Reduce test size to avoid GPU memory issue.

python/paddle/fluid/tests/unittests/CMakeLists.txt

@@ -29,6 +29,7 @@ function(py_test_modules TARGET_NAME)
 endfunction()
 
 # test time consuming OPs in a separate process for expliot parallism
+list(REMOVE_ITEM TEST_OPS test_parallel_executor)
 list(REMOVE_ITEM TEST_OPS test_warpctc_op)
 list(REMOVE_ITEM TEST_OPS test_dyn_rnn)
 list(REMOVE_ITEM TEST_OPS test_mul_op)
@@ -64,6 +65,7 @@ else()
 endif(WITH_FAST_BUNDLE_TEST)
 
 # tests with high overhead
+py_test_modules(test_parallel_executor MODULES test_parallel_executor)
 py_test_modules(test_warpctc_op MODULES test_warpctc_op ENVS FLAGS_warpctc_dir=${WARPCTC_LIB_DIR})
 py_test_modules(test_train_dyn_rnn MODULES test_dyn_rnn)
 py_test_modules(test_mul_op MODULES test_mul_op)

python/paddle/fluid/tests/unittests/test_parallel_executor.py

@@ -135,18 +135,18 @@ def bottleneck_block(input, num_filters, stride, cardinality, reduction_ratio):
     return fluid.layers.elementwise_add(x=short, y=scale, act='relu')
 
 
-def SE_ResNeXt152(batch_size=4):
+def SE_ResNeXt152Small(batch_size=2):
     img = fluid.layers.fill_constant(
         shape=[batch_size, 3, 224, 224], dtype='float32', value=0.0)
     label = fluid.layers.fill_constant(
         shape=[batch_size, 1], dtype='int64', value=0.0)
 
     conv = conv_bn_layer(
-        input=img, num_filters=64, filter_size=3, stride=2, act='relu')
+        input=img, num_filters=16, filter_size=3, stride=2, act='relu')
     conv = conv_bn_layer(
-        input=conv, num_filters=64, filter_size=3, stride=1, act='relu')
+        input=conv, num_filters=16, filter_size=3, stride=1, act='relu')
     conv = conv_bn_layer(
-        input=conv, num_filters=128, filter_size=3, stride=1, act='relu')
+        input=conv, num_filters=16, filter_size=3, stride=1, act='relu')
     conv = fluid.layers.pool2d(
         input=conv, pool_size=3, pool_stride=2, pool_padding=1, pool_type='max')
 
@@ -226,7 +226,7 @@ class TestMNIST(TestParallelExecutorBase):
     def setUpClass(cls):
         # Convert mnist to recordio file
         with fluid.program_guard(fluid.Program(), fluid.Program()):
-            reader = paddle.batch(mnist.train(), batch_size=32)
+            reader = paddle.batch(mnist.train(), batch_size=4)
             feeder = fluid.DataFeeder(
                 feed_list=[  # order is image and label
                     fluid.layers.data(
@@ -268,15 +268,15 @@ class TestResnet(TestParallelExecutorBase):
 
     def test_resnet(self):
         import functools
-        batch_size = 4
+        batch_size = 2
         self.check_network_convergence(
             functools.partial(
-                SE_ResNeXt152, batch_size=batch_size),
+                SE_ResNeXt152Small, batch_size=batch_size),
             iter=20,
             batch_size=batch_size)
         self.check_network_convergence(
             functools.partial(
-                SE_ResNeXt152, batch_size=batch_size),
+                SE_ResNeXt152Small, batch_size=batch_size),
             iter=20,
             batch_size=batch_size,
             allow_op_delay=True)