Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into revert_callstack

.travis.yml

@@ -12,7 +12,6 @@ services:
 os:
   - linux
 env:
-  - JOB=doc
   - JOB=check_style
   - JOB=build_android
 addons:

CMakeLists.txt

@@ -69,6 +69,7 @@ option(WITH_ANAKIN      "Compile with Anakin library"                   OFF)
 option(WITH_GRPC     "Use grpc as the default rpc framework"            ${WITH_DISTRIBUTE})
 option(WITH_BRPC_RDMA     "Use brpc rdma as the rpc protocal"           OFF)
 option(WITH_INFERENCE    "Compile fluid inference library"              ON)
+option(WITH_INFERENCE_API_TEST   "Test fluid inference high-level api interface"  OFF)
 option(WITH_SYSTEM_BLAS   "Use system blas library"           OFF)
 option(PY_VERSION       "Compile PaddlePaddle with python3 support"     ${PY_VERSION})
 
@@ -213,9 +214,11 @@ include(configure)          # add paddle env configuration
 if(WITH_GPU)
     include(cuda)
     include(tensorrt)
+endif()
+if(WITH_MKL OR WITH_MKLML)
     include(external/anakin)
 elseif()
-    set(WITH_ANAKIN OFF CACHE STRING "Anakin is used in GPU only now." FORCE)
+    set(WITH_ANAKIN OFF CACHE STRING "Anakin is used in MKL only now." FORCE)
 endif()
 
 include(generic)            # simplify cmake module

Dockerfile

@@ -53,7 +53,7 @@ RUN curl -s -q https://glide.sh/get | sh
 #    and its size is only one-third of the official one.
 # 2. Manually add ~IPluginFactory() in IPluginFactory class of NvInfer.h, otherwise, it couldn't work in paddle.
 #    See https://github.com/PaddlePaddle/Paddle/issues/10129 for details.
-RUN wget -qO- http://paddlepaddledeps.bj.bcebos.com/TensorRT-4.0.0.3.Ubuntu-16.04.4.x86_64-gnu.cuda-8.0.cudnn7.0.tar.gz | \
+RUN wget -qO- http://paddlepaddledeps.cdn.bcebos.com/TensorRT-4.0.0.3.Ubuntu-16.04.4.x86_64-gnu.cuda-8.0.cudnn7.0.tar.gz | \
     tar -xz -C /usr/local && \
     cp -rf /usr/local/TensorRT/include /usr && \
     cp -rf /usr/local/TensorRT/lib /usr

README.md

@@ -19,7 +19,7 @@ Our vision is to enable deep learning for everyone via PaddlePaddle.
 Please refer to our [release announcement](https://github.com/PaddlePaddle/Paddle/releases) to track the latest feature of PaddlePaddle.
 
 
-### Latest PaddlePaddle Release: [Fluid 0.14.0](https://github.com/PaddlePaddle/Paddle/tree/v0.14.0)
+### Latest PaddlePaddle Release: [Fluid 0.15.0](https://github.com/PaddlePaddle/Paddle/tree/v0.15.0)
 ### Install Latest Stable Release:
 ```
 # Linux CPU
@@ -27,9 +27,9 @@ pip install paddlepaddle
 # Linux GPU cuda9cudnn7
 pip install paddlepaddle-gpu
 # Linux GPU cuda8cudnn7
-pip install paddlepaddle-gpu==0.14.0.post87
+pip install paddlepaddle-gpu==0.15.0.post87
 # Linux GPU cuda8cudnn5
-pip install paddlepaddle-gpu==0.14.0.post85
+pip install paddlepaddle-gpu==0.15.0.post85
 
 # For installation on other platform, refer to http://paddlepaddle.org/
 ```
@@ -76,26 +76,26 @@ pip install paddlepaddle-gpu==0.14.0.post85
 
 ## Installation
 
-It is recommended to read [this doc](http://paddlepaddle.org/documentation/docs/zh/0.14.0/new_docs/beginners_guide/install/install_doc.html) on our website.
+It is recommended to read [this doc](http://paddlepaddle.org/documentation/docs/zh/0.15.0/new_docs/beginners_guide/install/install_doc.html) on our website.
 
 ## Documentation
 
-We provide [English](http://paddlepaddle.org/documentation/docs/en/0.14.0/getstarted/index_en.html) and
+We provide [English](http://paddlepaddle.org/documentation/docs/en/0.15.0/getstarted/index_en.html) and
-[Chinese](http://paddlepaddle.org/documentation/docs/zh/0.14.0/new_docs/beginners_guide/index.html) documentation.
+[Chinese](http://paddlepaddle.org/documentation/docs/zh/0.15.0/new_docs/beginners_guide/index.html) documentation.
 
 - [Deep Learning 101](https://github.com/PaddlePaddle/book)
 
   You might want to start from this online interactive book that can run in a Jupyter Notebook.
 
