未验证 提交 ad4d9651 编写于 作者: Y Yan Xu 提交者: GitHub

Merge pull request #13250 from Yancey1989/fix_dist_base

fix parallel run dist unit test
...@@ -104,7 +104,7 @@ def batch_images_from_tar(data_file, ...@@ -104,7 +104,7 @@ def batch_images_from_tar(data_file,
pickle.dump( pickle.dump(
output, output,
open('%s/batch_%d' % (out_path, file_id), 'wb'), open('%s/batch_%d' % (out_path, file_id), 'wb'),
protocol=pickle.HIGHEST_PROTOCOL) protocol=2)
file_id += 1 file_id += 1
data = [] data = []
labels = [] labels = []
...@@ -113,9 +113,7 @@ def batch_images_from_tar(data_file, ...@@ -113,9 +113,7 @@ def batch_images_from_tar(data_file,
output['label'] = labels output['label'] = labels
output['data'] = data output['data'] = data
pickle.dump( pickle.dump(
output, output, open('%s/batch_%d' % (out_path, file_id), 'wb'), protocol=2)
open('%s/batch_%d' % (out_path, file_id), 'wb'),
protocol=pickle.HIGHEST_PROTOCOL)
with open(meta_file, 'a') as meta: with open(meta_file, 'a') as meta:
for file in os.listdir(out_path): for file in os.listdir(out_path):
......
...@@ -55,6 +55,7 @@ class TestDistRunnerBase(object): ...@@ -55,6 +55,7 @@ class TestDistRunnerBase(object):
pserver_prog = t.get_pserver_program(args.current_endpoint) pserver_prog = t.get_pserver_program(args.current_endpoint)
startup_prog = t.get_startup_program(args.current_endpoint, startup_prog = t.get_startup_program(args.current_endpoint,
pserver_prog) pserver_prog)
place = fluid.CPUPlace() place = fluid.CPUPlace()
exe = fluid.Executor(place) exe = fluid.Executor(place)
exe.run(startup_prog) exe.run(startup_prog)
...@@ -147,6 +148,8 @@ def runtime_main(test_class): ...@@ -147,6 +148,8 @@ def runtime_main(test_class):
import paddle.compat as cpt import paddle.compat as cpt
import socket
from contextlib import closing
class TestDistBase(unittest.TestCase): class TestDistBase(unittest.TestCase):
...@@ -156,13 +159,19 @@ class TestDistBase(unittest.TestCase): ...@@ -156,13 +159,19 @@ class TestDistBase(unittest.TestCase):
def setUp(self): def setUp(self):
self._trainers = 2 self._trainers = 2
self._pservers = 2 self._pservers = 2
self._ps_endpoints = "127.0.0.1:9123,127.0.0.1:9124" self._ps_endpoints = "127.0.0.1:%s,127.0.0.1:%s" % (
self._find_free_port(), self._find_free_port())
self._python_interp = "python" self._python_interp = "python"
self._sync_mode = True self._sync_mode = True
self._mem_opt = False self._mem_opt = False
self._use_reduce = False self._use_reduce = False
self._setup_config() self._setup_config()
def _find_free_port(self):
with closing(socket.socket(socket.AF_INET, socket.SOCK_STREAM)) as s:
s.bind(('', 0))
return s.getsockname()[1]
def start_pserver(self, model_file, check_error_log): def start_pserver(self, model_file, check_error_log):
ps0_ep, ps1_ep = self._ps_endpoints.split(",") ps0_ep, ps1_ep = self._ps_endpoints.split(",")
ps_cmd = "%s %s --role pserver --endpoints %s --trainer_id 0 --current_endpoint %s --trainers %d --is_dist" ps_cmd = "%s %s --role pserver --endpoints %s --trainer_id 0 --current_endpoint %s --trainers %d --is_dist"
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册