import time
import argparse
+import math
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
######################################################################
type = str, default = 'cnn-svrt.log',
help = 'Log file name')
+parser.add_argument('--compress_vignettes',
+ 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)
######################################################################
-def generate_set(p, n):
- target = torch.LongTensor(n).bernoulli_(0.5)
- t = time.time()
- input = svrt.generate_vignettes(p, target)
- t = time.time() - t
- log_string('data_set_generation {:.02f} sample/s'.format(n / t))
- input = input.view(input.size(0), 1, input.size(1), input.size(2)).float()
- return Variable(input), Variable(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_input, train_target):
- bs = args.batch_size
+######################################################################
+
+def train_model(model, train_set):
+ batch_size = args.batch_size
criterion = nn.CrossEntropyLoss()
if torch.cuda.is_available():
optimizer = optim.SGD(model.parameters(), lr = 1e-2)
- for k in range(0, args.nb_epochs):
+ start_t = time.time()
+
+ for e in range(0, args.nb_epochs):
acc_loss = 0.0
- for b in range(0, train_input.size(0), bs):
- output = model.forward(train_input.narrow(0, b, bs))
- loss = criterion(output, train_target.narrow(0, b, bs))
+ for b in range(0, train_set.nb_batches):
+ input, target = train_set.get_batch(b)
+ output = model.forward(Variable(input))
+ loss = criterion(output, Variable(target))
acc_loss = acc_loss + loss.data[0]
model.zero_grad()
loss.backward()
optimizer.step()
- log_string('train_loss {:d} {:f}'.format(k, acc_loss))
+ log_string('train_loss {:d} {:f}'.format(e + 1, acc_loss))
+ dt = (time.time() - t) / (e + 1)
+ print(Fore.CYAN + 'ETA ' + time.ctime(time.time() + dt * (args.nb_epochs - e)) + Style.RESET_ALL)
return model
######################################################################
-def nb_errors(model, data_input, data_target):
- bs = args.batch_size
-
+def nb_errors(model, data_set):
ne = 0
- for b in range(0, data_input.size(0), bs):
- output = model.forward(data_input.narrow(0, b, bs))
+ for b in range(0, data_set.nb_batches):
+ input, target = data_set.get_batch(b)
+ output = model.forward(Variable(input))
wta_prediction = output.data.max(1)[1].view(-1)
- for i in range(0, bs):
- if wta_prediction[i] != data_target.narrow(0, b, bs).data[i]:
+ for i in range(0, data_set.batch_size):
+ if wta_prediction[i] != target[i]:
ne = ne + 1
return ne
for arg in vars(args):
log_string('argument ' + str(arg) + ' ' + str(getattr(args, arg)))
+######################################################################
+
for problem_number in range(1, 24):
- train_input, train_target = generate_set(problem_number,
- args.nb_train_batches * args.batch_size)
- test_input, test_target = generate_set(problem_number,
- args.nb_test_batches * args.batch_size)
+
+ log_string('**** problem ' + str(problem_number) + ' ****')
+
model = AfrozeShallowNet()
if torch.cuda.is_available():
- train_input, train_target = train_input.cuda(), train_target.cuda()
- test_input, test_target = test_input.cuda(), test_target.cuda()
model.cuda()
- mu, std = train_input.data.mean(), train_input.data.std()
- train_input.data.sub_(mu).div_(std)
- test_input.data.sub_(mu).div_(std)
+ 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')
- train_model(model, train_input, train_target)
+ 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_input, train_target)
+ 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_input.size(0),
- nb_train_errors,
- train_input.size(0))
- )
+ log_string('data_generation {:0.2f} samples / s'.format(test_set.nb_samples / (time.time() - t)))
- nb_test_errors = nb_errors(model, test_input, test_target)
+ nb_test_errors = nb_errors(model, test_set)
- log_string('test_error {:d} {:.02f}% {:d} {:d}'.format(
- problem_number,
- 100 * nb_test_errors / test_input.size(0),
- nb_test_errors,
- test_input.size(0))
- )
+ 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)
+ )
######################################################################