-- [Distributed Training](http://paddlepaddle.org/documentation/docs/zh/0.14.0/new_docs/user_guides/howto/training/cluster_howto.html)
+- [Distributed Training](http://paddlepaddle.org/documentation/docs/zh/0.15.0/new_docs/user_guides/howto/training/cluster_howto.html)
 
   You can run distributed training jobs on MPI clusters.
 
-- [Python API](http://paddlepaddle.org/documentation/api/zh/0.14.0/fluid.html)
+- [Python API](http://paddlepaddle.org/documentation/api/zh/0.15.0/fluid.html)
 
    Our new API enables much shorter programs.
 
-- [How to Contribute](http://paddlepaddle.org/documentation/docs/zh/0.14.0/new_docs/advanced_usage/development/contribute_to_paddle.html)
+- [How to Contribute](http://paddlepaddle.org/documentation/docs/zh/0.15.0/new_docs/advanced_usage/development/contribute_to_paddle.html)
 
    We appreciate your contributions!
 

benchmark/fluid/Dockerfile

@@ -11,6 +11,7 @@ RUN ln -s /usr/lib/x86_64-linux-gnu/libcudnn.so.7 /usr/lib/libcudnn.so && ln -s
 # Add "ENV http_proxy=http://ip:port" if your download is slow, and don't forget to unset it at runtime.
 # exmaple: unset http_proxy && unset https_proxy && python fluid_benchmark.py ...
 
+
 RUN pip install -U pip
 RUN pip install -U kubernetes paddlepaddle
 
@@ -27,5 +28,6 @@ ADD *.whl /
 RUN pip install /*.whl && rm -f /*.whl 
 
 ENV LD_LIBRARY_PATH=/usr/local/lib
-ADD fluid_benchmark.py recordio_converter.py args.py recordio_converter.py run.sh run_fluid_benchmark.sh /workspace/
+ADD fluid_benchmark.py recordio_converter.py args.py recordio_converter.py run.sh run_fluid_benchmark.sh imagenet_reader.py /workspace/
 ADD models/ /workspace/models/
+

benchmark/fluid/args.py

@@ -17,7 +17,8 @@ import argparse
 __all__ = ['parse_args', ]
 
 BENCHMARK_MODELS = [
-    "machine_translation", "resnet", "vgg", "mnist", "stacked_dynamic_lstm"
+    "machine_translation", "resnet", "se_resnext", "vgg", "mnist",
+    "stacked_dynamic_lstm", "resnet_with_preprocess"
 ]
 
 
@@ -67,12 +68,12 @@ def parse_args():
         '--cpus',
         type=int,
         default=1,
-        help='If cpus > 1, will use ParallelDo to run, else use Executor.')
+        help='If cpus > 1, will set ParallelExecutor to use multiple threads.')
     parser.add_argument(
         '--data_set',
         type=str,
         default='flowers',
-        choices=['cifar10', 'flowers'],
+        choices=['cifar10', 'flowers', 'imagenet'],
         help='Optional dataset for benchmark.')
     parser.add_argument(
         '--infer_only', action='store_true', help='If set, run forward only.')
@@ -122,6 +123,11 @@ def parse_args():
         type=str,
         default="",
         help='Directory that contains all the training recordio files.')
+    parser.add_argument(
+        '--test_data_path',
+        type=str,
+        default="",
+        help='Directory that contains all the test data (NOT recordio).')
     parser.add_argument(
         '--use_inference_transpiler',
         action='store_true',
@@ -130,5 +136,11 @@ def parse_args():
         '--no_random',
         action='store_true',
         help='If set, keep the random seed and do not shuffle the data.')
+    parser.add_argument(
+        '--reduce_strategy',
+        type=str,
+        choices=['reduce', 'all_reduce'],
+        default='all_reduce',
+        help='Specify the reduce strategy, can be reduce, all_reduce')
     args = parser.parse_args()
     return args

benchmark/fluid/kube_gen_job.py

@@ -163,6 +163,19 @@ def gen_job():
         volumes.append({"name": "dshm", "emptyDir": {"medium": "Memory"}})
         volumeMounts.append({"mountPath": "/dev/shm", "name": "dshm"})
 
+    # add ceph volumes
+    volumes.append({
+        "name": "ceph-data",
+        "cephfs": {
+            "monitors": ["192.168.16.23:6789"],
+            "secretRef": {
+                "name": "ceph-secret"
+            },
+            "user": "admin",
+        }
+    })
+    volumeMounts.append({"mountPath": "/mnt/data", "name": "ceph-data"})
+
     tn["spec"]["template"]["spec"]["volumes"] = volumes
     tn_container["volumeMounts"] = volumeMounts
 

benchmark/fluid/models/__init__.py

@@ -13,5 +13,6 @@
 # limitations under the License.
 
