from colorama import Fore, Back, Style
+# Pytorch
+
import torch
from torch import optim
from torch.nn import functional as fn
from torchvision import datasets, transforms, utils
-import svrt
+# SVRT
+
+from vignette_set import VignetteSet, CompressedVignetteSet
######################################################################
action='store_true', default = False,
help = 'Use lossless compression to reduce the memory footprint')
+parser.add_argument('--test_loaded_models',
+ action='store_true', default = False,
+ help = 'Should we compute the test error of models we load')
+
args = parser.parse_args()
######################################################################
log_file = open(args.log_file, 'w')
+pred_log_t = None
print(Fore.RED + 'Logging into ' + args.log_file + Style.RESET_ALL)
def log_string(s):
- s = Fore.GREEN + time.ctime() + Style.RESET_ALL + ' ' + s
+ global pred_log_t
+ t = time.time()
+
+ if pred_log_t is None:
+ elapsed = 'start'
+ else:
+ elapsed = '+{:.02f}s'.format(t - pred_log_t)
+ pred_log_t = t
+ s = Fore.BLUE + time.ctime() + ' ' + Fore.GREEN + elapsed + Style.RESET_ALL + ' ' + s
log_file.write(s + '\n')
log_file.flush()
print(s)
######################################################################
-class VignetteSet:
- def __init__(self, problem_number, nb_batches):
- self.batch_size = args.batch_size
- self.problem_number = problem_number
- self.nb_batches = nb_batches
- self.nb_samples = self.nb_batches * self.batch_size
- self.targets = []
- self.inputs = []
-
- acc = 0.0
- acc_sq = 0.0
-
- for b in range(0, self.nb_batches):
- target = torch.LongTensor(self.batch_size).bernoulli_(0.5)
- input = svrt.generate_vignettes(problem_number, target)
- input = input.float().view(input.size(0), 1, input.size(1), input.size(2))
- if torch.cuda.is_available():
- input = input.cuda()
- target = target.cuda()
- acc += input.sum() / input.numel()
- acc_sq += input.pow(2).sum() / input.numel()
- self.targets.append(target)
- self.inputs.append(input)
-
- mean = acc / self.nb_batches
- std = math.sqrt(acc_sq / self.nb_batches - mean * mean)
- for b in range(0, self.nb_batches):
- self.inputs[b].sub_(mean).div_(std)
-
- def get_batch(self, b):
- return self.inputs[b], self.targets[b]
-
-######################################################################
-
-class CompressedVignetteSet:
- def __init__(self, problem_number, nb_batches):
- self.batch_size = args.batch_size
- self.problem_number = problem_number
- self.nb_batches = nb_batches
- self.nb_samples = self.nb_batches * self.batch_size
- self.targets = []
- self.input_storages = []
-
- acc = 0.0
- acc_sq = 0.0
- for b in range(0, self.nb_batches):
- target = torch.LongTensor(self.batch_size).bernoulli_(0.5)
- input = svrt.generate_vignettes(problem_number, target)
- acc += input.float().sum() / input.numel()
- acc_sq += input.float().pow(2).sum() / input.numel()
- self.targets.append(target)
- self.input_storages.append(svrt.compress(input.storage()))
-
- self.mean = acc / self.nb_batches
- self.std = math.sqrt(acc_sq / self.nb_batches - self.mean * self.mean)
-
- def get_batch(self, b):
- input = torch.ByteTensor(svrt.uncompress(self.input_storages[b])).float()
- input = input.view(self.batch_size, 1, 128, 128).sub_(self.mean).div_(self.std)
- target = self.targets[b]
-
- if torch.cuda.is_available():
- input = input.cuda()
- target = target.cuda()
-
- return input, target
-
-######################################################################
-
# Afroze's ShallowNet
# map size nb. maps
self.conv3 = nn.Conv2d(16, 120, kernel_size=18)
self.fc1 = nn.Linear(120, 84)
self.fc2 = nn.Linear(84, 2)
+ self.name = 'shallownet'
def forward(self, x):
x = fn.relu(fn.max_pool2d(self.conv1(x), kernel_size=2))
x = self.fc2(x)
