Enhance layer_function_generator

* Generated functions can take `*args` as inputs.

python/paddle/v2/fluid/layers/layer_function_generator.py

@@ -155,7 +155,7 @@ def generate_layer_fn(op_type):
 
         return dtype
 
-    def func(**kwargs):
+    def func(*args, **kwargs):
         helper = LayerHelper(op_type, **kwargs)
 
         dtype = infer_and_check_dtype(op_proto, **kwargs)
@@ -166,6 +166,9 @@ def generate_layer_fn(op_type):
             val = kwargs.pop(name, [])
             if not isinstance(val, list) and not isinstance(val, tuple):
                 val = [val]
+            if len(val) == 0 and len(args) != 0:
+                val = args[0]
+                args = args[1:]
             inputs[ipt.name] = val
 
         outputs = dict()

python/paddle/v2/fluid/layers/tensor.py

@@ -160,8 +160,8 @@ def sums(input, out=None):
           a0 = layers.array_read(array=tmp, i=i)
           i = layers.increment(x=i)
           a1 = layers.array_read(array=tmp, i=i)
-          mean_a0 = layers.mean(x=a0)
-          mean_a1 = layers.mean(x=a1)
+          mean_a0 = layers.mean(a0)
+          mean_a1 = layers.mean(a1)
           a_sum = layers.sums(input=[mean_a0, mean_a1])
     """
     helper = LayerHelper('sum', **locals())

python/paddle/v2/fluid/tests/book/notest_rnn_encoder_decoer.py

@@ -147,7 +147,7 @@ def seq_to_seq_net():
     label = fluid.layers.data(
         name='label_sequence', shape=[1], dtype='int64', lod_level=1)
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
-    avg_cost = fluid.layers.mean(x=cost)
+    avg_cost = fluid.layers.mean(cost)
 
     return avg_cost, prediction
 

python/paddle/v2/fluid/tests/book/test_fit_a_line.py

@@ -29,7 +29,7 @@ def train(use_cuda, save_dirname):
     y = fluid.layers.data(name='y', shape=[1], dtype='float32')
 
     cost = fluid.layers.square_error_cost(input=y_predict, label=y)
-    avg_cost = fluid.layers.mean(x=cost)
+    avg_cost = fluid.layers.mean(cost)
 
     sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.001)
     sgd_optimizer.minimize(avg_cost)

python/paddle/v2/fluid/tests/book/test_image_classification.py

@@ -110,7 +110,7 @@ def train(net_type, use_cuda, save_dirname):
 
     predict = fluid.layers.fc(input=net, size=classdim, act='softmax')
     cost = fluid.layers.cross_entropy(input=predict, label=label)
-    avg_cost = fluid.layers.mean(x=cost)
+    avg_cost = fluid.layers.mean(cost)
     acc = fluid.layers.accuracy(input=predict, label=label)
 
     # Test program 

python/paddle/v2/fluid/tests/book/test_label_semantic_roles.py

@@ -164,7 +164,7 @@ def train(use_cuda, save_dirname=None):
         label=target,
         param_attr=fluid.ParamAttr(
             name='crfw', learning_rate=mix_hidden_lr))
-    avg_cost = fluid.layers.mean(x=crf_cost)
+    avg_cost = fluid.layers.mean(crf_cost)
 
     # TODO(qiao)
     # check other optimizers and check why out will be NAN

python/paddle/v2/fluid/tests/book/test_machine_translation.py

@@ -178,7 +178,7 @@ def train_main(use_cuda, is_sparse):
     label = pd.data(
         name="target_language_next_word", shape=[1], dtype='int64', lod_level=1)
     cost = pd.cross_entropy(input=rnn_out, label=label)
-    avg_cost = pd.mean(x=cost)
+    avg_cost = pd.mean(cost)
 
     optimizer = fluid.optimizer.Adagrad(learning_rate=1e-4)
     optimizer.minimize(avg_cost)

python/paddle/v2/fluid/tests/book/test_recognize_digits.py

@@ -48,7 +48,7 @@ BATCH_SIZE = 64
 def loss_net(hidden, label):
     prediction = fluid.layers.fc(input=hidden, size=10, act='softmax')
     loss = fluid.layers.cross_entropy(input=prediction, label=label)
-    avg_loss = fluid.layers.mean(x=loss)
+    avg_loss = fluid.layers.mean(loss)
     acc = fluid.layers.accuracy(input=prediction, label=label)
     return prediction, avg_loss, acc
 