 __all__ = [
-    "machine_translation", "resnet", "vgg", "mnist", "stacked_dynamic_lstm"
+    "machine_translation", "resnet", "vgg", "mnist", "stacked_dynamic_lstm",
+    "resnet_with_preprocess"
 ]

benchmark/fluid/models/machine_translation.py

@@ -12,6 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 """seq2seq model for fluid."""
+
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
@@ -181,7 +182,7 @@ def lodtensor_to_ndarray(lod_tensor):
     return ndarray
 
 
-def get_model(args):
+def get_model(args, is_train, main_prog, startup_prog):
     if args.use_reader_op:
         raise Exception("machine_translation do not support reader op for now.")
     embedding_dim = 512
@@ -190,30 +191,27 @@ def get_model(args):
     dict_size = 30000
     beam_size = 3
     max_length = 250
-    avg_cost, feeding_list = seq_to_seq_net(
-        embedding_dim,
-        encoder_size,
-        decoder_size,
-        dict_size,
-        dict_size,
-        False,
-        beam_size=beam_size,
-        max_length=max_length)
-
-    # clone from default main program
-    inference_program = fluid.default_main_program().clone()
-
-    optimizer = fluid.optimizer.Adam(learning_rate=args.learning_rate)
-
-    train_batch_generator = paddle.batch(
-        paddle.reader.shuffle(
-            paddle.dataset.wmt14.train(dict_size), buf_size=1000),
-        batch_size=args.batch_size * args.gpus)
 
-    test_batch_generator = paddle.batch(
+    with fluid.program_guard(main_prog, startup_prog):
+        with fluid.unique_name.guard():
+            avg_cost, feeding_list = seq_to_seq_net(
+                embedding_dim,
+                encoder_size,
+                decoder_size,
+                dict_size,
+                dict_size,
+                False,
+                beam_size=beam_size,
+                max_length=max_length)
+    if is_train:
+        optimizer = fluid.optimizer.Adam(learning_rate=args.learning_rate)
+        optimizer.minimize(avg_cost)
+
+    batch_generator = paddle.batch(
         paddle.reader.shuffle(
-            paddle.dataset.wmt14.test(dict_size), buf_size=1000),
+            paddle.dataset.wmt14.train(dict_size)
-        batch_size=args.batch_size)
+            if is_train else paddle.dataset.wmt14.test(dict_size),
+            buf_size=1000),
+        batch_size=args.batch_size * args.gpus)
 
-    return avg_cost, inference_program, optimizer, train_batch_generator, \
+    return avg_cost, optimizer, [], batch_generator, None
-           test_batch_generator, None

benchmark/fluid/models/mnist.py

@@ -65,61 +65,53 @@ def cnn_model(data):
     return predict
 
 
-def get_model(args):
+def get_model(args, is_train, main_prog, startup_prog):
-    if args.use_reader_op:
+    # NOTE: mnist is small, we don't implement data sharding yet.
-        filelist = [
+    opt = None
-            os.path.join(args.data_path, f) for f in os.listdir(args.data_path)
+    data_file_handle = None
-        ]
+    with fluid.program_guard(main_prog, startup_prog):
-        data_file = fluid.layers.open_files(
+        if args.use_reader_op:
-            filenames=filelist,
+            filelist = [
-            shapes=[[-1, 1, 28, 28], (-1, 1)],
+                os.path.join(args.data_path, f)
-            lod_levels=[0, 0],
+                for f in os.listdir(args.data_path)
-            dtypes=["float32", "int64"],
+            ]
-            thread_num=args.gpus,
+            data_file_handle = fluid.layers.open_files(
-            pass_num=args.pass_num)
+                filenames=filelist,
-        data_file = fluid.layers.double_buffer(
+                shapes=[[-1, 1, 28, 28], (-1, 1)],
-            fluid.layers.batch(
+                lod_levels=[0, 0],
-                data_file, batch_size=args.batch_size))
+                dtypes=["float32", "int64"],
-        images, label = fluid.layers.read_file(data_file)
+                thread_num=1,
-    else:
+                pass_num=1)
-        images = fluid.layers.data(name='pixel', shape=[1, 28, 28], dtype=DTYPE)
+            data_file = fluid.layers.double_buffer(
-        label = fluid.layers.data(name='label', shape=[1], dtype='int64')
+                fluid.layers.batch(
-
+                    data_file_handle, batch_size=args.batch_size))
-    if args.device == 'CPU' and args.cpus > 1:
+        with fluid.unique_name.guard():
-        places = fluid.layers.get_places(args.cpus)
+            if args.use_reader_op:
-        pd = fluid.layers.ParallelDo(places)
+                input, label = fluid.layers.read_file(data_file)
-        with pd.do():
+            else:
-            predict = cnn_model(pd.read_input(images))
+                images = fluid.layers.data(
-            label = pd.read_input(label)
+                    name='pixel', shape=[1, 28, 28], dtype='float32')
+                label = fluid.layers.data(
+                    name='label', shape=[1], dtype='int64')
+
+            predict = cnn_model(images)
             cost = fluid.layers.cross_entropy(input=predict, label=label)
             avg_cost = fluid.layers.mean(x=cost)
+            # Evaluator
             batch_acc = fluid.layers.accuracy(input=predict, label=label)
-
+            # Optimization
-            pd.write_output(avg_cost)
+            if is_train:
-            pd.write_output(batch_acc)
+                opt = fluid.optimizer.AdamOptimizer(
-
+                    learning_rate=0.001, beta1=0.9, beta2=0.999)
-        avg_cost, batch_acc = pd()
+                opt.minimize(avg_cost)
-        avg_cost = fluid.layers.mean(avg_cost)
+                if args.memory_optimize:
-        batch_acc = fluid.layers.mean(batch_acc)
+                    fluid.memory_optimize(main_prog)
-    else:
-        # Train program
-        predict = cnn_model(images)
-        cost = fluid.layers.cross_entropy(input=predict, label=label)
-        avg_cost = fluid.layers.mean(x=cost)
-
-        # Evaluator
-        batch_acc = fluid.layers.accuracy(input=predict, label=label)
-
-    # inference program
-    inference_program = fluid.default_main_program().clone()
-
-    # Optimization
-    opt = fluid.optimizer.AdamOptimizer(
-        learning_rate=0.001, beta1=0.9, beta2=0.999)
 
