Added a logger with ETA for the sample generation.

diff --git a/cnn-svrt.py b/cnn-svrt.py
index 58035d2..26e7de8 100755 (executable)
--- a/cnn-svrt.py
+++ b/cnn-svrt.py
@@ -247,6 +247,21 @@ def int_to_suffix(n):
     else:
         return str(n)
 
     else:
         return str(n)
 

+class vignette_logger():
+    def __init__(self, delay_min = 60):
+        self.start_t = time.time()
+        self.delay_min = delay_min
+
+    def __call__(self, n, m):
+        t = time.time()
+        if t > self.start_t + self.delay_min:
+            dt = (t - self.start_t) / m
+            log_string('sample_generation {:d} / {:d}'.format(
+                m,
+                n), ' [ETA ' + time.ctime(time.time() + dt * (n - m)) + ']'
+            )
+            self.start_t = t
+

 ######################################################################
 
 if args.nb_train_samples%args.batch_size > 0 or args.nb_test_samples%args.batch_size > 0:
 ######################################################################
 
 if args.nb_train_samples%args.batch_size > 0 or args.nb_test_samples%args.batch_size > 0:


@@ -300,7 +315,8 @@ for problem_number in range(1, 24):
 
         train_set = VignetteSet(problem_number,
                                 args.nb_train_samples, args.batch_size,
 
         train_set = VignetteSet(problem_number,
                                 args.nb_train_samples, args.batch_size,

-                                cuda = torch.cuda.is_available())
+                                cuda = torch.cuda.is_available(),
+                                logger = vignette_logger())

 
         log_string('data_generation {:0.2f} samples / s'.format(
             train_set.nb_samples / (time.time() - t))
 
         log_string('data_generation {:0.2f} samples / s'.format(
             train_set.nb_samples / (time.time() - t))

diff --git a/svrtset.py b/svrtset.py
index cbc71a3..49f3279 100755 (executable)
--- a/svrtset.py
+++ b/svrtset.py
@@ -41,7 +41,7 @@ def generate_one_batch(s):
 
 class VignetteSet:
 
 
 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')
 
         if nb_samples%batch_size > 0:
             print('nb_samples must be a multiple of batch_size')


@@ -61,6 +61,7 @@ class VignetteSet:
         self.data = []
         for b in range(0, self.nb_batches):
             self.data.append(generate_one_batch(mp_args[b]))
         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
 
 
         # Weird thing going on with the multi-processing, waiting for more info
 


@@ -88,7 +89,7 @@ class VignetteSet:
 ######################################################################
 
 class CompressedVignetteSet:
 ######################################################################
 
 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')
 
         if nb_samples%batch_size > 0:
             print('nb_samples must be a multiple of batch_size')


@@ -111,6 +112,7 @@ class CompressedVignetteSet:
             acc_sq += input.float().pow(2).sum() /  input.numel()
             self.targets.append(target)
             self.input_storages.append(svrt.compress(input.storage()))
             acc_sq += input.float().pow(2).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)

 
         self.mean = acc / self.nb_batches
         self.std = sqrt(acc_sq / self.nb_batches - self.mean * self.mean)
 
         self.mean = acc / self.nb_batches
         self.std = sqrt(acc_sq / self.nb_batches - self.mean * self.mean)