def main(device=torch.device('cuda:0')):
# CLI arguments
parser = arg.ArgumentParser(
description='We all know what we are doing. Fighting!')
parser.add_argument("--datasize",
"-d",
default="small",
type=str,
help="data size you want to use, small, medium, total")
# Parsing
args = parser.parse_args()
# Data loaders
datasize = args.datasize
pathname = "data/nyu.zip"
tr_loader, va_loader, te_loader = getTrainingValidationTestingData(
datasize, pathname, batch_size=config("unet.batch_size"))
# Model
#model = Net()
#model = Dense121()
model = Dense169()
model = model.to(device)
# define loss function
# criterion = torch.nn.L1Loss()
# Attempts to restore the latest checkpoint if exists
print("Loading unet...")
model, start_epoch, stats = utils.restore_checkpoint(
model, utils.config("unet.checkpoint"))
acc, loss = utils.evaluate_model(model, te_loader, device)
# axes = util.make_training_plot()
print(f'Test Error:{acc}')
print(f'Test Loss:{loss}')
# Get Test Images
img_list = glob("examples/" + "*.png")
# Set model to eval mode
model.eval()
model = model.to(device)
# Begin testing loop
print("Begin Test Loop ...")
for idx, img_name in enumerate(img_list):
img = load_images([img_name])
img = torch.Tensor(img).float().to(device)
print("Processing {}, Tensor Shape: {}".format(img_name, img.shape))
with torch.no_grad():
preds = model(img).squeeze(0)
output = colorize(preds.data)
output = output.transpose((1, 2, 0))
cv2.imwrite(img_name.split(".")[0] + "_result.png", output)
print("Processing {} done.".format(img_name))
def main(device=torch.device('cuda:0')):
# CLI arguments
parser = arg.ArgumentParser(
description='We all know what we are doing. Fighting!')
parser.add_argument("--datasize",
"-d",
default="small",
type=str,
help="data size you want to use, small, medium, total")
# Parsing
args = parser.parse_args()
# Data loaders
# TODO:
####### Enter the model selection here! #####
modelSelection = input(
'Please input the type of model to be used(res50,dense121,dense169,mob_v2,mob):'
)
datasize = args.datasize
filename = "nyu_new.zip"
pathname = f"data/{filename}"
csv = "data/nyu_csv.zip"
te_loader = getTestingData(datasize,
csv,
pathname,
batch_size=config(modelSelection +
".batch_size"))
# Model
if modelSelection.lower() == 'res50':
model = Res50()
elif modelSelection.lower() == 'dense121':
model = Dense121()
elif modelSelection.lower() == 'mob_v2':
model = Mob_v2()
elif modelSelection.lower() == 'dense169':
model = Dense169()
elif modelSelection.lower() == 'mob':
model = Net()
elif modelSelection.lower() == 'squeeze':
model = Squeeze()
else:
assert False, 'Wrong type of model selection string!'
model = model.to(device)
# define loss function
# criterion = torch.nn.L1Loss()
# Attempts to restore the latest checkpoint if exists
print(f"Loading {mdoelSelection}...")
model, start_epoch, stats = utils.restore_checkpoint(
model, utils.config(modelSelection + ".checkpoint"))
acc, loss = utils.evaluate_model(model, te_loader, device, test=True)
# axes = util.make_training_plot()
print(f'Test Error:{acc}')
print(f'Test Loss:{loss}')
def main(device=torch.device('cuda:0')):
# Model
modelSelection = input(
'Please input the type of model to be used(res50,dense121,dense169,dense161,mob_v2,mob):'
)
if modelSelection.lower() == 'res50':
model = Res50()
elif modelSelection.lower() == 'dense121':
model = Dense121()
elif modelSelection.lower() == 'dense161':
model = Dense161()
elif modelSelection.lower() == 'mob_v2':
model = Mob_v2()
elif modelSelection.lower() == 'dense169':
model = Dense169()
elif modelSelection.lower() == 'mob':
model = Net()
elif modelSelection.lower() == 'squeeze':
model = Squeeze()
else:
assert False, 'Wrong type of model selection string!'