@@ -101,8 +101,8 @@ def train(nn_type, use_cuda, parallel, save_dirname, save_param_filename):
 
         avg_loss, acc = pd()
         # get mean loss and acc through every devices.
-        avg_loss = fluid.layers.mean(x=avg_loss)
-        acc = fluid.layers.mean(x=acc)
+        avg_loss = fluid.layers.mean(avg_loss)
+        acc = fluid.layers.mean(acc)
     else:
         prediction, avg_loss, acc = net_conf(img, label)
 

python/paddle/v2/fluid/tests/book/test_recommender_system.py

@@ -147,7 +147,7 @@ def model():
 
     label = layers.data(name='score', shape=[1], dtype='float32')
     square_cost = layers.square_error_cost(input=scale_infer, label=label)
-    avg_cost = layers.mean(x=square_cost)
+    avg_cost = layers.mean(square_cost)
 
     return scale_infer, avg_cost
 

python/paddle/v2/fluid/tests/book/test_understand_sentiment.py

@@ -42,7 +42,7 @@ def convolution_net(data, label, input_dim, class_dim=2, emb_dim=32,
                                  size=class_dim,
                                  act="softmax")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
-    avg_cost = fluid.layers.mean(x=cost)
+    avg_cost = fluid.layers.mean(cost)
     accuracy = fluid.layers.accuracy(input=prediction, label=label)
     return avg_cost, accuracy, prediction
 
@@ -82,7 +82,7 @@ def dyn_rnn_lstm(data, label, input_dim, class_dim=2, emb_dim=32,
     last = fluid.layers.sequence_last_step(rnn())
     prediction = fluid.layers.fc(input=last, size=class_dim, act="softmax")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
-    avg_cost = fluid.layers.mean(x=cost)
+    avg_cost = fluid.layers.mean(cost)
     accuracy = fluid.layers.accuracy(input=prediction, label=label)
     return avg_cost, accuracy, prediction
 
@@ -119,7 +119,7 @@ def stacked_lstm_net(data,
                                  size=class_dim,
                                  act='softmax')
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
-    avg_cost = fluid.layers.mean(x=cost)
+    avg_cost = fluid.layers.mean(cost)
     accuracy = fluid.layers.accuracy(input=prediction, label=label)
     return avg_cost, accuracy, prediction
 
@@ -158,8 +158,8 @@ def train(word_dict, net_method, use_cuda, parallel=False, save_dirname=None):
             pd.write_output(acc)
 
         cost, acc = pd()
-        cost = fluid.layers.mean(x=cost)
-        acc_out = fluid.layers.mean(x=acc)
+        cost = fluid.layers.mean(cost)
+        acc_out = fluid.layers.mean(acc)
         prediction = None
         assert save_dirname is None
 

python/paddle/v2/fluid/tests/book/test_word2vec.py

@@ -118,7 +118,7 @@ def train(use_cuda, is_sparse, parallel, save_dirname):
                                        size=dict_size,
                                        act='softmax')
         cost = fluid.layers.cross_entropy(input=predict_word, label=words[4])
-        avg_cost = fluid.layers.mean(x=cost)
+        avg_cost = fluid.layers.mean(cost)
         return avg_cost, predict_word
 
     word_dict = paddle.dataset.imikolov.build_dict()
@@ -143,7 +143,7 @@ def train(use_cuda, is_sparse, parallel, save_dirname):
                 ]))
             pd.write_output(avg_cost)
 