     # Reader
-    train_reader = paddle.batch(
+    if is_train:
-        paddle.dataset.mnist.train(), batch_size=args.batch_size * args.gpus)
+        reader = paddle.dataset.mnist.train()
-    test_reader = paddle.batch(
+    else:
-        paddle.dataset.mnist.test(), batch_size=args.batch_size)
+        reader = paddle.dataset.mnist.test()
-    return avg_cost, inference_program, opt, train_reader, test_reader, batch_acc
+    batched_reader = paddle.batch(
+        reader, batch_size=args.batch_size * args.gpus)
+    return avg_cost, opt, [batch_acc], batched_reader, data_file_handle

benchmark/fluid/models/stacked_dynamic_lstm.py

@@ -26,7 +26,6 @@ import numpy
 import paddle
 import paddle.dataset.imdb as imdb
 import paddle.fluid as fluid
-import paddle.batch as batch
 import paddle.fluid.profiler as profiler
 
 word_dict = imdb.word_dict()
@@ -43,19 +42,7 @@ def crop_sentence(reader, crop_size):
     return __impl__
 
 
-def get_model(args):
+def lstm_net(sentence, lstm_size):
-    if args.use_reader_op:
-        raise Exception(
-            "stacked_dynamic_lstm do not support reader op for now.")
-    lstm_size = 512
-    emb_dim = 512
-    crop_size = 1500
-
-    data = fluid.layers.data(
-        name="words", shape=[1], lod_level=1, dtype='int64')
-    sentence = fluid.layers.embedding(
-        input=data, size=[len(word_dict), emb_dim])
-
     sentence = fluid.layers.fc(input=sentence, size=lstm_size, act='tanh')
 
     rnn = fluid.layers.DynamicRNN()
@@ -97,31 +84,47 @@ def get_model(args):
 
     last = fluid.layers.sequence_pool(rnn(), 'last')
     logit = fluid.layers.fc(input=last, size=2, act='softmax')
-    loss = fluid.layers.cross_entropy(
+    return logit
-        input=logit,
-        label=fluid.layers.data(
-            name='label', shape=[1], dtype='int64'))
-    loss = fluid.layers.mean(x=loss)
 
-    # add acc
-    batch_size_tensor = fluid.layers.create_tensor(dtype='int64')
-    batch_acc = fluid.layers.accuracy(input=logit, label=fluid.layers.data(name='label', \
-                shape=[1], dtype='int64'), total=batch_size_tensor)
 
-    inference_program = fluid.default_main_program().clone()
+def get_model(args, is_train, main_prog, startup_prog):
-    with fluid.program_guard(inference_program):
+    if args.use_reader_op:
-        inference_program = fluid.io.get_inference_program(
+        raise Exception(
-            target_vars=[batch_acc, batch_size_tensor])
+            "stacked_dynamic_lstm do not support reader op for now.")
-
+    lstm_size = 512
-    adam = fluid.optimizer.Adam()
+    emb_dim = 512
+    crop_size = 1500
 
-    train_reader = batch(
+    with fluid.program_guard(main_prog, startup_prog):
+        with fluid.unique_name.guard():
+            data = fluid.layers.data(
+                name="words", shape=[1], lod_level=1, dtype='int64')
+            sentence = fluid.layers.embedding(
+                input=data, size=[len(word_dict), emb_dim])
+            logit = lstm_net(sentence, lstm_size)
+            loss = fluid.layers.cross_entropy(
+                input=logit,
+                label=fluid.layers.data(
+                    name='label', shape=[1], dtype='int64'))
+            loss = fluid.layers.mean(x=loss)
+
+            # add acc
+            batch_size_tensor = fluid.layers.create_tensor(dtype='int64')
+            batch_acc = fluid.layers.accuracy(input=logit, label=fluid.layers.data(name='label', \
+                        shape=[1], dtype='int64'), total=batch_size_tensor)
+
+            if is_train:
+                adam = fluid.optimizer.Adam()
+                adam.minimize(loss)
+
+    if is_train:
+        reader = crop_sentence(imdb.train(word_dict), crop_size)
+    else:
+        reader = crop_sentence(imdb.test(word_dict), crop_size)
+
+    batched_reader = paddle.batch(
         paddle.reader.shuffle(
-            crop_sentence(imdb.train(word_dict), crop_size), buf_size=25000),
+            reader, buf_size=25000),
         batch_size=args.batch_size * args.gpus)
-    test_reader = batch(
-        paddle.reader.shuffle(
-            crop_sentence(imdb.test(word_dict), crop_size), buf_size=25000),
-        batch_size=args.batch_size)
 
