Merge pull request lisa-lab#172 from abergeron/mixed

Fixes for float16 problems in the DLT

Author: lamblin

code/DBN.py

@@ -340,7 +340,7 @@ def test_DBN(finetune_lr=0.1, pretraining_epochs=100,
                 c.append(pretraining_fns[i](index=batch_index,
                                             lr=pretrain_lr))
             print('Pre-training layer %i, epoch %d, cost ' % (i, epoch), end=' ')
-            print(numpy.mean(c))
+            print(numpy.mean(c, dtype='float64'))
 
     end_time = timeit.default_timer()
     # end-snippet-2
@@ -391,7 +391,7 @@ def test_DBN(finetune_lr=0.1, pretraining_epochs=100,
             if (iter + 1) % validation_frequency == 0:
 
                 validation_losses = validate_model()
-                this_validation_loss = numpy.mean(validation_losses)
+                this_validation_loss = numpy.mean(validation_losses, dtype='float64')
                 print('epoch %i, minibatch %i/%i, validation error %f %%' % (
                     epoch,
                     minibatch_index + 1,
@@ -414,7 +414,7 @@ def test_DBN(finetune_lr=0.1, pretraining_epochs=100,
 
                     # test it on the test set
                     test_losses = test_model()
-                    test_score = numpy.mean(test_losses)
+                    test_score = numpy.mean(test_losses, dtype='float64')
                     print(('     epoch %i, minibatch %i/%i, test error of '
                            'best model %f %%') %
                           (epoch, minibatch_index + 1, n_train_batches,

code/SdA.py

@@ -40,7 +40,7 @@
 
 import theano
 import theano.tensor as T
-from theano.tensor.shared_randomstreams import RandomStreams
+from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
 
 from logistic_sgd import LogisticRegression, load_data
 from mlp import HiddenLayer
@@ -394,7 +394,7 @@ def test_SdA(finetune_lr=0.1, pretraining_epochs=15,
                 c.append(pretraining_fns[i](index=batch_index,
                          corruption=corruption_levels[i],
                          lr=pretrain_lr))
-            print('Pre-training layer %i, epoch %d, cost %f' % (i, epoch, numpy.mean(c)))
+            print('Pre-training layer %i, epoch %d, cost %f' % (i, epoch, numpy.mean(c, dtype='float64')))
 
     end_time = timeit.default_timer()
 
@@ -442,7 +442,7 @@ def test_SdA(finetune_lr=0.1, pretraining_epochs=15,
 
             if (iter + 1) % validation_frequency == 0:
                 validation_losses = validate_model()
-                this_validation_loss = numpy.mean(validation_losses)
+                this_validation_loss = numpy.mean(validation_losses, dtype='float64')
                 print('epoch %i, minibatch %i/%i, validation error %f %%' %
                       (epoch, minibatch_index + 1, n_train_batches,
                        this_validation_loss * 100.))
@@ -463,7 +463,7 @@ def test_SdA(finetune_lr=0.1, pretraining_epochs=15,
 
                     # test it on the test set
                     test_losses = test_model()
-                    test_score = numpy.mean(test_losses)
+                    test_score = numpy.mean(test_losses, dtype='float64')
                     print(('     epoch %i, minibatch %i/%i, test error of '
                            'best model %f %%') %
                           (epoch, minibatch_index + 1, n_train_batches,

code/dA.py

@@ -40,7 +40,7 @@
 
 import theano
 import theano.tensor as T
-from theano.tensor.shared_randomstreams import RandomStreams
+from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
 
 from logistic_sgd import load_data
 from utils import tile_raster_images
@@ -336,7 +336,7 @@ def test_dA(learning_rate=0.1, training_epochs=15,
         for batch_index in range(n_train_batches):
             c.append(train_da(batch_index))
 
-        print('Training epoch %d, cost ' % epoch, numpy.mean(c))
+        print('Training epoch %d, cost ' % epoch, numpy.mean(c, dtype='float64'))
 
     end_time = timeit.default_timer()
 
@@ -394,7 +394,7 @@ def test_dA(learning_rate=0.1, training_epochs=15,
         for batch_index in range(n_train_batches):
             c.append(train_da(batch_index))
 
-        print('Training epoch %d, cost ' % epoch, numpy.mean(c))
+        print('Training epoch %d, cost ' % epoch, numpy.mean(c, dtype='float64'))
 
     end_time = timeit.default_timer()
 

code/hmc/hmc.py

@@ -7,6 +7,7 @@
 from theano import function, shared
 from theano import tensor as TT
 import theano
+import theano.sandbox.rng_mrg
 
 sharedX = (lambda X, name:
            shared(numpy.asarray(X, dtype=theano.config.floatX), name=name))
@@ -275,14 +276,14 @@ def hmc_updates(positions, stepsize, avg_acceptance_rate, final_pos, accept,
 
     """
 
-    ## POSITION UPDATES ##
+    # POSITION UPDATES #
     # broadcast `accept` scalar to tensor with the same dimensions as
     # final_pos.
     accept_matrix = accept.dimshuffle(0, *(('x',) * (final_pos.ndim - 1)))
     # if accept is True, update to `final_pos` else stay put
     new_positions = TT.switch(accept_matrix, final_pos, positions)
     # end-snippet-5 start-snippet-7
-    ## STEPSIZE UPDATES ##
+    # STEPSIZE UPDATES #
     # if acceptance rate is too low, our sampler is too "noisy" and we reduce
     # the stepsize. If it is too high, our sampler is too conservative, we can
     # get away with a larger stepsize (resulting in better mixing).
@@ -292,7 +293,7 @@ def hmc_updates(positions, stepsize, avg_acceptance_rate, final_pos, accept,
     new_stepsize = TT.clip(_new_stepsize, stepsize_min, stepsize_max)
 
     # end-snippet-7 start-snippet-6
-    ## ACCEPT RATE UPDATES ##
+    # ACCEPT RATE UPDATES #
     # perform exponential moving average
     mean_dtype = theano.scalar.upcast(accept.dtype, avg_acceptance_rate.dtype)
     new_acceptance_rate = TT.add(
@@ -358,7 +359,7 @@ def new_from_shared_positions(
         stepsize = sharedX(initial_stepsize, 'hmc_stepsize')
         avg_acceptance_rate = sharedX(target_acceptance_rate,
                                       'avg_acceptance_rate')
-        s_rng = TT.shared_randomstreams.RandomStreams(seed)
+        s_rng = theano.sandbox.rng_mrg.MRG_RandomStreams(seed)
 
         # define graph for an `n_steps` HMC simulation
         accept, final_pos = hmc_move(

code/lstm.py

@@ -605,8 +605,8 @@ def train_lstm(
                         best_p = unzip(tparams)
                         bad_counter = 0
 
-                    print( ('Train ', train_err, 'Valid ', valid_err,
-                           'Test ', test_err) )
+                    print('Train ', train_err, 'Valid ', valid_err,
+                           'Test ', test_err)
 
                     if (len(history_errs) > patience and
                         valid_err >= numpy.array(history_errs)[:-patience,

code/rbm.py

@@ -20,7 +20,7 @@
 import theano.tensor as T
 import os
 
-from theano.tensor.shared_randomstreams import RandomStreams
+from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
 
 from utils import tile_raster_images
 from logistic_sgd import load_data

code/rnnrbm.py

@@ -19,7 +19,7 @@
 from midi.utils import midiread, midiwrite
 import theano
 import theano.tensor as T
-from theano.tensor.shared_randomstreams import RandomStreams
+from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
 
 #Don't use a python long as this don't work on 32 bits computers.
 numpy.random.seed(0xbeef)