-        avg_cost = fluid.layers.mean(x=pd())
+        avg_cost = fluid.layers.mean(pd())
 
     sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.001)
     sgd_optimizer.minimize(avg_cost)

python/paddle/v2/fluid/tests/book_distribute/notest_dist_fit_a_line.py

@@ -24,7 +24,7 @@ y_predict = fluid.layers.fc(input=x, size=1, act=None)
 y = fluid.layers.data(name='y', shape=[1], dtype='float32')
 
 cost = fluid.layers.square_error_cost(input=y_predict, label=y)
-avg_cost = fluid.layers.mean(x=cost)
+avg_cost = fluid.layers.mean(cost)
 
 sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.001)
 optimize_ops, params_grads = sgd_optimizer.minimize(avg_cost)

python/paddle/v2/fluid/tests/book_distribute/notest_dist_image_classification.py

@@ -114,7 +114,7 @@ else:
 
 predict = fluid.layers.fc(input=net, size=classdim, act='softmax')
 cost = fluid.layers.cross_entropy(input=predict, label=label)
-avg_cost = fluid.layers.mean(x=cost)
+avg_cost = fluid.layers.mean(cost)
 
 optimizer = fluid.optimizer.Adam(learning_rate=0.001)
 optimize_ops, params_grads = optimizer.minimize(avg_cost)

python/paddle/v2/fluid/tests/book_distribute/notest_dist_label_semantic_roles.py

@@ -154,7 +154,7 @@ def main():
         label=target,
         param_attr=fluid.ParamAttr(
             name='crfw', learning_rate=mix_hidden_lr))
-    avg_cost = fluid.layers.mean(x=crf_cost)
+    avg_cost = fluid.layers.mean(crf_cost)
 
     # TODO(qiao)
     # check other optimizers and check why out will be NAN

python/paddle/v2/fluid/tests/book_distribute/notest_dist_word2vec.py

@@ -65,7 +65,7 @@ concat_embed = fluid.layers.concat(
 hidden1 = fluid.layers.fc(input=concat_embed, size=HIDDEN_SIZE, act='sigmoid')
 predict_word = fluid.layers.fc(input=hidden1, size=dict_size, act='softmax')
 cost = fluid.layers.cross_entropy(input=predict_word, label=next_word)
-avg_cost = fluid.layers.mean(x=cost)
+avg_cost = fluid.layers.mean(cost)
 sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.001)
 optimize_ops, params_grads = sgd_optimizer.minimize(avg_cost)
 train_reader = paddle.batch(

python/paddle/v2/fluid/tests/book_distribute/notest_machine_translation.py

@@ -94,7 +94,7 @@ def main():
     label = layers.data(
         name="target_language_next_word", shape=[1], dtype='int64', lod_level=1)
     cost = layers.cross_entropy(input=rnn_out, label=label)
-    avg_cost = fluid.layers.mean(x=cost)
+    avg_cost = fluid.layers.mean(cost)
 
     optimizer = fluid.optimizer.Adagrad(learning_rate=1e-4)
     optimize_ops, params_grads = optimizer.minimize(avg_cost)

python/paddle/v2/fluid/tests/book_distribute/notest_recognize_digits_conv_dist.py

@@ -37,7 +37,7 @@ conv_pool_2 = fluid.nets.simple_img_conv_pool(
 
 predict = fluid.layers.fc(input=conv_pool_2, size=10, act="softmax")
 cost = fluid.layers.cross_entropy(input=predict, label=label)
-avg_cost = fluid.layers.mean(x=cost)
+avg_cost = fluid.layers.mean(cost)
 optimizer = fluid.optimizer.Adam(learning_rate=0.01)
 optimize_ops, params_grads = optimizer.minimize(avg_cost)
 

python/paddle/v2/fluid/tests/book_distribute/notest_recognize_digits_mlp_dist.py

@@ -32,7 +32,7 @@ predict = fluid.layers.fc(input=hidden2, size=10, act='softmax')
 label = fluid.layers.data(name='y', shape=[1], dtype='int64')
 
 cost = fluid.layers.cross_entropy(input=predict, label=label)
-avg_cost = fluid.layers.mean(x=cost)
+avg_cost = fluid.layers.mean(cost)
 
 optimizer = fluid.optimizer.Momentum(learning_rate=0.001, momentum=0.9)
 optimize_ops, params_grads = optimizer.minimize(avg_cost)

python/paddle/v2/fluid/tests/book_distribute/notest_recommender_system_dist.py

@@ -117,7 +117,7 @@ def model():
 
     label = layers.data(name='score', shape=[1], dtype='float32')
     square_cost = layers.square_error_cost(input=scale_infer, label=label)
-    avg_cost = layers.mean(x=square_cost)
+    avg_cost = layers.mean(square_cost)
 
     return avg_cost
 

python/paddle/v2/fluid/tests/book_distribute/notest_understand_sentiment_conv_dist.py

