Merge pull request #6755 from tensor-tang/benchmark

use small samples to infer openblas

benchmark/paddle/image/googlenet.py

@@ -7,13 +7,15 @@ num_class = 1000
 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 @@ num_class = 1000
 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_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

benchmark/paddle/image/run_openblas_infer.sh

@@ -23,24 +23,25 @@ function infer() {
     echo "./run_mkl_infer.sh to save the model first"
     exit 0
   fi
-  log_period=$((256 / bs))
+  log_period=$((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=${layer_num},is_infer=True" \
+    --config_args="batch_size=${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 1280 samples,
+  # 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 $end`
-  fps=`awk 'BEGIN{printf "%.2f",(1280 / ('$end_sec' - '$start_sec'))}'`
-  echo "Last 1280 samples start: ${start}(${start_sec} sec), end: ${end}(${end_sec} sec;" >> ${log}
+  fps=`awk 'BEGIN{printf "%.2f",(160 / ('$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}
 }
 

benchmark/paddle/image/run_openblas_train.sh

@@ -12,10 +12,11 @@ function train() {
   config="${topology}.py"
   paddle train --job=time \
     --config=$config \
+    --use_mkldnn=False \
     --use_gpu=False \
     --trainer_count=$thread \
-    --log_period=10 \
-    --test_period=100 \
+    --log_period=3 \
+    --test_period=30 \
     --config_args=$args \
     2>&1 | tee ${log} 
 

benchmark/paddle/image/vgg.py

@@ -7,13 +7,15 @@ num_class = 1000
 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,