X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?p=pysvrt.git;a=blobdiff_plain;f=svrtset.py;h=ecbaa68b992b81c20ba6a2874a4a74152e78566e;hp=cbc71a373237356007bca386de4890036ac902e5;hb=a500b3545f6eb25c480e945f2e12786933c92423;hpb=b6cc25f4622917b0025d613d617b5ce9e23f07e9

diff --git a/svrtset.py b/svrtset.py
index cbc71a3..ecbaa68 100755
--- a/svrtset.py
+++ b/svrtset.py
@@ -29,6 +29,9 @@ from torch.autograd import Variable
 
 import svrt
 
+# FIXME
+import resource
+
 ######################################################################
 
 def generate_one_batch(s):
@@ -41,17 +44,18 @@ def generate_one_batch(s):
 
 class VignetteSet:
 
-    def __init__(self, problem_number, nb_samples, batch_size, cuda = False):
+    def __init__(self, problem_number, nb_samples, batch_size, cuda = False, logger = None):
 
         if nb_samples%batch_size > 0:
             print('nb_samples must be a multiple of batch_size')
             raise
 
         self.cuda = cuda
-        self.batch_size = batch_size
         self.problem_number = problem_number
-        self.nb_batches = nb_samples // batch_size
-        self.nb_samples = self.nb_batches * self.batch_size
+
+        self.batch_size = batch_size
+        self.nb_samples = nb_samples
+        self.nb_batches = self.nb_samples // self.batch_size
 
         seeds = torch.LongTensor(self.nb_batches).random_()
         mp_args = []
@@ -61,6 +65,7 @@ class VignetteSet:
         self.data = []
         for b in range(0, self.nb_batches):
             self.data.append(generate_one_batch(mp_args[b]))
+            if logger is not None: logger(self.nb_batches * self.batch_size, b * self.batch_size)
 
         # Weird thing going on with the multi-processing, waiting for more info
 
@@ -88,17 +93,19 @@ class VignetteSet:
 ######################################################################
 
 class CompressedVignetteSet:
-    def __init__(self, problem_number, nb_samples, batch_size, cuda = False):
+    def __init__(self, problem_number, nb_samples, batch_size, cuda = False, logger = None):
 
         if nb_samples%batch_size > 0:
             print('nb_samples must be a multiple of batch_size')
             raise
 
         self.cuda = cuda
-        self.batch_size = batch_size
         self.problem_number = problem_number
-        self.nb_batches = nb_samples // batch_size
-        self.nb_samples = self.nb_batches * self.batch_size
+
+        self.batch_size = batch_size
+        self.nb_samples = nb_samples
+        self.nb_batches = self.nb_samples // self.batch_size
+
         self.targets = []
         self.input_storages = []
 
@@ -107,10 +114,16 @@ class CompressedVignetteSet:
         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()
+            acc += float(input.sum()) / input.numel()
+            acc_sq += float((input * input).sum()) /  input.numel()
             self.targets.append(target)
             self.input_storages.append(svrt.compress(input.storage()))
+            if logger is not None: logger(self.nb_batches * self.batch_size, b * self.batch_size)
+
+            # FIXME
+            if resource.getrusage(resource.RUSAGE_SELF).ru_maxrss > 16e6:
+                print('Memory leak?!')
+                raise
 
         self.mean = acc / self.nb_batches
         self.std = sqrt(acc_sq / self.nb_batches - self.mean * self.mean)