model = model.to(device)
# Attempts to restore the latest checkpoint if exists
print("Loading unet...")
model, start_epoch, stats = utils.restore_checkpoint(
model, utils.config(modelSelection + ".checkpoint"))
# Get Test Images
img_list = glob("examples/" + "*.png")
# Set model to eval mode
model.eval()
model = model.to(device)
# Begin testing loop
print("Begin Test Loop ...")
for idx, img_name in enumerate(img_list):
img = load_images([img_name])
img = torch.Tensor(img).float().to(device)
print("Processing {}, Tensor Shape: {}".format(img_name, img.shape))
with torch.no_grad():
preds = model(img).squeeze(0)
output = colorize(preds.data)
output = output.transpose((1, 2, 0))
cv2.imwrite(
img_name.split(".")[0] + "_" + modelSelection + "_result.png",
output)
print("Processing {} done.".format(img_name))
def __init__(self, imgH, nc, nclass, nh, n_rnn=2, leakyRelu=False):
super(CRNN, self).__init__()
assert imgH % 16 == 0, 'imgH has to be a multiple of 16'
ks = [3, 3, 3, 3, 3, 3, 2]
ps = [1, 1, 1, 1, 1, 1, 0]
ss = [1, 1, 1, 1, 1, 1, 1]
nm = [64, 128, 256, 256, 512, 512, 512]
#cnn = nn.Sequential()
# def convRelu(i, batchNormalization=False):
# nIn = nc if i == 0 else nm[i - 1]
# nOut = nm[i]
# cnn.add_module('conv{0}'.format(i),
# nn.Conv2d(nIn, nOut, ks[i], ss[i], ps[i]))
# if batchNormalization:
# cnn.add_module('batchnorm{0}'.format(i), nn.BatchNorm2d(nOut))
# if leakyRelu:
# cnn.add_module('relu{0}'.format(i),
# nn.LeakyReLU(0.2, inplace=True))
# else:
# cnn.add_module('relu{0}'.format(i), nn.ReLU(True))
# convRelu(0)
# cnn.add_module('pooling{0}'.format(0), nn.MaxPool2d(2, 2)) # 64x16x64
# convRelu(1)
# cnn.add_module('pooling{0}'.format(1), nn.MaxPool2d(2, 2)) # 128x8x32
# convRelu(2, True)
# convRelu(3)
# cnn.add_module('pooling{0}'.format(2),
# nn.MaxPool2d((2, 2), (2, 1), (0, 1))) # 256x4x16
# convRelu(4, True)
# convRelu(5)
# cnn.add_module('pooling{0}'.format(3),
# nn.MaxPool2d((2, 2), (2, 1), (0, 1))) # 512x2x16
# convRelu(6, True) # 512x1x16
# self.cnn = cnn
self.cnn = Dense169(32)
self.rnn = nn.Sequential(BidirectionalLSTM(512, nh, nh),
BidirectionalLSTM(nh, nh, nclass))
def main(device, tr_loader, va_loader, te_loader, modelSelection):
"""Train CNN and show training plots."""
# Model
if modelSelection.lower() == 'res50':
model = Res50()
elif modelSelection.lower() == 'dense121':
model = Dense121()
elif modelSelection.lower() == 'dense161':
model = Dense161()
elif modelSelection.lower() == 'mobv2':
model = Mob_v2()
elif modelSelection.lower() == 'dense169':
model = Dense169()
elif modelSelection.lower() == 'mob':
model = Net()
elif modelSelection.lower() == 'squeeze':
model = Squeeze()
else:
assert False, 'Wrong type of model selection string!'
model = model.to(device)
# TODO: define loss function, and optimizer
learning_rate = utils.config(modelSelection + ".learning_rate")
criterion = DepthLoss(0.1).to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
number_of_epoches = 10
#
# Attempts to restore the latest checkpoint if exists
print("Loading unet...")