-    return loss, inference_program, adam, train_reader, test_reader, batch_acc
+    return loss, adam, [batch_acc], batched_reader, None

benchmark/fluid/models/vgg.py

@@ -25,7 +25,7 @@ import functools
 import os
 
 
-def vgg16_bn_drop(input):
+def vgg16_bn_drop(input, is_train=True):
     def conv_block(input, num_filter, groups, dropouts):
         return fluid.nets.img_conv_group(
             input=input,
@@ -46,13 +46,13 @@ def vgg16_bn_drop(input):
 
     drop = fluid.layers.dropout(x=conv5, dropout_prob=0.5)
     fc1 = fluid.layers.fc(input=drop, size=512, act=None)
-    bn = fluid.layers.batch_norm(input=fc1, act='relu')
+    bn = fluid.layers.batch_norm(input=fc1, act='relu', is_test=not is_train)
     drop2 = fluid.layers.dropout(x=bn, dropout_prob=0.5)
     fc2 = fluid.layers.fc(input=drop2, size=512, act=None)
     return fc2
 
 
-def get_model(args):
+def get_model(args, is_train, main_prog, startup_prog):
     if args.data_set == "cifar10":
         classdim = 10
         if args.data_format == 'NCHW':
@@ -65,57 +65,56 @@ def get_model(args):
             data_shape = [3, 224, 224]
         else:
             data_shape = [224, 224, 3]
+    filelist = [
+        os.path.join(args.data_path, f) for f in os.listdir(args.data_path)
+    ]
+    with fluid.program_guard(main_prog, startup_prog):
+        if args.use_reader_op:
+            data_file_handle = fluid.layers.open_files(
+                filenames=filelist,
+                shapes=[[-1] + data_shape, (-1, 1)],
+                lod_levels=[0, 0],
+                dtypes=["float32", "int64"],
+                thread_num=1,
+                pass_num=1)
+            data_file = fluid.layers.double_buffer(
+                fluid.layers.batch(
+                    data_file_handle, batch_size=args.batch_size))
+        with fluid.unique_name.guard():
+            if args.use_reader_op:
+                images, label = fluid.layers.read_file(data_file)
+            else:
+                images = fluid.layers.data(
+                    name='data', shape=data_shape, dtype='float32')
+                label = fluid.layers.data(
+                    name='label', shape=[1], dtype='int64')
+            # Train program
+            net = vgg16_bn_drop(images, is_train=is_train)
+            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)
 
-    if args.use_reader_op:
+            # Evaluator
-        filelist = [
+            batch_size_tensor = fluid.layers.create_tensor(dtype='int64')
-            os.path.join(args.data_path, f) for f in os.listdir(args.data_path)
+            batch_acc = fluid.layers.accuracy(
-        ]
+                input=predict, label=label, total=batch_size_tensor)
-        data_file = fluid.layers.open_files(
+            # Optimization
-            filenames=filelist,
+            if is_train:
-            shapes=[[-1] + data_shape, (-1, 1)],
+                optimizer = fluid.optimizer.Adam(
-            lod_levels=[0, 0],
+                    learning_rate=args.learning_rate)
-            dtypes=["float32", "int64"],
+                optimizer.minimize(avg_cost)
-            thread_num=args.gpus,
-            pass_num=args.pass_num)
-        data_file = fluid.layers.double_buffer(
-            fluid.layers.batch(
-                data_file, batch_size=args.batch_size))
-        images, label = fluid.layers.read_file(data_file)
-    else:
-        images = fluid.layers.data(
-            name='data', shape=data_shape, dtype='float32')
-        label = fluid.layers.data(name='label', shape=[1], dtype='int64')
-
-    # Train program
-    net = vgg16_bn_drop(images)
-    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)
-
-    # Evaluator
-    batch_size_tensor = fluid.layers.create_tensor(dtype='int64')
-    batch_acc = fluid.layers.accuracy(
-        input=predict, label=label, total=batch_size_tensor)
-
-    # inference program
-    inference_program = fluid.default_main_program().clone()
-    with fluid.program_guard(inference_program):
-        inference_program = fluid.io.get_inference_program(
-            target_vars=[batch_acc, batch_size_tensor])
-
-    # Optimization
-    optimizer = fluid.optimizer.Adam(learning_rate=args.learning_rate)
 