@@ -38,7 +38,7 @@ def convolution_net(data, label, input_dim, class_dim=2, emb_dim=32,
                                  size=class_dim,
                                  act="softmax")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
-    avg_cost = fluid.layers.mean(x=cost)
+    avg_cost = fluid.layers.mean(cost)
     adam_optimizer = fluid.optimizer.Adam(learning_rate=0.002)
     optimize_ops, params_grads = adam_optimizer.minimize(avg_cost)
     accuracy = fluid.evaluator.Accuracy(input=prediction, label=label)

python/paddle/v2/fluid/tests/book_distribute/notest_understand_sentiment_dynamic_lstm.py

@@ -49,7 +49,7 @@ def stacked_lstm_net(data,
                                  size=class_dim,
                                  act='softmax')
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
-    avg_cost = fluid.layers.mean(x=cost)
+    avg_cost = fluid.layers.mean(cost)
     adam_optimizer = fluid.optimizer.Adam(learning_rate=0.002)
     optimize_ops, params_grads = adam_optimizer.minimize(avg_cost)
     accuracy = fluid.evaluator.Accuracy(input=prediction, label=label)

python/paddle/v2/fluid/tests/book_memory_optimization/test_memopt_fit_a_line.py

@@ -30,7 +30,7 @@ y_predict = fluid.layers.fc(input=x, size=1, act=None)
 y = fluid.layers.data(name='y', shape=[1], dtype='float32')
 
 cost = fluid.layers.square_error_cost(input=y_predict, label=y)
-avg_cost = fluid.layers.mean(x=cost)
+avg_cost = fluid.layers.mean(cost)
 
 sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.1)
 sgd_optimizer.minimize(avg_cost)

python/paddle/v2/fluid/tests/book_memory_optimization/test_memopt_image_classification_train.py

@@ -117,7 +117,7 @@ else:
 
 predict = fluid.layers.fc(input=net, size=classdim, act='softmax')
 cost = fluid.layers.cross_entropy(input=predict, label=label)
-avg_cost = fluid.layers.mean(x=cost)
+avg_cost = fluid.layers.mean(cost)
 
 optimizer = fluid.optimizer.Adam(learning_rate=0.001)
 opts = optimizer.minimize(avg_cost)

python/paddle/v2/fluid/tests/book_memory_optimization/test_memopt_machine_translation.py

@@ -100,7 +100,7 @@ def main():
     label = layers.data(
         name="target_language_next_word", shape=[1], dtype='int64', lod_level=1)
     cost = layers.cross_entropy(input=rnn_out, label=label)
-    avg_cost = fluid.layers.mean(x=cost)
+    avg_cost = fluid.layers.mean(cost)
 
     optimizer = fluid.optimizer.Adagrad(learning_rate=1e-4)
     optimizer.minimize(avg_cost)

python/paddle/v2/fluid/tests/demo/fc_gan.py

@@ -96,7 +96,7 @@ def main():
             x=D(img),
             label=fluid.layers.data(
                 name='label', shape=[1], dtype='float32'))
-        d_loss = fluid.layers.mean(x=d_loss)
+        d_loss = fluid.layers.mean(d_loss)
 
     with fluid.program_guard(dg_program, startup_program):
         noise = fluid.layers.data(
@@ -107,7 +107,7 @@ def main():
             x=D(g_img),
             label=fluid.layers.fill_constant_batch_size_like(
                 input=noise, dtype='float32', shape=[-1, 1], value=1.0))
-        dg_loss = fluid.layers.mean(x=dg_loss)
+        dg_loss = fluid.layers.mean(dg_loss)
 
     opt = fluid.optimizer.Adam(learning_rate=LEARNING_RATE)