model, start_epoch, stats = utils.restore_checkpoint(
model, utils.config(modelSelection + ".checkpoint"))
running_va_loss = [] if 'va_loss' not in stats else stats['va_loss']
running_va_acc = [] if 'va_err' not in stats else stats['va_err']
running_tr_loss = [] if 'tr_loss' not in stats else stats['tr_loss']
running_tr_acc = [] if 'tr_err' not in stats else stats['tr_err']
tr_acc, tr_loss = utils.evaluate_model(model, tr_loader, device)
acc, loss = utils.evaluate_model(model, va_loader, device)
running_va_acc.append(acc)
running_va_loss.append(loss)
running_tr_acc.append(tr_acc)
running_tr_loss.append(tr_loss)
stats = {
'va_err': running_va_acc,
'va_loss': running_va_loss,
'tr_err': running_tr_acc,
'tr_loss': running_tr_loss,
}
# Loop over the entire dataset multiple times
# for epoch in range(start_epoch, config('cnn.num_epochs')):
epoch = start_epoch
# while curr_patience < patience:
while epoch < number_of_epoches:
# Train model
utils.train_epoch(device, tr_loader, model, criterion, optimizer)
# Save checkpoint
utils.save_checkpoint(model, epoch + 1,
utils.config(modelSelection + ".checkpoint"),
stats)
# Evaluate model
tr_acc, tr_loss = utils.evaluate_model(model, tr_loader, device)
va_acc, va_loss = utils.evaluate_model(model, va_loader, device)
running_va_acc.append(va_acc)
running_va_loss.append(va_loss)
running_tr_acc.append(tr_acc)
running_tr_loss.append(tr_loss)
epoch += 1
print("Finished Training")
utils.make_plot(running_tr_loss, running_tr_acc, running_va_loss,
running_va_acc)
def main(device, tr_loader, va_loader, te_loader, modelSelection):
"""Train CNN and show training plots."""
# CLI arguments
# parser = arg.ArgumentParser(description='We all know what we are doing. Fighting!')
# parser.add_argument("--datasize", "-d", default="small", type=str,
# help="data size you want to use, small, medium, total")
# Parsing
# args = parser.parse_args()
# Data loaders
# datasize = args.datasize
# Model
if modelSelection.lower() == 'res50':
model = Res50()
elif modelSelection.lower() == 'dense121':
model = Dense121()
elif modelSelection.lower() == 'mobv2':
model = Mob_v2()
elif modelSelection.lower() == 'dense169':
model = Dense169()
elif modelSelection.lower() == 'mob':
model = Net()
elif modelSelection.lower() == 'squeeze':
model = Squeeze()
else:
assert False, 'Wrong type of model selection string!'
# Model
# model = Net()
# model = Squeeze()
model = model.to(device)
# TODO: define loss function, and optimizer
learning_rate = utils.config(modelSelection + ".learning_rate")
criterion = DepthLoss(0.1).to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
number_of_epoches = 10
#
# Attempts to restore the latest checkpoint if exists
print("Loading unet...")