     # data reader
-    train_reader = paddle.batch(
+    if is_train:
+        reader = paddle.dataset.cifar.train10() \
+            if args.data_set == 'cifar10' else paddle.dataset.flowers.train()
+    else:
+        reader = paddle.dataset.cifar.test10() \
+            if args.data_set == 'cifar10' else paddle.dataset.flowers.test()
+
+    batched_reader = paddle.batch(
         paddle.reader.shuffle(
-            paddle.dataset.cifar.train10()
+            reader, buf_size=5120),
-            if args.data_set == 'cifar10' else paddle.dataset.flowers.train(),
-            buf_size=5120),
         batch_size=args.batch_size * args.gpus)
-    test_reader = paddle.batch(
-        paddle.dataset.cifar.test10()
-        if args.data_set == 'cifar10' else paddle.dataset.flowers.test(),
-        batch_size=args.batch_size)
 
-    return avg_cost, inference_program, optimizer, train_reader, test_reader, batch_acc
+    return avg_cost, optimizer, [batch_acc], batched_reader, data_file_handle

cmake/external/anakin.cmake

@@ -16,16 +16,6 @@ set(ANAKIN_LIBRARY     ${ANAKIN_INSTALL_DIR})
 set(ANAKIN_SHARED_LIB  ${ANAKIN_LIBRARY}/libanakin.so)
 set(ANAKIN_SABER_LIB   ${ANAKIN_LIBRARY}/libanakin_saber_common.so)
 
-# TODO(luotao): ANAKIN_MODLE_URL etc will move to demo ci later.
-set(INFERENCE_URL "http://paddle-inference-dist.bj.bcebos.com")
-set(ANAKIN_MODLE_URL "${INFERENCE_URL}/mobilenet_v2.anakin.bin")
-set(ANAKIN_RNN_MODLE_URL "${INFERENCE_URL}/anakin_test%2Fditu_rnn.anakin2.model.bin")
-set(ANAKIN_RNN_DATA_URL "${INFERENCE_URL}/anakin_test%2Fditu_rnn_data.txt")
-execute_process(COMMAND bash -c "mkdir -p ${ANAKIN_SOURCE_DIR}")
-execute_process(COMMAND bash -c "cd ${ANAKIN_SOURCE_DIR}; wget -q --no-check-certificate ${ANAKIN_MODLE_URL} -N")
-execute_process(COMMAND bash -c "cd ${ANAKIN_SOURCE_DIR}; wget -q --no-check-certificate ${ANAKIN_RNN_MODLE_URL} -N")
-execute_process(COMMAND bash -c "cd ${ANAKIN_SOURCE_DIR}; wget -q --no-check-certificate ${ANAKIN_RNN_DATA_URL} -N")
-
 include_directories(${ANAKIN_INCLUDE})
 include_directories(${ANAKIN_INCLUDE}/saber/)
 include_directories(${ANAKIN_INCLUDE}/saber/core/)
@@ -48,21 +38,24 @@ set(ANAKIN_COMPILE_EXTRA_FLAGS
     -Wno-reorder
     -Wno-error=cpp)
 
+if(WITH_GPU)
+    set(CMAKE_ARGS_PREFIX -DUSE_GPU_PLACE=YES -DCUDNN_ROOT=${CUDNN_ROOT} -DCUDNN_INCLUDE_DIR=${CUDNN_INCLUDE_DIR})
+else()
+    set(CMAKE_ARGS_PREFIX -DUSE_GPU_PLACE=NO)
+endif()
 ExternalProject_Add(
     extern_anakin
     ${EXTERNAL_PROJECT_LOG_ARGS}
     DEPENDS             ${MKLML_PROJECT}
     GIT_REPOSITORY      "https://github.com/PaddlePaddle/Anakin"
-    GIT_TAG             "9424277cf9ae180a14aff09560d3cd60a49c76d2"
+    GIT_TAG             "3c8554f4978628183566ab7dd6c1e7e66493c7cd"
     PREFIX              ${ANAKIN_SOURCE_DIR}
     UPDATE_COMMAND      ""
-    CMAKE_ARGS          -DUSE_GPU_PLACE=YES
+    CMAKE_ARGS          ${CMAKE_ARGS_PREFIX}
                         -DUSE_X86_PLACE=YES
                         -DBUILD_WITH_UNIT_TEST=NO
                         -DPROTOBUF_ROOT=${THIRD_PARTY_PATH}/install/protobuf
                         -DMKLML_ROOT=${THIRD_PARTY_PATH}/install/mklml
-                        -DCUDNN_ROOT=${CUDNN_ROOT}
-                        -DCUDNN_INCLUDE_DIR=${CUDNN_INCLUDE_DIR}
                         -DENABLE_OP_TIMER=${ANAKIN_ENABLE_OP_TIMER}
                         ${EXTERNAL_OPTIONAL_ARGS}
     CMAKE_CACHE_ARGS    -DCMAKE_INSTALL_PREFIX:PATH=${ANAKIN_INSTALL_DIR}