return x
+######################################################################
+
def train_model(model, train_set):
batch_size = args.batch_size
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr = 1e-2)
+ start_t = time.time()
+
for e in range(0, args.nb_epochs):
acc_loss = 0.0
for b in range(0, train_set.nb_batches):
loss.backward()
optimizer.step()
log_string('train_loss {:d} {:f}'.format(e + 1, acc_loss))
+ dt = (time.time() - start_t) / (e + 1)
+ print(Fore.CYAN + 'ETA ' + time.ctime(time.time() + dt * (args.nb_epochs - e)) + Style.RESET_ALL)
return model
for arg in vars(args):
log_string('argument ' + str(arg) + ' ' + str(getattr(args, arg)))
+######################################################################
+
for problem_number in range(1, 24):
- if args.compress_vignettes:
- train_set = CompressedVignetteSet(problem_number, args.nb_train_batches)
- test_set = CompressedVignetteSet(problem_number, args.nb_test_batches)
- else:
- train_set = VignetteSet(problem_number, args.nb_train_batches)
- test_set = VignetteSet(problem_number, args.nb_test_batches)
+
+ log_string('**** problem ' + str(problem_number) + ' ****')
model = AfrozeShallowNet()
if torch.cuda.is_available():
model.cuda()
+ model_filename = model.name + '_' + \
+ str(problem_number) + '_' + \
+ str(args.nb_train_batches) + '.param'
+
nb_parameters = 0
- for p in model.parameters():
- nb_parameters += p.numel()
+ for p in model.parameters(): nb_parameters += p.numel()
log_string('nb_parameters {:d}'.format(nb_parameters))
- model_filename = 'model_' + str(problem_number) + '.param'
-
+ need_to_train = False
try:
model.load_state_dict(torch.load(model_filename))
log_string('loaded_model ' + model_filename)
except:
- log_string('training_model')
+ need_to_train = True
+
+ if need_to_train:
+
+ log_string('training_model ' + model_filename)
+
+ t = time.time()
+
+ if args.compress_vignettes:
+ train_set = CompressedVignetteSet(problem_number,
+ args.nb_train_batches, args.batch_size,
+ cuda=torch.cuda.is_available())
+ else:
+ train_set = VignetteSet(problem_number,
+ args.nb_train_batches, args.batch_size,
+ cuda=torch.cuda.is_available())
+
+ log_string('data_generation {:0.2f} samples / s'.format(train_set.nb_samples / (time.time() - t)))
+
train_model(model, train_set)
torch.save(model.state_dict(), model_filename)
log_string('saved_model ' + model_filename)
- nb_train_errors = nb_errors(model, train_set)
+ nb_train_errors = nb_errors(model, train_set)
+
+ log_string('train_error {:d} {:.02f}% {:d} {:d}'.format(
+ problem_number,
+ 100 * nb_train_errors / train_set.nb_samples,
+ nb_train_errors,
+ train_set.nb_samples)
+ )
+
+ if need_to_train or args.test_loaded_models:
+
+ t = time.time()
+
+ if args.compress_vignettes:
+ test_set = CompressedVignetteSet(problem_number,
+ args.nb_test_batches, args.batch_size,
+ cuda=torch.cuda.is_available())
+ else:
+ test_set = VignetteSet(problem_number,
+ args.nb_test_batches, args.batch_size,
+ cuda=torch.cuda.is_available())
- log_string('train_error {:d} {:.02f}% {:d} {:d}'.format(
- problem_number,
- 100 * nb_train_errors / train_set.nb_samples,
- nb_train_errors,
- train_set.nb_samples)
- )
+ log_string('data_generation {:0.2f} samples / s'.format(test_set.nb_samples / (time.time() - t)))
- nb_test_errors = nb_errors(model, test_set)
+ nb_test_errors = nb_errors(model, test_set)
- log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
- problem_number,
- 100 * nb_test_errors / test_set.nb_samples,
- nb_test_errors,
- test_set.nb_samples)
- )
+ log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
+ problem_number,
+ 100 * nb_test_errors / test_set.nb_samples,
+ nb_test_errors,
+ test_set.nb_samples)
+ )
######################################################################