From: Francois Fleuret Date: Thu, 15 Nov 2018 10:09:50 +0000 (+0100) Subject: Update. X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=commitdiff_plain;h=663ddb29ecd584102f5a19eefc686b7d5ed77d3e;p=pytorch.git Update. --- diff --git a/mine_mnist.py b/mine_mnist.py index f573b89..c6dc287 100755 --- a/mine_mnist.py +++ b/mine_mnist.py @@ -3,7 +3,7 @@ # @XREMOTE_HOST: elk.fleuret.org # @XREMOTE_EXEC: ~/conda/bin/python # @XREMOTE_PRE: ln -s ~/data/pytorch ./data -# @XREMOTE_PRE: killall -q -9 python || echo "Nothing killed" +# @XREMOTE_PRE: killall -q -9 python || true import math, sys, torch, torchvision @@ -12,9 +12,9 @@ from torch.nn import functional as F ###################################################################### -# Returns a pair of tensors (x, c), where x is a Nx2x28x28 containing -# pairs of images of same classes (one per channel), and p is a 1d -# long tensor with the count of pairs per class used +# Returns a pair of tensors (a, b, c), where a and b are Nx1x28x28 +# tensors containing images, with a[i] and b[i] of same class for any +# i, and c is a 1d long tensor with the count of pairs per class used. def create_pair_set(used_classes, input, target): u = [] @@ -28,10 +28,11 @@ def create_pair_set(used_classes, input, target): x = x[0:2 * (x.size(0) // 2)].reshape(-1, 2, 28, 28) u.append(x) - x = torch.cat(u, 0).contiguous() + x = torch.cat(u, 0) + x = x[torch.randperm(x.size(0))] c = torch.tensor([x.size(0) for x in u]) - return x, c + return x.narrow(1, 0, 1).contiguous(), x.narrow(1, 1, 1).contiguous(), c ###################################################################### @@ -43,7 +44,8 @@ class Net(nn.Module): self.fc1 = nn.Linear(256, 200) self.fc2 = nn.Linear(200, 1) - def forward(self, x): + def forward(self, a, b): + x = torch.cat((a, b), 1) x = F.relu(F.max_pool2d(self.conv1(x), kernel_size = 3)) x = F.relu(F.max_pool2d(self.conv2(x), kernel_size = 2)) x = x.view(x.size(0), -1) @@ -57,8 +59,13 @@ train_set = torchvision.datasets.MNIST('./data/mnist/', train = True, download = train_input = train_set.train_data.view(-1, 1, 28, 28).float() train_target = train_set.train_labels +test_set = torchvision.datasets.MNIST('./data/mnist/', train = False, download = True) +test_input = test_set.test_data.view(-1, 1, 28, 28).float() +test_target = test_set.test_labels + mu, std = train_input.mean(), train_input.std() train_input.sub_(mu).div_(std) +test_input.sub_(mu).div_(std) ###################################################################### @@ -75,31 +82,56 @@ optimizer = torch.optim.Adam(model.parameters(), lr = 1e-3) if torch.cuda.is_available(): model.cuda() train_input, train_target = train_input.cuda(), train_target.cuda() + test_input, test_target = test_input.cuda(), test_target.cuda() for e in range(nb_epochs): - input, count = create_pair_set(used_classes, train_input, train_target) + + input_a, input_b, count = create_pair_set(used_classes, train_input, train_target) class_proba = count.float() class_proba /= class_proba.sum() class_entropy = - (class_proba.log() * class_proba).sum().item() - input = input[torch.randperm(input.size(0))] - indep_input = input.clone() - indep_input[:, 1] = input[torch.randperm(input.size(0)), 1] + input_br = input_b[torch.randperm(input_b.size(0))] mi = 0.0 - for batch, indep_batch in zip(input.split(batch_size), indep_input.split(batch_size)): - loss = - (model(batch).mean() - model(indep_batch).exp().mean().log()) + for batch_a, batch_b, batch_br in zip(input_a.split(batch_size), + input_b.split(batch_size), + input_br.split(batch_size)): + loss = - (model(batch_a, batch_b).mean() - model(batch_a, batch_br).exp().mean().log()) mi -= loss.item() optimizer.zero_grad() loss.backward() optimizer.step() - mi /= (input.size(0) // batch_size) + mi /= (input_a.size(0) // batch_size) print('%d %.04f %.04f'%(e, mi / math.log(2), class_entropy / math.log(2))) sys.stdout.flush() ###################################################################### + +input_a, input_b, count = create_pair_set(used_classes, test_input, test_target) + +for e in range(nb_epochs): + class_proba = count.float() + class_proba /= class_proba.sum() + class_entropy = - (class_proba.log() * class_proba).sum().item() + + input_br = input_b[torch.randperm(input_b.size(0))] + + mi = 0.0 + + for batch_a, batch_b, batch_br in zip(input_a.split(batch_size), + input_b.split(batch_size), + input_br.split(batch_size)): + loss = - (model(batch_a, batch_b).mean() - model(batch_a, batch_br).exp().mean().log()) + mi -= loss.item() + + mi /= (input_a.size(0) // batch_size) + +print('test %.04f %.04f'%(mi / math.log(2), class_entropy / math.log(2))) + +######################################################################