Kaggle-Otto train/stats modes a bit more obvious.

Just like in MNIST.

Author: lucasb-eyer

examples/Kaggle-Otto/run.py

@@ -59,8 +59,8 @@ def nnet():
         model.training()
         if epoch % 100 == 0:
             optimiser.hyperparams['lr'] /= 10
-        train(train_data_x, train_data_y, model, optimiser, criterion, epoch, 100)
-        train(train_data_x, train_data_y, model, optimiser, criterion, epoch, 100, 'stat')
+        train(train_data_x, train_data_y, model, optimiser, criterion, epoch, 100, 'train')
+        train(train_data_x, train_data_y, model, optimiser, criterion, epoch, 100, 'stats')
 
         model.evaluate()
         validate(test_data_x, test_data_y, model, epoch, 100)

examples/Kaggle-Otto/train.py

@@ -3,8 +3,9 @@
 
 from examples.utils import make_progressbar
 
-def train(dataset_x, dataset_y, model, optimiser, criterion, epoch, batch_size, mode=None):
-    progress = make_progressbar('Training epoch #{}'.format(epoch), len(dataset_x))
+
+def train(dataset_x, dataset_y, model, optimiser, criterion, epoch, batch_size, mode='train'):
+    progress = make_progressbar('Training ({}) epoch #{}'.format(mode, epoch), len(dataset_x))
     progress.start()
 
     shuffle = np.random.permutation(len(dataset_x))
@@ -17,12 +18,14 @@ def train(dataset_x, dataset_y, model, optimiser, criterion, epoch, batch_size,
             mini_batch_input[k] = dataset_x[shuffle[j * batch_size + k]]
             mini_batch_targets[k] = dataset_y[shuffle[j * batch_size + k]]
 
-        if mode is None:
+        if mode == 'train':
             model.zero_grad_parameters()
             model.accumulate_gradients(mini_batch_input, mini_batch_targets, criterion)
             optimiser.update_parameters(model)
-        else:
+        elif mode == 'stats':
             model.accumulate_statistics(mini_batch_input)
+        else:
+            assert False, "Mode should be either 'train' or 'stats'"
 
         progress.update((j+1) * batch_size)