Skip to content

GitLab

Commit 5a42d7a9 authored by Benjamin Thomas Graham's avatar Benjamin Thomas Graham
Browse files

tidy

parent c54569a8
Show whitespace changes
Inline Side-by-side
Showing with 82 additions and 72 deletions
examples/Assamese_handwriting/data.py
View file @ 5a42d7a9
......@@ -40,7 +40,7 @@ def train(spatial_size, Scale, precomputeSize):
v = torch.FloatTensor([1, 0, 0])
np_random = np.random.RandomState(tbl['idx'])
for char in tbl['input']:
inp.addSample()
inp.add_sample()
m = torch.eye(2)
r = np_random.randint(1, 3)
alpha = random.uniform(-0.2, 0.2)
......@@ -80,7 +80,7 @@ def train(spatial_size, Scale, precomputeSize):
# for j in np.arange(0,1,1/l):
# p[0]=math.floor(x1*j+x2*(1-j))
# p[1]=math.floor(y1*j+y2*(1-j))
# inp.setLocation(p,v,False)
# inp.set_location(p,v,False)
###############################################################
inp.precomputeMetadata(precomputeSize)
return {'input': inp, 'target': torch.LongTensor(tbl['target']) - 1}
......@@ -107,7 +107,7 @@ def val(spatial_size, Scale, precomputeSize):
p = torch.LongTensor(2)
v = torch.FloatTensor([1, 0, 0])
for char in tbl['input']:
inp.addSample()
inp.add_sample()
for stroke in char:
stroke = stroke.float() * (Scale - 0.01) / 255 - 0.5 * (Scale - 0.01)
stroke += center.expand_as(stroke)
......@@ -128,5 +128,5 @@ def val(spatial_size, Scale, precomputeSize):
return iter
def getIterators(*args):
def get_iterators(*args):
return {'train': train(*args), 'val': val(*args)}
examples/Chinese_handwriting/DenseNet-A-VSC.py
View file @ 5a42d7a9
......@@ -7,7 +7,7 @@
import torch
import torch.legacy.nn as nn
import sparseconvnet.legacy as scn
from data import getIterators
from data import get_iterators
# Use the GPU if there is one, otherwise CPU
dtype = 'torch.cuda.FloatTensor' if torch.cuda.is_available() else 'torch.FloatTensor'
......@@ -38,7 +38,7 @@ print(model)
spatial_size = sparseModel.suggestInputSize(torch.LongTensor([1, 1]))
print('input spatial size', spatial_size)
dataset = getIterators(spatial_size, 64, 2)
dataset = get_iterators(spatial_size, 64, 2)
scn.ClassificationTrainValidate(
model, dataset,
{'nEpochs': 100, 'initial_LR': 0.1, 'LR_decay': 0.05, 'weightDecay': 1e-4})
examples/Chinese_handwriting/ResNet-A-VSC.py
View file @ 5a42d7a9
......@@ -7,7 +7,7 @@
import torch
import torch.legacy.nn as nn
import sparseconvnet.legacy as scn
from data import getIterators
from data import get_iterators
# Use the GPU if there is one, otherwise CPU
dtype = 'torch.cuda.FloatTensor' if torch.cuda.is_available() else 'torch.FloatTensor'
......@@ -34,7 +34,7 @@ print(model)
spatial_size = sparseModel.suggestInputSize(torch.LongTensor([1, 1]))
print('input spatial size', spatial_size)
dataset = getIterators(spatial_size, 63, 3)
dataset = get_iterators(spatial_size, 63, 3)
scn.ClassificationTrainValidate(
model, dataset,
{'nEpochs': 100, 'initial_LR': 0.1, 'LR_decay': 0.05, 'weightDecay': 1e-4})
