fix deprecation about dropout; fix Keras compatibility in tf1.13

examples/DoReFa-Net/svhn-digit-dorefa.py

@@ -100,7 +100,7 @@ class Model(ModelDesc):
                       .apply(fg)
                       .BatchNorm('bn5').apply(activate)
                       # 5
-                      .tf.nn.dropout(0.5 if is_training else 1.0)
+                      .Dropout(rate=0.5 if is_training else 0.0)
                       .Conv2D('conv6', 512, 5, padding='VALID')
                       .apply(fg).BatchNorm('bn6')
                       .apply(nonlin)

examples/basics/cifar-convnet.py

@@ -33,7 +33,7 @@ class Model(ModelDesc):
 
     def build_graph(self, image, label):
         is_training = get_current_tower_context().is_training
-        keep_prob = tf.constant(0.5 if is_training else 1.0)
+        drop_rate = tf.constant(0.5 if is_training else 0.0)
 
         if is_training:
             tf.summary.image("train_image", image, 10)
@@ -56,7 +56,7 @@ class Model(ModelDesc):
                 .Conv2D('conv3.1', filters=128, padding='VALID') \
                 .Conv2D('conv3.2', filters=128, padding='VALID') \
                 .FullyConnected('fc0', 1024 + 512, activation=tf.nn.relu) \
-                .tf.nn.dropout(keep_prob) \
+                .Dropout(rate=drop_rate) \
                 .FullyConnected('fc1', 512, activation=tf.nn.relu) \
                 .FullyConnected('linear', out_dim=self.cifar_classnum)()
 

examples/keras/imagenet-resnet-keras.py

@@ -147,8 +147,8 @@ if __name__ == '__main__':
 
     num_gpu = get_num_gpu()
     if args.fake:
-        df_train = FakeData([[64, 224, 224, 3], [64, 1000]], 5000, random=False, dtype='uint8')
-        df_val = FakeData([[64, 224, 224, 3], [64, 1000]], 5000, random=False)
+        df_train = FakeData([[32, 224, 224, 3], [32, 1000]], 5000, random=False, dtype='uint8')
+        df_val = FakeData([[32, 224, 224, 3], [32, 1000]], 5000, random=False)
     else:
         batch_size = TOTAL_BATCH_SIZE // num_gpu
         assert args.data is not None

tensorpack/contrib/keras.py

@@ -4,7 +4,9 @@
 import tensorflow as tf
 import six
 from tensorflow import keras
+import tensorflow.keras.backend as K
 from tensorflow.python.keras import metrics as metrics_module
+from contextlib import contextmanager
 
 from ..models.regularize import regularize_cost_from_collection
 from ..train import Trainer, SimpleTrainer, SyncMultiGPUTrainerParameterServer
@@ -82,7 +84,19 @@ class KerasModelCaller(object):
 
         if self.cached_model is None:
             assert not reuse
-            model = self.cached_model = self.get_model(*input_tensors)
+
+            # starting from some versions, tf.keras starts to prepend name scope to variable names ..
+            @contextmanager
+            def clear_tower0_name_scope():
+                ns = tf.get_default_graph().get_name_scope()
+                if ns == 'tower0':
+                    with tf.name_scope('/'):
+                        yield
+                else:
+                    yield
+
+            with clear_tower0_name_scope():
+                model = self.cached_model = self.get_model(*input_tensors)
             outputs = model.outputs
         elif reuse:
             # use the cached Keras model to mimic reuse
@@ -108,7 +122,7 @@ class KerasPhaseCallback(Callback):
     def __init__(self, isTrain):
         assert isinstance(isTrain, bool), isTrain
         self._isTrain = isTrain
-        self._learning_phase = keras.backend.learning_phase()
+        self._learning_phase = K.learning_phase()
 
     def _setup_graph(self):
         logger.info("Using Keras learning phase {} in the graph!".format(
@@ -200,7 +214,8 @@ def setup_keras_trainer(
         input,
         get_cost,
         lambda: optimizer)
-    if model_caller.cached_model.uses_learning_phase:
+    if len(K.learning_phase().consumers()) > 0:
+        # check if learning_phase is used in this model
         trainer.register_callback(KerasPhaseCallback(True))