loss: %.3f | Err: %.3f%% (%d/%d)' % \
(train_loss/(batch_idx+1),
err, total-correct, total))
tbar.set_description('\rLoss: %.3f | Err: %.3f%% (%d/%d)' % \
(train_loss/(batch_idx+1), err, total-correct, total))
errlist_train += [err]
def test(epoch):
......@@ -126,7 +107,8 @@ def main():
global best_pred, errlist_train, errlist_val
test_loss, correct, total = 0,0,0
is_best = False
for batch_idx, (data, target) in enumerate(test_loader):
tbar = tqdm(test_loader, desc='\r')
for batch_idx, (data, target) in enumerate(tbar):
if args.cuda:
data, target = data.cuda(), target.cuda()
data, target = Variable(data, volatile=True), Variable(target)
......@@ -138,10 +120,8 @@ def main():
total += target.size(0)
err = 100-100.*correct/total
progress_bar(batch_idx, len(test_loader),
'Loss: %.3f | Err: %.3f%% (%d/%d)'% \
(test_loss/(batch_idx+1),
err, total-correct, total))
tbar.set_description('Loss: %.3f | Err: %.3f%% (%d/%d)'% \
(test_loss/(batch_idx+1), err, total-correct, total))
if args.eval:
print('Error rate is %.3f'%err)
......
experiments/model/encodingnet.py → experiments/recognition/model/deepten.py
View file @ 8425bd86
......@@ -17,19 +17,19 @@ import encoding
import torchvision.models as resnet
class Net(nn.Module):
def __init__(self, nclass=23, aux=False, backbone='resnet50'):
def __init__(self, args):
nclass=args.nclass
super(Net, self).__init__()
self.backbone = backbone
self.backbone = args.backbone
# copying modules from pretrained models
if backbone == 'resnet50':
if self.backbone == 'resnet50':
self.pretrained = resnet.resnet50(pretrained=True)
elif backbone == 'resnet101':
elif self.backbone == 'resnet101':
self.pretrained = resnet.resnet101(pretrained=True)
elif backbone == 'resnet152':
elif self.backbone == 'resnet152':
self.pretrained = resnet.resnet152(pretrained=True)
else:
raise RuntimeError('unknown backbone: {}'.format(backbone))
self.aux = aux
raise RuntimeError('unknown backbone: {}'.format(self.backbone))
n_codes = 32
self.head = nn.Sequential(
nn.Conv2d(2048, 128, 1),
......@@ -51,35 +51,13 @@ class Net(nn.Module):
_, _, h, w = var_input.size()
else:
raise RuntimeError('unknown input type: ', type(x))
if self.backbone == 'resnet50' or self.backbone == 'resnet101' \
or self.backbone == 'resnet152':
# pre-trained ResNet feature
x = self.pretrained.conv1(x)
x = self.pretrained.bn1(x)
x = self.pretrained.relu(x)
x = self.pretrained.maxpool(x)
x = self.pretrained.layer1(x)
x = self.pretrained.layer2(x)
x = self.pretrained.layer3(x)
x = self.pretrained.layer4(x)
else:
x = self.pretrained(x)
x = self.pretrained.conv1(x)
x = self.pretrained.bn1(x)
x = self.pretrained.relu(x)
x = self.pretrained.maxpool(x)
x = self.pretrained.layer1(x)
x = self.pretrained.layer2(x)
x = self.pretrained.layer3(x)
x = self.pretrained.layer4(x)
return self.head(x)
def test():
net = Net(nclass=23).cuda()
print(net)
x = Variable(torch.randn(1,3,224,224)).cuda()
y = net(x)
print(y)
params = net.parameters()
sum = 0
for param in params:
sum += param.nelement()
print('Total params:', sum)
if __name__ == "__main__":
test()
experiments/option.py → experiments/recognition/option.py
View file @ 8425bd86
......@@ -17,11 +17,15 @@ class Options():
parser = argparse.ArgumentParser(description='Deep Encoding')
parser.add_argument('--dataset', type=str, default='cifar10',
help='training dataset (default: cifar10)')
# model params
parser.add_argument('--model', type=str, default='densenet',
help='network model type (default: densenet)')
# scale factor for HangsNet only
parser.add_argument('--nclass', type=int, default=10, metavar='N',
help='number of classes (default: 10)')
parser.add_argument('--widen', type=int, default=4, metavar='N',
help='widen factor of the network (default: 4)')
parser.add_argument('--backbone', type=str, default='resnet50',
help='backbone name (default: resnet50)')
# training hyper params
parser.add_argument('--batch-size', type=int, default=128,
metavar='N', help='batch size for training (default: 128)')
......@@ -31,12 +35,18 @@ class Options():
help='number of epochs to train (default: 300)')
parser.add_argument('--start_epoch', type=int, default=1,
metavar='N', help='the epoch number to start (default: 0)')
# lr setting
parser.add_argument('--lr', type=float, default=0.1, metavar='LR',
help='learning rate (default: 0.1)')
parser.add_argument('--lr-scheduler', type=str, default='step',
help='learning rate scheduler (default: step)')
parser.add_argument('--lr-step', type=int, default=40, metavar='LR',
help='learning rate step (default: 40)')
# optimizer
parser.add_argument('--momentum', type=float, default=0.9,
metavar='M', help='SGD momentum (default: 0.9)')
parser.add_argument('--weight-decay', type=float, default=1e-4,
metavar ='M', help='SGD weight decay (default: 1e-4)')
parser.add_argument('--weight-decay', type=float, default=5e-4,
metavar ='M', help='SGD weight decay (default: 5e-4)')
# cuda, seed and logging
parser.add_argument('--no-cuda', action='store_true',
default=False, help='disables CUDA training')
......@@ -53,5 +63,6 @@ class Options():
parser.add_argument('--eval', action='store_true', default= False,
help='evaluating')
self.parser = parser
def parse(self):
return self.parser.parse_args()
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment