Update.

[pytorch.git] / mine_mnist.py

diff --git a/mine_mnist.py b/mine_mnist.py
index c6dc287..6f65136 100755 (executable)
--- a/mine_mnist.py
+++ b/mine_mnist.py
@@ -12,27 +12,30 @@ from torch.nn import functional as F
 
 ######################################################################
 
-# 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.
+# Returns a pair of tensors (a, b, c), where a and b are tensors
+# containing 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.
 
 def create_pair_set(used_classes, input, target):
-    u = []
+    ua, ub = [], []
 
     for i in used_classes:
         used_indices = torch.arange(input.size(0), device = target.device)\
                             .masked_select(target == i.item())
         x = input[used_indices]
         x = x[torch.randperm(x.size(0))]
-        # Careful with odd numbers of samples in a class
-        x = x[0:2 * (x.size(0) // 2)].reshape(-1, 2, 28, 28)
-        u.append(x)
+        ua.append(x.narrow(0, 0, x.size(0)//2))
+        ub.append(x.narrow(0, x.size(0)//2, x.size(0)//2))
 
-    x = torch.cat(u, 0)
-    x = x[torch.randperm(x.size(0))]
-    c = torch.tensor([x.size(0) for x in u])
+    a = torch.cat(ua, 0)
+    b = torch.cat(ub, 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 x.narrow(1, 0, 1).contiguous(), x.narrow(1, 1, 1).contiguous(), c
+    return a, b, c
 
 ######################################################################
 
@@ -94,20 +97,21 @@ for e in range(nb_epochs):
 
     input_br = input_b[torch.randperm(input_b.size(0))]
 
-    mi = 0.0
+    acc_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 = model(batch_a, batch_b).mean() - model(batch_a, batch_br).exp().mean().log()
+        loss = - mi
+        acc_mi += mi.item()
         optimizer.zero_grad()
         loss.backward()
         optimizer.step()
 
-    mi /= (input_a.size(0) // batch_size)
+    acc_mi /= (input_a.size(0) // batch_size)
 
-    print('%d %.04f %.04f'%(e, mi / math.log(2), class_entropy / math.log(2)))
+    print('%d %.04f %.04f'%(e, acc_mi / math.log(2), class_entropy / math.log(2)))
 
     sys.stdout.flush()
 
@@ -122,16 +126,16 @@ for e in range(nb_epochs):
 
     input_br = input_b[torch.randperm(input_b.size(0))]
 
-    mi = 0.0
+    acc_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()
+        acc_mi -= loss.item()
 
-    mi /= (input_a.size(0) // batch_size)
+    acc_mi /= (input_a.size(0) // batch_size)
 
-print('test %.04f %.04f'%(mi / math.log(2), class_entropy / math.log(2)))
+print('test %.04f %.04f'%(acc_mi / math.log(2), class_entropy / math.log(2)))
 
 ######################################################################