examples/Chinese_handwriting/VGG-C.py
View file @ 5a42d7a9
......@@ -5,35 +5,40 @@
# LICENSE file in the root directory of this source tree.
import torch
import torch.legacy.nn as nn
import sparseconvnet.legacy as scn
from data import getIterators
# Use the GPU if there is one, otherwise CPU
dtype = 'torch.cuda.FloatTensor' if torch.cuda.is_available() else 'torch.FloatTensor'
import torch.nn as nn
import sparseconvnet as scn
from data import get_iterators
# two-dimensional SparseConvNet
model = nn.Sequential()
sparseModel = scn.Sequential()
denseModel = nn.Sequential()
model.add(sparseModel).add(denseModel)
sparseModel.add(scn.SparseVggNet(2, 3, [
class Model(nn.Module):
def __init__(self):
nn.Module.__init__(self)
self.sparseModel = scn.SparseVggNet(2, 3, [
['C', 16], ['C', 16], 'MP',
['C', 32], ['C', 32], 'MP',
['C', 48], ['C', 48], 'MP',
['C', 64], ['C', 64], 'MP',
['C', 96], ['C', 96]]))
sparseModel.add(scn.Convolution(2, 96, 128, 3, 2, False))
sparseModel.add(scn.BatchNormReLU(128))
sparseModel.add(scn.SparseToDense(2))
denseModel.add(nn.View(-1, 128))
denseModel.add(nn.Linear(128, 3755))
model.type(dtype)
print(model)
['C', 96], ['C', 96]]
).add(scn.Convolution(2, 96, 128, 3, 2, False)
).add(scn.BatchNormReLU(128)
).add(scn.SparseToDense(2, 128))
self.linear = nn.Linear(128, 3755)
def forward(self, x):
x = self.sparseModel(x)
x = x.view(-1, 128)
x = self.linear(x)
return x
spatial_size = sparseModel.suggestInputSize(torch.LongTensor([1, 1]))
print('input spatial size', spatial_size)
dataset = getIterators(spatial_size, 63, 3)
model = Model()
spatial_size = model.sparseModel.input_spatial_size(torch.LongTensor([1, 1]))
print('Input spatial size:', spatial_size)
dataset = get_iterators(spatial_size, 63, 3)
scn.ClassificationTrainValidate(
model, dataset,
{'nEpochs': 100, 'initial_LR': 0.1, 'LR_decay': 0.05, 'weightDecay': 1e-4})
{'n_epochs': 100,
'initial_lr': 0.1,
'lr_decay': 0.05,
'weight_decay': 1e-4,
'use_gpu': torch.cuda.is_available(),
'check_point': True, })
examples/Chinese_handwriting/VGG-Cplus.py
View file @ 5a42d7a9
......@@ -5,35 +5,40 @@
# LICENSE file in the root directory of this source tree.
import torch
import torch.legacy.nn as nn
import sparseconvnet.legacy as scn
from data import getIterators
# Use the GPU if there is one, otherwise CPU
dtype = 'torch.cuda.FloatTensor' if torch.cuda.is_available() else 'torch.FloatTensor'
import torch.nn as nn
import sparseconvnet as scn
from data import get_iterators
# two-dimensional SparseConvNet
model = nn.Sequential()
sparseModel = scn.Sequential()
denseModel = nn.Sequential()
model.add(sparseModel).add(denseModel)
sparseModel.add(scn.SparseVggNet(2, 3, [
class Model(nn.Module):
def __init__(self):
nn.Module.__init__(self)
self.sparseModel = scn.SparseVggNet(2, 3, [
['C', 16, 8], ['C', 16, 8], 'MP',
['C', 32, 8], ['C', 32, 8], 'MP',
['C', 48, 16], ['C', 48, 16], 'MP',
['C', 64, 16], ['C', 64, 16], 'MP',
['C', 96, 16], ['C', 96, 16]]))
sparseModel.add(scn.Convolution(2, 96 + 16, 128, 3, 2, False))
sparseModel.add(scn.BatchNormReLU(128))
sparseModel.add(scn.SparseToDense(2))
denseModel.add(nn.View(-1, 128))
denseModel.add(nn.Linear(128, 3755))
model.type(dtype)
print(model)
['C', 96, 16], ['C', 96, 16]]
