Merge remote-tracking branch 'upstream/develop' into mkl_packed

README.md

@@ -61,32 +61,32 @@ Please refer to our [release announcement](https://github.com/PaddlePaddle/Paddl
 ## Installation
 
 It is recommended to check out the
-[Docker installation guide](http://doc.paddlepaddle.org/develop/doc/getstarted/build_and_install/docker_install_en.html)
+[Docker installation guide](http://www.paddlepaddle.org/docs/develop/documentation/en/getstarted/build_and_install/docker_install_en.html)
 before looking into the
-[build from source guide](http://doc.paddlepaddle.org/develop/doc/getstarted/build_and_install/build_from_source_en.html).
+[build from source guide](http://www.paddlepaddle.org/docs/develop/documentation/en/getstarted/build_and_install/build_from_source_en.html).
 
 ## Documentation
 
-We provide [English](http://doc.paddlepaddle.org/develop/doc/) and
-[Chinese](http://doc.paddlepaddle.org/doc_cn/) documentation.
+We provide [English](http://www.paddlepaddle.org/docs/develop/documentation/en/getstarted/index_en.html) and
+[Chinese](http://www.paddlepaddle.org/docs/develop/documentation/zh/getstarted/index_cn.html) documentation.
 
-- [Deep Learning 101](http://book.paddlepaddle.org/index.html)
+- [Deep Learning 101](http://www.paddlepaddle.org/docs/develop/book/01.fit_a_line/index.html)
 
   You might want to start from this online interactive book that can run in a Jupyter Notebook.
 
-- [Distributed Training](http://doc.paddlepaddle.org/develop/doc/howto/usage/cluster/cluster_train_en.html)
+- [Distributed Training](http://www.paddlepaddle.org/docs/develop/documentation/en/howto/usage/cluster/cluster_train_en.html)
 
   You can run distributed training jobs on MPI clusters.
 
-- [Distributed Training on Kubernetes](http://doc.paddlepaddle.org/develop/doc/howto/usage/k8s/k8s_en.html)
+- [Distributed Training on Kubernetes](http://www.paddlepaddle.org/docs/develop/documentation/en/howto/usage/cluster/k8s_en.html)
 
    You can also run distributed training jobs on Kubernetes clusters.
 
-- [Python API](http://doc.paddlepaddle.org/develop/doc/api/index_en.html)
+- [Python API](http://www.paddlepaddle.org/docs/develop/documentation/en/api/index_en.html)
 
    Our new API enables much shorter programs.
 
-- [How to Contribute](http://doc.paddlepaddle.org/develop/doc/howto/dev/contribute_to_paddle_en.html)
+- [How to Contribute](http://www.paddlepaddle.org/docs/develop/documentation/en/howto/dev/contribute_to_paddle_en.html)
 
    We appreciate your contributions!
 

benchmark/paddle/image/alexnet.py

@@ -6,8 +6,18 @@
 width = 227
 num_class = 1000
 batch_size = get_config_arg('batch_size', int, 128)
+gp = get_config_arg('layer_num', int, 1)
+is_infer = get_config_arg("is_infer", bool, False)
+num_samples = get_config_arg('num_samples', int, 2560)
 
-args = {'height': height, 'width': width, 'color': True, 'num_class': num_class}
+args = {
+    'height': height,
+    'width': width,
+    'color': True,
+    'num_class': num_class,
+    'is_infer': is_infer,
+    'num_samples': num_samples
+}
 define_py_data_sources2(
     "train.list", None, module="provider", obj="process", args=args)
 
@@ -31,7 +41,7 @@
 
 # conv2
 net = img_conv_layer(
-    input=net, filter_size=5, num_filters=256, stride=1, padding=2, groups=1)
+    input=net, filter_size=5, num_filters=256, stride=1, padding=2, groups=gp)
 net = img_cmrnorm_layer(input=net, size=5, scale=0.0001, power=0.75)
 net = img_pool_layer(input=net, pool_size=3, stride=2)
 
