Merge pull request #13223 from velconia/open_python35_CI

Open python35 ci

paddle/fluid/operators/fake_quantize_op.cu

@@ -119,7 +119,8 @@ struct FindRangeAbsMaxFunctor<platform::CUDADeviceContext, T> {
                   const framework::Tensor& last_scale,
                   const framework::Tensor& iter, const int window_size,
                   framework::Tensor* scales_arr, framework::Tensor* out_scale) {
-    auto& gpu_place = boost::get<platform::CUDAPlace>(ctx.GetPlace());
+    const auto gpu_place = boost::get<platform::CUDAPlace>(ctx.GetPlace());
+
     T* scale_arr = scales_arr->mutable_data<T>(gpu_place);
     T* out_scale_data = out_scale->mutable_data<T>(gpu_place);
 

paddle/scripts/paddle_build.sh

@@ -115,6 +115,7 @@ function cmake_gen() {
         -DWITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF}
         -DCMAKE_EXPORT_COMPILE_COMMANDS=ON
         -DWITH_CONTRIB=${WITH_CONTRIB:-ON}
+        -DWITH_INFERENCE=${WITH_INFERENCE:-ON}
         -DWITH_ANAKIN=${WITH_ANAKIN:-OFF}
         -DPY_VERSION=${PY_VERSION:-2.7}
     ========================================
@@ -144,6 +145,7 @@ EOF
         -DWITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} \
         -DCMAKE_EXPORT_COMPILE_COMMANDS=ON \
         -DWITH_CONTRIB=${WITH_CONTRIB:-ON} \
+        -DWITH_INFERENCE=${WITH_INFERENCE:-ON} \
         -DWITH_ANAKIN=${WITH_ANAKIN:-OFF} \
         -DPY_VERSION=${PY_VERSION:-2.7}
 }

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

@@ -36,6 +36,7 @@ import paddle.fluid as fluid
 import paddle.fluid.layers as layers
 from paddle.fluid import core
 from test_dist_base import TestDistRunnerBase, runtime_main
+import paddle.compat as cpt
 from paddle.compat import long_type
 
 import hashlib
@@ -315,8 +316,9 @@ def pad_batch_data(insts,
     """
     return_list = []
     max_len = max(len(inst) for inst in insts)
-    num_token = reduce(lambda x, y: x + y,
-                       [len(inst) for inst in insts]) if return_num_token else 0
+    num_token = six.moves.reduce(
+        lambda x, y: x + y,
+        [len(inst) for inst in insts]) if return_num_token else 0
     # Any token included in dict can be used to pad, since the paddings' loss
     # will be masked out by weights and make no effect on parameter gradients.
     inst_data = np.array(
@@ -328,7 +330,7 @@ def pad_batch_data(insts,
         return_list += [inst_weight.astype("float32").reshape([-1, 1])]
     else:  # position data
         inst_pos = np.array([
-            range(1, len(inst) + 1) + [0] * (max_len - len(inst))
+            list(range(1, len(inst) + 1)) + [0] * (max_len - len(inst))
             for inst in insts
         ])
         return_list += [inst_pos.astype("int64").reshape([-1, 1])]
@@ -385,10 +387,11 @@ def prepare_batch_input(insts, data_input_names, src_pad_idx, trg_pad_idx,
         return_num_token=True)
 
     data_input_dict = dict(
-        zip(data_input_names, [
-            src_word, src_pos, src_slf_attn_bias, trg_word, trg_pos,
-            trg_slf_attn_bias, trg_src_attn_bias, lbl_word, lbl_weight
-        ]))
+        list(
+            zip(data_input_names, [
+                src_word, src_pos, src_slf_attn_bias, trg_word, trg_pos,
+                trg_slf_attn_bias, trg_src_attn_bias, lbl_word, lbl_weight
+            ])))
     return data_input_dict, np.asarray([num_token], dtype="float32")
 
 
@@ -561,7 +564,7 @@ def train_loop(exe, train_progm, dev_count, sum_cost, avg_cost, lr_scheduler,
                         np.log(TrainTaskConfig.label_smooth_eps / (
                             ModelHyperParams.trg_vocab_size - 1) + 1e-20))
     init = False
-    for pass_id in xrange(TrainTaskConfig.pass_num):
+    for pass_id in six.moves.xrange(TrainTaskConfig.pass_num):
         pass_start_time = time.time()
         for batch_id, data in enumerate(train_data()):
             if batch_id >= 5:
@@ -587,11 +590,11 @@ def train_loop(exe, train_progm, dev_count, sum_cost, avg_cost, lr_scheduler,
                     ModelHyperParams.eos_idx, ModelHyperParams.n_head,
                     ModelHyperParams.d_model)
                 total_num_token += num_token
-                feed_kv_pairs = data_input_dict.items()
+                feed_kv_pairs = list(data_input_dict.items())
                 if TrainTaskConfig.local:
-                    feed_kv_pairs += {
+                    feed_kv_pairs += list({
                         lr_scheduler.learning_rate.name: lr_rate
-                    }.items()
+                    }.items())
                 feed_list.append(dict(feed_kv_pairs))
 
                 if not init:
@@ -873,6 +876,7 @@ class DataReader(object):
 
             f = tarfile.open(fpaths[0], "r")
             for line in f.extractfile(tar_fname):
+                line = cpt.to_text(line)
                 fields = line.strip("\n").split(self._field_delimiter)
                 if (not self._only_src and len(fields) == 2) or (
                         self._only_src and len(fields) == 1):
@@ -882,8 +886,9 @@ class DataReader(object):
                 if not os.path.isfile(fpath):
                     raise IOError("Invalid file: %s" % fpath)
 