cmake/external/mklml.cmake

@@ -29,7 +29,7 @@ INCLUDE(ExternalProject)
 SET(MKLML_PROJECT       "extern_mklml")
 IF((NOT DEFINED MKLML_VER) OR (NOT DEFINED MKLML_URL))
   MESSAGE(STATUS "use pre defined download url")
-  SET(MKLML_VER "mklml_lnx_2018.0.3.20180406" CACHE STRING "" FORCE)
+  SET(MKLML_VER "mklml_lnx_2019.0.20180710" CACHE STRING "" FORCE)
   SET(MKLML_URL "http://paddlepaddledeps.cdn.bcebos.com/${MKLML_VER}.tgz" CACHE STRING "" FORCE)
 ENDIF()
 MESSAGE(STATUS "MKLML_VER: ${MKLML_VER}, MKLML_URL: ${MKLML_URL}")

cmake/generic.cmake

@@ -298,11 +298,10 @@ function(cc_test TARGET_NAME)
              WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR})
     if (${cc_test_SERIAL})
         set_property(TEST ${TARGET_NAME} PROPERTY RUN_SERIAL 1)
-
+    endif()
     set_property(TEST ${TARGET_NAME} PROPERTY ENVIRONMENT FLAGS_cpu_deterministic=true)
     set_property(TEST ${TARGET_NAME} PROPERTY ENVIRONMENT FLAGS_init_allocated_mem=true)
     set_property(TEST ${TARGET_NAME} PROPERTY ENVIRONMENT FLAGS_cudnn_deterministic=true)
-    endif()
   endif()
 endfunction(cc_test)
 
@@ -366,11 +365,10 @@ function(nv_test TARGET_NAME)
     add_test(${TARGET_NAME} ${TARGET_NAME})
     if (nv_test_SERIAL)
         set_property(TEST ${TARGET_NAME} PROPERTY RUN_SERIAL 1)
-
+    endif()
     set_property(TEST ${TARGET_NAME} PROPERTY ENVIRONMENT FLAGS_cpu_deterministic=true)
     set_property(TEST ${TARGET_NAME} PROPERTY ENVIRONMENT FLAGS_init_allocated_mem=true)
     set_property(TEST ${TARGET_NAME} PROPERTY ENVIRONMENT FLAGS_cudnn_deterministic=true)
-    endif()
   endif()
 endfunction(nv_test)
 

cmake/inference_lib.cmake

@@ -128,16 +128,13 @@ set(src_dir "${PADDLE_SOURCE_DIR}/paddle/fluid")
 set(dst_dir "${FLUID_INSTALL_DIR}/paddle/fluid")
 set(module "framework")
 if (NOT WIN32)
-copy(framework_lib DEPS framework_py_proto 
+set(framework_lib_deps framework_py_proto)
-  SRCS ${src_dir}/${module}/*.h ${src_dir}/${module}/details/*.h ${PADDLE_BINARY_DIR}/paddle/fluid/framework/framework.pb.h
+endif(NOT WIN32)
-  DSTS ${dst_dir}/${module} ${dst_dir}/${module}/details ${dst_dir}/${module}
+copy(framework_lib DEPS ${framework_lib_deps}
-)
-else()
-copy(framework_lib
   SRCS ${src_dir}/${module}/*.h ${src_dir}/${module}/details/*.h ${PADDLE_BINARY_DIR}/paddle/fluid/framework/framework.pb.h
-  DSTS ${dst_dir}/${module} ${dst_dir}/${module}/details ${dst_dir}/${module}
+       ${src_dir}/${module}/ir/*.h
+  DSTS ${dst_dir}/${module} ${dst_dir}/${module}/details ${dst_dir}/${module} ${dst_dir}/${module}/ir
 )
-endif(NOT WIN32)
 
 set(module "memory")
 copy(memory_lib
@@ -148,12 +145,12 @@ copy(memory_lib
 set(inference_deps paddle_fluid_shared paddle_fluid)
 
 set(module "inference/api")
-if (WITH_ANAKIN AND WITH_GPU)
+if (WITH_ANAKIN AND WITH_MKL)
     copy(anakin_inference_lib DEPS paddle_inference_api inference_anakin_api
         SRCS
         ${PADDLE_BINARY_DIR}/paddle/fluid/inference/api/libinference_anakin_api* # compiled anakin api
         ${ANAKIN_INSTALL_DIR} # anakin release
-        DSTS ${dst_dir}/inference/anakin ${dst_dir}/inference/anakin)
+        DSTS ${dst_dir}/inference/anakin ${FLUID_INSTALL_DIR}/third_party/install/anakin)
      list(APPEND inference_deps anakin_inference_lib)
 endif()
 
@@ -161,7 +158,8 @@ set(module "inference")
 copy(inference_lib DEPS ${inference_deps}
   SRCS ${src_dir}/${module}/*.h ${PADDLE_BINARY_DIR}/paddle/fluid/inference/libpaddle_fluid.*
        ${src_dir}/${module}/api/paddle_inference_api.h ${src_dir}/${module}/api/demo_ci
-  DSTS ${dst_dir}/${module} ${dst_dir}/${module} ${dst_dir}/${module} ${dst_dir}/${module}
+       ${PADDLE_BINARY_DIR}/paddle/fluid/inference/api/paddle_inference_pass.h
+  DSTS ${dst_dir}/${module} ${dst_dir}/${module} ${dst_dir}/${module} ${dst_dir}/${module} ${dst_dir}/${module}
 )
 
 set(module "platform")

cmake/tensorrt.cmake

@@ -16,7 +16,9 @@ find_library(TENSORRT_LIBRARY NAMES libnvinfer.so libnvinfer.a
     DOC "Path to TensorRT library.")
 