@@ -40,11 +50,11 @@
     input=net, filter_size=3, num_filters=384, stride=1, padding=1)
 # conv4
 net = img_conv_layer(
-    input=net, filter_size=3, num_filters=384, stride=1, padding=1, groups=1)
+    input=net, filter_size=3, num_filters=384, stride=1, padding=1, groups=gp)
 
 # conv5
 net = img_conv_layer(
-    input=net, filter_size=3, num_filters=256, stride=1, padding=1, groups=1)
+    input=net, filter_size=3, num_filters=256, stride=1, padding=1, groups=gp)
 net = img_pool_layer(input=net, pool_size=3, stride=2)
 
 net = fc_layer(
@@ -59,6 +69,9 @@
     layer_attr=ExtraAttr(drop_rate=0.5))
 net = fc_layer(input=net, size=1000, act=SoftmaxActivation())
 
-lab = data_layer('label', num_class)
-loss = cross_entropy(input=net, label=lab)
-outputs(loss)
+if is_infer:
+    outputs(net)
+else:
+    lab = data_layer('label', num_class)
+    loss = cross_entropy(input=net, label=lab)
+    outputs(loss)

benchmark/paddle/image/googlenet.py

@@ -7,13 +7,15 @@
 batch_size = get_config_arg('batch_size', int, 128)
 use_gpu = get_config_arg('use_gpu', bool, True)
 is_infer = get_config_arg("is_infer", bool, False)
+num_samples = get_config_arg('num_samples', int, 2560)
 
 args = {
     'height': height,
     'width': width,
     'color': True,
     'num_class': num_class,
-    'is_infer': is_infer
+    'is_infer': is_infer,
+    'num_samples': num_samples
 }
 define_py_data_sources2(
     "train.list" if not is_infer else None,

benchmark/paddle/image/provider.py

@@ -14,6 +14,7 @@ def initHook(settings, height, width, color, num_class, **kwargs):
     else:
         settings.data_size = settings.height * settings.width
     settings.is_infer = kwargs.get('is_infer', False)
+    settings.num_samples = kwargs.get('num_samples', 2560)
     if settings.is_infer:
         settings.slots = [dense_vector(settings.data_size)]
     else:
@@ -23,7 +24,7 @@ def initHook(settings, height, width, color, num_class, **kwargs):
 @provider(
     init_hook=initHook, min_pool_size=-1, cache=CacheType.CACHE_PASS_IN_MEM)
 def process(settings, file_list):
-    for i in xrange(2560 if settings.is_infer else 1024):
+    for i in xrange(settings.num_samples):
         img = np.random.rand(1, settings.data_size).reshape(-1, 1).flatten()
         if settings.is_infer:
             yield img.astype('float32')

benchmark/paddle/image/resnet.py

@@ -7,13 +7,15 @@
 batch_size = get_config_arg('batch_size', int, 64)
 layer_num = get_config_arg("layer_num", int, 50)
 is_infer = get_config_arg("is_infer", bool, False)
+num_samples = get_config_arg('num_samples', int, 2560)
 
 args = {
     'height': height,
     'width': width,
     'color': True,
     'num_class': num_class,
-    'is_infer': is_infer
+    'is_infer': is_infer,
+    'num_samples': num_samples
 }
 define_py_data_sources2(
     "train.list" if not is_infer else None,

benchmark/paddle/image/run_mkldnn_infer.sh → benchmark/paddle/image/run_mkl_infer.sh