model, start_epoch, stats = utils.restore_checkpoint(
model, utils.config(modelSelection + ".checkpoint"))
running_va_loss = [] if 'va_loss' not in stats else stats['va_loss']
running_va_acc = [] if 'va_err' not in stats else stats['va_err']
running_tr_loss = [] if 'tr_loss' not in stats else stats['tr_loss']
running_tr_acc = [] if 'tr_err' not in stats else stats['tr_err']
tr_acc, tr_loss = utils.evaluate_model(model, tr_loader, device)
acc, loss = utils.evaluate_model(model, va_loader, device)
running_va_acc.append(acc)
running_va_loss.append(loss)
running_tr_acc.append(tr_acc)
running_tr_loss.append(tr_loss)
stats = {
'va_err': running_va_acc,
'va_loss': running_va_loss,
'tr_err': running_tr_acc,
'tr_loss': running_tr_loss,
# 'num_of_epoch': 0
}
# Loop over the entire dataset multiple times
# for epoch in range(start_epoch, config('cnn.num_epochs')):
epoch = start_epoch
# while curr_patience < patience:
while epoch < number_of_epoches:
# Train model
utils.train_epoch(device, tr_loader, model, criterion, optimizer)
# Save checkpoint
utils.save_checkpoint(model, epoch + 1,
utils.config(modelSelection + ".checkpoint"),
stats)
# Evaluate model
tr_acc, tr_loss = utils.evaluate_model(model, tr_loader, device)
va_acc, va_loss = utils.evaluate_model(model, va_loader, device)
running_va_acc.append(va_acc)
running_va_loss.append(va_loss)
running_tr_acc.append(tr_acc)
running_tr_loss.append(tr_loss)
epoch += 1
print("Finished Training")
utils.make_plot(running_tr_loss, running_tr_acc, running_va_loss,
running_va_acc)
import torch.nn as nn
from dense169 import Dense169
#from .Dense169 import Dense169
Dense169()
class BidirectionalLSTM(nn.Module):
def __init__(self, nIn, nHidden, nOut):
super(BidirectionalLSTM, self).__init__()
self.rnn = nn.LSTM(nIn, nHidden, bidirectional=True)
self.embedding = nn.Linear(nHidden * 2, nOut)
def forward(self, input):
recurrent, _ = self.rnn(input)
T, b, h = recurrent.size()
t_rec = recurrent.view(T * b, h)
output = self.embedding(t_rec) # [T * b, nOut]
output = output.view(T, b, -1)
return output
class CRNN(nn.Module):
def __init__(self, imgH, nc, nclass, nh, n_rnn=2, leakyRelu=False):
super(CRNN, self).__init__()
assert imgH % 16 == 0, 'imgH has to be a multiple of 16'
ks = [3, 3, 3, 3, 3, 3, 2]
def main(device=torch.device('cuda:0')):
# CLI arguments
parser = arg.ArgumentParser(
description='We all know what we are doing. Fighting!')
parser.add_argument("--datasize",
"-d",
default="small",
type=str,
help="data size you want to use, small, medium, total")
# Parsing
args = parser.parse_args()
# Data loaders
datasize = args.datasize
pathname = "data/nyu.zip"
# Model
modelSelection = input(
'Please input the type of model to be used(res50,dense121,dense169,mob_v2,mob):'
)
# Model
if modelSelection.lower() == 'res50':
model = Res50()
elif modelSelection.lower() == 'dense121':
model = Dense121()
elif modelSelection.lower() == 'mob_v2':
model = Mob_v2()
elif modelSelection.lower() == 'dense169':
model = Dense169()
elif modelSelection.lower() == 'mob':
model = Net()
elif modelSelection.lower() == 'squeeze':
model = Squeeze()
else:
assert False, 'Wrong type of model selection string!'
model = model.to(device)
# Attempts to restore the latest checkpoint if exists
print("Loading unet...")
model, start_epoch, stats = utils.restore_checkpoint(
model, utils.config(modelSelection + ".checkpoint"))
# Get Test Images
img_list = glob("examples/" + "*.png")
# Set model to eval mode
model.eval()
model = model.to(device)
# Begin testing loop
print("Begin Test Loop ...")
for idx, img_name in enumerate(img_list):
img = load_images([img_name])
img = torch.Tensor(img).float().to(device)
print("Processing {}, Tensor Shape: {}".format(img_name, img.shape))
with torch.no_grad():
preds = model(img).squeeze(0)
output = colorize(preds.data)
output = output.transpose((1, 2, 0))
cv2.imwrite(
img_name.split(".")[0] + "_" + modelSelection + "_result.png",
output)
print("Processing {} done.".format(img_name))
