#!/usr/bin/env python
-import argparse
+import argparse, math, sys
-import math, sys, torch, torchvision
+import torch, torchvision
from torch import nn
-from torch.nn import functional as F
######################################################################
######################################################################
+if torch.cuda.is_available():
+ device = torch.device('cuda')
+else:
+ device = torch.device('cpu')
+
+######################################################################
+
+def entropy(target):
+ probas = []
+ for k in range(target.max() + 1):
+ n = (target == k).sum().item()
+ if n > 0: probas.append(n)
+ probas = torch.tensor(probas).float()
+ probas /= probas.sum()
+ return - (probas * probas.log()).sum().item()
+
+######################################################################
+
args = parser.parse_args()
if args.seed >= 0:
torch.manual_seed(args.seed)
-used_MNIST_classes = torch.tensor(eval('[' + args.mnist_classes + ']'))
+used_MNIST_classes = torch.tensor(eval('[' + args.mnist_classes + ']'), device = device)
######################################################################
train_set = torchvision.datasets.MNIST('./data/mnist/', train = True, download = True)
-train_input = train_set.train_data.view(-1, 1, 28, 28).float()
-train_target = train_set.train_labels
+train_input = train_set.train_data.view(-1, 1, 28, 28).to(device).float()
+train_target = train_set.train_labels.to(device)
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
-
-if torch.cuda.is_available():
- used_MNIST_classes = used_MNIST_classes.cuda()
- train_input, train_target = train_input.cuda(), train_target.cuda()
- test_input, test_target = test_input.cuda(), test_target.cuda()
+test_input = test_set.test_data.view(-1, 1, 28, 28).to(device).float()
+test_target = test_set.test_labels.to(device)
mu, std = train_input.mean(), train_input.std()
train_input.sub_(mu).div_(std)
# Returns a triplet of tensors (a, b, c), where a and b contain each
# half of the samples, 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.
+# c is a 1d long tensor real classes
def create_image_pairs(train = False):
ua, ub = [], []
hs = x.size(0)//2
ua.append(x.narrow(0, 0, hs))
ub.append(x.narrow(0, hs, hs))
+ uc.append(target[used_indices])
a = torch.cat(ua, 0)
b = torch.cat(ub, 0)
+ c = torch.cat(uc, 0)
perm = torch.randperm(a.size(0))
a = a[perm].contiguous()
b = b[perm].contiguous()
- c = torch.tensor([x.size(0) for x in ua])
return a, b, c
######################################################################
+# Returns a triplet a, b, c where a are the standard MNIST images, c
+# the classes, and b is a Nx2 tensor, eith for every n:
+#
+# b[n, 0] ~ Uniform(0, 10)
+# b[n, 1] ~ b[n, 0] + Uniform(0, 0.5) + c[n]
+
def create_image_values_pairs(train = False):
ua, ub = [], []
target = target[used_indices].contiguous()
a = input
+ c = target
b = a.new(a.size(0), 2)
b[:, 0].uniform_(10)
b[:, 1].uniform_(0.5)
b[:, 1] += b[:, 0] + target.float()
- c = torch.tensor([(target == k).sum().item() for k in used_MNIST_classes])
-
return a, b, c
######################################################################
-class NetImagePair(nn.Module):
+class NetForImagePair(nn.Module):
def __init__(self):
- super(NetImagePair, self).__init__()
+ super(NetForImagePair, self).__init__()
self.features_a = nn.Sequential(
nn.Conv2d(1, 16, kernel_size = 5),
nn.MaxPool2d(3), nn.ReLU(),
######################################################################
-class NetImageValuesPair(nn.Module):
+class NetForImageValuesPair(nn.Module):
def __init__(self):
- super(NetImageValuesPair, self).__init__()
+ super(NetForImageValuesPair, self).__init__()
self.features_a = nn.Sequential(
nn.Conv2d(1, 16, kernel_size = 5),
nn.MaxPool2d(3), nn.ReLU(),
if args.data == 'image_pair':
create_pairs = create_image_pairs
- model = NetImagePair()
+ model = NetForImagePair()
elif args.data == 'image_values_pair':
create_pairs = create_image_values_pairs
- model = NetImageValuesPair()
+ model = NetForImageValuesPair()
else:
raise Exception('Unknown data ' + args.data)
optimizer = torch.optim.Adam(model.parameters(), lr = 1e-3)
-if torch.cuda.is_available():
- model.cuda()
+model.to(device)
for e in range(nb_epochs):
- input_a, input_b, count = create_pairs(train = True)
-
- # The information bound is the entropy of the class distribution
- class_proba = count.float()
- class_proba /= class_proba.sum()
- class_entropy = - (class_proba.log() * class_proba).sum().item()
+ input_a, input_b, classes = create_pairs(train = True)
input_br = input_b[torch.randperm(input_b.size(0))]
acc_mi /= (input_a.size(0) // batch_size)
- print('%d %.04f %.04f' % (e, acc_mi / math.log(2), class_entropy / math.log(2)))
+ print('%d %.04f %.04f' % (e, acc_mi / math.log(2), entropy(classes) / math.log(2)))
sys.stdout.flush()
######################################################################
-input_a, input_b, count = create_pairs(train = False)
+input_a, input_b, classes = create_pairs(train = False)
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))]
acc_mi = 0.0
acc_mi /= (input_a.size(0) // batch_size)
-print('test %.04f %.04f'%(acc_mi / math.log(2), class_entropy / math.log(2)))
+print('test %.04f %.04f'%(acc_mi / math.log(2), entropy(classes) / math.log(2)))
######################################################################
projects / pytorch.git / commitdiff