@@ -37,7 +37,7 @@ function infer() {
       --trainer_count=1 \
       --num_passes=1 \
       --save_dir="models/${topology}-${layer_num}" \
-      --config_args="batch_size=128,layer_num=${layer_num}" \
+      --config_args="batch_size=128,layer_num=${layer_num},num_samples=256" \
       > /dev/null 2>&1
     echo "Done"
   fi
@@ -79,8 +79,9 @@ fi
 # inference benchmark
 for use_mkldnn in True False; do
   for batchsize in 1 2 4 8 16; do
-    infer googlenet v1 $batchsize $use_mkldnn
-    infer resnet 50 $batchsize $use_mkldnn
     infer vgg 19 $batchsize $use_mkldnn
+    infer resnet 50 $batchsize $use_mkldnn
+    infer googlenet v1 $batchsize $use_mkldnn
+    infer alexnet 2 $batchsize $use_mkldnn
   done
 done

benchmark/paddle/image/run_mkldnn_train.sh → benchmark/paddle/image/run_mkl_train.sh

@@ -28,6 +28,10 @@ function train() {
     --test_period=100 \
     --config_args=$args \
     2>&1 | tee ${log} 
+
+  avg_time=`tail ${log} -n 1 | awk -F ' ' '{print $8}' | sed 's/avg=//'`
+  fps=`awk 'BEGIN{printf "%.2f",('$bs' / '$avg_time' * 1000)}'`
+  echo "FPS: $fps images/sec" 2>&1 | tee -a ${log}
 }
 
 if [ ! -f "train.list" ]; then
@@ -43,5 +47,6 @@ for use_mkldnn in True False; do
     train vgg 19 $batchsize $use_mkldnn
     train resnet 50 $batchsize $use_mkldnn
     train googlenet v1 $batchsize $use_mkldnn
+    train alexnet 2 $batchsize $use_mkldnn
   done
 done

benchmark/paddle/image/run_openblas_infer.sh

@@ -0,0 +1,64 @@
+set -e
+
+function clock_to_seconds() {
+  hours=`echo $1 | awk -F ':' '{print $1}'`
+  mins=`echo $1 | awk -F ':' '{print $2}'`
+  secs=`echo $1 | awk -F ':' '{print $3}'`
+  echo `awk 'BEGIN{printf "%.2f",('$secs' + '$mins' * 60 + '$hours' * 3600)}'`
+}
+
+function infer() {
+  unset OMP_NUM_THREADS MKL_NUM_THREADS OMP_DYNAMIC KMP_AFFINITY
+  topology=$1
+  layer_num=$2
+  bs=$3
+  thread=`nproc`
+  if [ $thread -gt $bs ]; then
+    thread=$bs
+  fi
+  log="logs/infer-${topology}-${layer_num}-${thread}openblas-${bs}.log"
+
+  models_in="models/${topology}-${layer_num}/pass-00000/"
+  if [ ! -d $models_in ]; then
+    echo "./run_mkl_infer.sh to save the model first"
+    exit 0
+  fi
+  log_period=$((32 / bs))
+  paddle train --job=test \
+    --config="${topology}.py" \
+    --use_mkldnn=False \
+    --use_gpu=False \
+    --trainer_count=$thread \
+    --log_period=$log_period \
+    --config_args="batch_size=${bs},layer_num=${layer_num},is_infer=True,num_samples=256" \
+    --init_model_path=$models_in \
+    2>&1 | tee ${log}
+
+  # calculate the last 5 logs period time of 160(=32*5) samples,
+  # the time before are burning time.
+  start=`tail ${log} -n 7 | head -n 1 | awk -F ' ' '{print $2}' | xargs`
+  end=`tail ${log} -n 2 | head -n 1 | awk -F ' ' '{print $2}' | xargs`
+  start_sec=`clock_to_seconds $start`
+  end_sec=`clock_to_seconds $end`
+  fps=`awk 'BEGIN{printf "%.2f",(160 / ('$end_sec' - '$start_sec'))}'`
+  echo "Last 160 samples start: ${start}(${start_sec} sec), end: ${end}(${end_sec} sec;" >> ${log}
+  echo "FPS: $fps images/sec" 2>&1 | tee -a ${log}
+}
+
+if [ ! -f "train.list" ]; then
+  echo " " > train.list
+fi
+if [ ! -f "test.list" ]; then
+  echo " " > test.list
+fi
+if [ ! -d "logs" ]; then
+  mkdir logs
+fi
+
+# inference benchmark
+for batchsize in 1 2 4 8 16; do
+  infer vgg 19 $batchsize
+  infer resnet 50 $batchsize 
+  infer googlenet v1 $batchsize
+  infer alexnet 2 $batchsize
+done