-                with open(fpath, "r") as f:
+                with open(fpath, "rb") as f:
                     for line in f:
+                        line = cpt.to_text(line)
                         fields = line.strip("\n").split(self._field_delimiter)
                         if (not self._only_src and len(fields) == 2) or (
                                 self._only_src and len(fields) == 1):
@@ -892,8 +897,9 @@ class DataReader(object):
     @staticmethod
     def load_dict(dict_path, reverse=False):
         word_dict = {}
-        with open(dict_path, "r") as fdict:
+        with open(dict_path, "rb") as fdict:
             for idx, line in enumerate(fdict):
+                line = cpt.to_text(line)
                 if reverse:
                     word_dict[idx] = line.strip("\n")
                 else:
@@ -1034,7 +1040,7 @@ def multi_head_attention(queries,
         # size of the input as the output dimension size.
         return layers.reshape(
             x=trans_x,
-            shape=map(int, [0, 0, trans_x.shape[2] * trans_x.shape[3]]))
+            shape=list(map(int, [0, 0, trans_x.shape[2] * trans_x.shape[3]])))
 
     def scaled_dot_product_attention(q, k, v, attn_bias, d_model, dropout_rate):
         """

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

@@ -16,6 +16,7 @@ from __future__ import print_function
 
 import unittest
 import numpy as np
+import six
 from op_test import OpTest
 
 
@@ -62,17 +63,20 @@ class PReluTest(OpTest):
 
 
 # TODO(minqiyang): Resume these test cases after fixing Python3 CI job issues
-#  class TestCase1(PReluTest):
-#  def initTestCase(self):
-#  self.attrs = {'mode': "all"}
+if six.PY2:
 
-#  class TestCase2(PReluTest):
-#  def initTestCase(self):
-#  self.attrs = {'mode': "channel"}
+    class TestCase1(PReluTest):
+        def initTestCase(self):
+            self.attrs = {'mode': "all"}
+
+    class TestCase2(PReluTest):
+        def initTestCase(self):
+            self.attrs = {'mode': "channel"}
+
+    class TestCase3(PReluTest):
+        def initTestCase(self):
+            self.attrs = {'mode': "element"}
 
-#  class TestCase3(PReluTest):
-#  def initTestCase(self):
-#  self.attrs = {'mode': "element"}
 
 if __name__ == "__main__":
     unittest.main()

python/paddle/fluid/transpiler/details/program_utils.py

@@ -153,7 +153,7 @@ def block_to_code(block, block_idx):
 
     indent += 1
     # sort all vars
-    all_vars = sorted(block.vars.iteritems(), key=lambda x: x[0])
+    all_vars = sorted(six.iteritems(block.vars), key=lambda x: x[0])
     for var in all_vars:
         print("{}{}".format(get_indent_space(indent), variable_to_code(var[1])))
 

python/paddle/fluid/transpiler/distribute_transpiler.py

@@ -300,7 +300,7 @@ class DistributeTranspiler(object):
             input_deps = grad_name_to_send_dummy_out.values()
             program.global_block().append_op(
                 type="send_barrier",
-                inputs={"X": input_deps},
+                inputs={"X": list(input_deps)},
                 outputs={"Out": send_barrier_out},
                 attrs={
                     "endpoints": pserver_endpoints,
@@ -401,7 +401,7 @@ class DistributeTranspiler(object):
 
         Args:
             recv_vars (list): Variable list to recv for current trainer_id
-            eplist (list): A list of strings indicating 
+            eplist (list): A list of strings indicating
 
         Returns:
             Program: trainer side startup program.
@@ -455,7 +455,7 @@ class DistributeTranspiler(object):
             if len(splited_var) <= 1:
                 continue
             # NOTE: if enable memory optimization, origin vars maybe removed.
-            if startup_program.global_block().vars.has_key(varname):
+            if varname in startup_program.global_block().vars:
                 orig_param = startup_program.global_block().vars[varname]
             else:
                 origin_param_var = self.origin_program.global_block().vars[
@@ -690,7 +690,7 @@ class DistributeTranspiler(object):
 
         Args:
             endpoint (str): current pserver endpoint.
-        
+
         Returns:
             tuple: (main_program, startup_program), of type "Program"
         """
@@ -713,7 +713,7 @@ class DistributeTranspiler(object):
             endpoint (str): current pserver endpoint.
             pserver_program (Program): deprecated, call get_pserver_program first.
             startup_program (Program): deprecated, should pass startup_program
-                when initalizing 
+                when initalizing
 
         Returns:
             Program: parameter server side startup program.