).add(scn.Convolution(2, 112, 128, 3, 2, False)
).add(scn.BatchNormReLU(128)
).add(scn.SparseToDense(2, 128))
self.linear = nn.Linear(128, 3755)
def forward(self, x):
x = self.sparseModel(x)
x = x.view(-1, 128)
x = self.linear(x)
return x
spatial_size = sparseModel.suggestInputSize(torch.LongTensor([1, 1]))
print('input spatial size', spatial_size)
dataset = getIterators(spatial_size, 63, 3)
model = Model()
spatial_size = model.sparseModel.input_spatial_size(torch.LongTensor([1, 1]))
print('Input spatial size:', spatial_size)
dataset = get_iterators(spatial_size, 63, 3)
scn.ClassificationTrainValidate(
model, dataset,
{'nEpochs': 100, 'initial_LR': 0.1, 'LR_decay': 0.05, 'weightDecay': 1e-4})
{'n_epochs': 100,
'initial_lr': 0.1,
'lr_decay': 0.05,
'weight_decay': 1e-4,
'use_gpu': torch.cuda.is_available(),
'check_point': True, })
examples/Chinese_handwriting/data.py
View file @ 5a42d7a9
......@@ -39,7 +39,7 @@ def train(spatial_size, Scale, precomputeSize):
p = torch.LongTensor(2)
v = torch.FloatTensor([1, 0, 0])
for char in tbl['input']:
inp.addSample()
inp.add_sample()
for stroke in char:
stroke = stroke.float() * (Scale - 0.01) / 255 - 0.5 * (Scale - 0.01)
stroke += center.expand_as(stroke)
......@@ -66,7 +66,7 @@ def train(spatial_size, Scale, precomputeSize):
# for j in numpy.arange(0,1,1/l):
# p[0]=math.floor(x1*j+x2*(1-j))
# p[1]=math.floor(y1*j+y2*(1-j))
# inp.setLocation(p,v,False)
# inp.set_location(p,v,False)
###############################################################
inp.precomputeMetadata(precomputeSize)
return {'input': inp, 'target': torch.LongTensor(tbl['target'])}
......@@ -93,7 +93,7 @@ def val(spatial_size, Scale, precomputeSize):
p = torch.LongTensor(2)
v = torch.FloatTensor([1, 0, 0])
for char in tbl['input']:
inp.addSample()
inp.add_sample()
for stroke in char:
stroke = stroke.float() * (Scale - 0.01) / 255 - 0.5 * (Scale - 0.01)
stroke += center.expand_as(stroke)
......@@ -114,5 +114,5 @@ def val(spatial_size, Scale, precomputeSize):
return iter
def getIterators(*args):
def get_iterators(*args):
return {'train': train(*args), 'val': val(*args)}
examples/hello-world.py
View file @ 5a42d7a9
......@@ -36,17 +36,17 @@ msg = [
" X X X X X X X X X X X X X X X X X X ",
" X X XXX XXX XXX XX X X XX X X XXX XXX "]
# Add a sample using setLocation
input.addSample()
# Add a sample using set_location
input.add_sample()
for y, line in enumerate(msg):
for x, c in enumerate(line):
if c == 'X':
location = torch.LongTensor([y, x])
featureVector = torch.FloatTensor([1])
input.setLocation(location, featureVector, 0)
input.set_location(location, featureVector, 0)
# Add a sample using setLocations
input.addSample()
# Add a sample using set_locations
input.add_sample()
locations = []
features = []
for y, line in enumerate(msg):
......@@ -56,7 +56,7 @@ for y, line in enumerate(msg):
features.append([1])
locations = torch.LongTensor(locations)
features = torch.FloatTensor(features)
input.setLocations(locations, features, 0)
input.set_locations(locations, features, 0)
# Optional: allow metadata preprocessing to be done in batch preparation threads
# to improve GPU utilization.
......
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