 if(TENSORRT_INCLUDE_DIR AND TENSORRT_LIBRARY)
+  if(WITH_DSO)
     set(TENSORRT_FOUND ON)
+  endif(WITH_DSO)
 else()
     set(TENSORRT_FOUND OFF)
 endif()

doc/README.md

@@ -0,0 +1,7 @@
+# For Readers and Developers
+
+Thanks for reading PaddlePaddle documentation. 
+
+Since **September 17th, 2018**, the **0.15.0 and develop** documentation source has been moved to [FluidDoc Repo](https://github.com/PaddlePaddle/FluidDoc) and updated there.
+
+Please turn to FluidDoc Repo for the latest documentation.

doc/fluid/CMakeLists.txt

@@ -1,54 +0,0 @@
-if(NOT DEFINED SPHINX_THEME)
-    set(SPHINX_THEME default)
-endif()
-
-if(NOT DEFINED SPHINX_THEME_DIR)
-    set(SPHINX_THEME_DIR)
-endif()
-
-# configured documentation tools and intermediate build results
-set(BINARY_BUILD_DIR_EN "${CMAKE_CURRENT_BINARY_DIR}/en/_build")
-
-# Sphinx cache with pickled ReST documents
-set(SPHINX_CACHE_DIR_EN "${CMAKE_CURRENT_BINARY_DIR}/en/_doctrees")
-
-# HTML output director
-set(SPHINX_HTML_DIR_EN "${CMAKE_CURRENT_BINARY_DIR}/en/html")
-
-set(IMPORT_PADDLE_STRING "")
-set(IMPORT_PADDLEV2_STRING "")
-
-configure_file(
-    "${CMAKE_CURRENT_SOURCE_DIR}/../templates/conf.py.en.in"
-    "${BINARY_BUILD_DIR_EN}/conf.py"
-    @ONLY)
-
-sphinx_add_target(paddle_fluid_docs
-                  html
-                  ${BINARY_BUILD_DIR_EN}
-                  ${SPHINX_CACHE_DIR_EN}
-                  ${CMAKE_CURRENT_SOURCE_DIR}
-                  ${SPHINX_HTML_DIR_EN})
-
-# configured documentation tools and intermediate build results
-set(BINARY_BUILD_DIR_CN "${CMAKE_CURRENT_BINARY_DIR}/cn/_build")
-
-# Sphinx cache with pickled ReST documents
-set(SPHINX_CACHE_DIR_CN "${CMAKE_CURRENT_BINARY_DIR}/cn/_doctrees")
-
-# HTML output directory
-set(SPHINX_HTML_DIR_CN "${CMAKE_CURRENT_BINARY_DIR}/cn/html")
-
-configure_file(
-    "${CMAKE_CURRENT_SOURCE_DIR}/../templates/conf.py.cn.in"
-    "${BINARY_BUILD_DIR_CN}/conf.py"
-    @ONLY)
-
-sphinx_add_target(paddle_fluid_docs_cn
-                  html
-                  ${BINARY_BUILD_DIR_CN}
-                  ${SPHINX_CACHE_DIR_CN}
-                  ${CMAKE_CURRENT_SOURCE_DIR}
-                  ${SPHINX_HTML_DIR_CN})
-
-add_subdirectory(api)

doc/fluid/api/CMakeLists.txt

@@ -1,25 +0,0 @@
-# configured documentation tools and intermediate build results
-set(BINARY_BUILD_DIR_EN "${CMAKE_CURRENT_BINARY_DIR}/en/_build")
-
-# Sphinx cache with pickled ReST documents
-set(SPHINX_CACHE_DIR_EN "${CMAKE_CURRENT_BINARY_DIR}/en/_doctrees")
-
-# HTML output director
-set(SPHINX_HTML_DIR_EN "${CMAKE_CURRENT_BINARY_DIR}/en/html")
-
-set(IMPORT_PADDLE_STRING "import paddle")
-set(IMPORT_PADDLEV2_STRING "import paddle.v2")
-
-configure_file(
-    "${CMAKE_CURRENT_SOURCE_DIR}/../../templates/conf.py.en.in"
-    "${BINARY_BUILD_DIR_EN}/conf.py"
-    @ONLY)
-
-sphinx_add_target(paddle_fluid_apis
-                  html
-                  ${BINARY_BUILD_DIR_EN}
-                  ${SPHINX_CACHE_DIR_EN}
-                  ${CMAKE_CURRENT_SOURCE_DIR}
-                  ${SPHINX_HTML_DIR_EN})
-
-add_dependencies(paddle_fluid_apis  gen_proto_py framework_py_proto copy_paddle_pybind paddle_python)