benchmark/paddle/image/run_openblas_train.sh

@@ -0,0 +1,41 @@
+set -e
+
+function train() {
+  unset OMP_NUM_THREADS MKL_NUM_THREADS OMP_DYNAMIC KMP_AFFINITY
+  topology=$1
+  layer_num=$2
+  bs=$3
+  thread=`nproc`
+  # each trainer_count use only 1 core to avoid conflict
+  log="logs/train-${topology}-${layer_num}-${thread}openblas-${bs}.log"
+  args="batch_size=${bs},layer_num=${layer_num}"
+  config="${topology}.py"
+  paddle train --job=time \
+    --config=$config \
+    --use_mkldnn=False \
+    --use_gpu=False \
+    --trainer_count=$thread \
+    --log_period=3 \
+    --test_period=30 \
+    --config_args=$args \
+    2>&1 | tee ${log} 
+
+  avg_time=`tail ${log} -n 1 | awk -F ' ' '{print $8}' | sed 's/avg=//'`
+  fps=`awk 'BEGIN{printf "%.2f",('$bs' / '$avg_time' * 1000)}'`
+  echo "FPS: $fps images/sec" 2>&1 | tee -a ${log}
+}
+
+if [ ! -f "train.list" ]; then
+  echo " " > train.list
+fi
+if [ ! -d "logs" ]; then
+  mkdir logs
+fi
+
+# training benchmark
+for batchsize in 64 128 256; do
+  train vgg 19 $batchsize
+  train resnet 50 $batchsize
+  train googlenet v1 $batchsize
+  train alexnet 2 $batchsize
+done

benchmark/paddle/image/vgg.py

@@ -7,13 +7,15 @@
 batch_size = get_config_arg('batch_size', int, 64)
 layer_num = get_config_arg('layer_num', int, 19)
 is_infer = get_config_arg("is_infer", bool, False)
+num_samples = get_config_arg('num_samples', int, 2560)
 
 args = {
     'height': height,
     'width': width,
     'color': True,
     'num_class': num_class,
-    'is_infer': is_infer
+    'is_infer': is_infer,
+    'num_samples': num_samples
 }
 define_py_data_sources2(
     "train.list" if not is_infer else None,

cmake/external/protobuf.cmake

@@ -253,9 +253,9 @@ IF(NOT PROTOBUF_FOUND)
     IF(WITH_C_API)
         INSTALL(DIRECTORY ${PROTOBUF_INCLUDE_DIR} DESTINATION third_party/protobuf)
         IF(ANDROID)
-            INSTALL(FILES ${PROTOBUF_LIBRARY} DESTINATION third_party/protobuf/lib/${ANDROID_ABI})
+            INSTALL(FILES ${PROTOBUF_LITE_LIBRARY} DESTINATION third_party/protobuf/lib/${ANDROID_ABI})
         ELSE()
-            INSTALL(FILES ${PROTOBUF_LIBRARY} DESTINATION third_party/protobuf/lib)
+            INSTALL(FILES ${PROTOBUF_LITE_LIBRARY} DESTINATION third_party/protobuf/lib)
         ENDIF()
     ENDIF()
 

doc/api/v2/config/layer.rst

@@ -467,7 +467,7 @@ lambda_cost
     :noindex:
 
 square_error_cost
---------
+-----------------
 ..  autoclass:: paddle.v2.layer.square_error_cost
     :noindex:
 
@@ -533,7 +533,7 @@ Miscs
 =====
 
 dropout
---------------
+--------
 ..  autoclass:: paddle.v2.layer.dropout
     :noindex: