Port utils to Python3

python/paddle/utils/dump_config.py

@@ -37,9 +37,9 @@ if __name__ == '__main__':
     assert isinstance(conf, TrainerConfig_pb2.TrainerConfig)
 
     if whole_conf:
-        print conf
+        print(conf)
     else:
         if binary:
             sys.stdout.write(conf.model_config.SerializeToString())
         else:
-            print conf.model_config
+            print(conf.model_config)

python/paddle/utils/image_multiproc.py

@@ -15,7 +15,8 @@
 import os, sys
 import numpy as np
 from PIL import Image
-from cStringIO import StringIO
+import six
+from six.moves import cStringIO as StringIO
 import multiprocessing
 import functools
 import itertools
@@ -187,7 +188,8 @@ class PILTransformer(ImageTransformer):
         return self.transform(im)
 
 
-def job(is_img_string, transformer, (data, label)):
+def job(is_img_string, transformer, data_label_pack):
+    (data, label) = data_label_pack
     if is_img_string:
         return transformer.transform_from_string(data), label
     else:
@@ -273,4 +275,4 @@ class MultiProcessImageTransformer(object):
     def run(self, data, label):
         fun = functools.partial(job, self.is_img_string, self.transformer)
         return self.pool.imap_unordered(
-            fun, itertools.izip(data, label), chunksize=100 * self.procnum)
+            fun, six.moves.zip(data, label), chunksize=100 * self.procnum)

python/paddle/utils/image_util.py

@@ -14,7 +14,7 @@
 
 import numpy as np
 from PIL import Image
-from cStringIO import StringIO
+from six.moves import cStringIO as StringIO
 
 
 def resize_image(img, target_size):

python/paddle/utils/make_model_diagram.py

@@ -15,6 +15,9 @@
 # Generate dot diagram file for the given paddle model config
 # The generated file can be viewed using Graphviz (http://graphviz.org)
 
+from __future__ import print_function
+
+import six
 import sys
 import traceback
 
@@ -61,9 +64,9 @@ def make_diagram_from_proto(model_config, dot_file):
                                              name2id[mem.link_name])
         return s
 
-    print >> f, 'digraph graphname {'
-    print >> f, 'node [width=0.375,height=0.25];'
-    for i in xrange(len(model_config.layers)):
+    print('digraph graphname {', file=f)
+    print('node [width=0.375,height=0.25];', file=f)
+    for i in six.moves.xrange(len(model_config.layers)):
         l = model_config.layers[i]
         name2id[l.name] = i
 
@@ -71,12 +74,12 @@ def make_diagram_from_proto(model_config, dot_file):
     for sub_model in model_config.sub_models:
         if sub_model.name == 'root':
             continue
-        print >> f, 'subgraph cluster_%s {' % i
-        print >> f, 'style=dashed;'
+        print('subgraph cluster_%s {' % i, file=f)
+        print('style=dashed;', file=f)
         label = '%s ' % sub_model.name
         if sub_model.reversed:
             label += '<=='
-        print >> f, 'label = "%s";' % label
+        print('label = "%s";' % label, file=f)
         i += 1
         submodel_layers.add(sub_model.name)
         for layer_name in sub_model.layer_names:
@@ -84,37 +87,41 @@ def make_diagram_from_proto(model_config, dot_file):
             lid = name2id[layer_name]
             layer_config = model_config.layers[lid]
             label = make_layer_label(layer_config)
-            print >> f, 'l%s [label="%s", shape=box];' % (lid, label)
-        print >> f, '}'
+            print('l%s [label="%s", shape=box];' % (lid, label), file=f)
+        print('}', file=f)
 
-    for i in xrange(len(model_config.layers)):
+    for i in six.moves.xrange(len(model_config.layers)):
         l = model_config.layers[i]
         if l.name not in submodel_layers:
             label = make_layer_label(l)
-            print >> f, 'l%s [label="%s", shape=box];' % (i, label)
+            print('l%s [label="%s", shape=box];' % (i, label), file=f)
 
     for sub_model in model_config.sub_models:
         if sub_model.name == 'root':
             continue
         for link in sub_model.in_links:
-            print >> f, make_link(link)
+            print(make_link(link), file=f)
         for link in sub_model.out_links:
-            print >> f, make_link(link)
+            print(make_link(link), file=f)
         for mem in sub_model.memories:
-            print >> f, make_mem(mem)
+            print(make_mem(mem), file=f)
 
-    for i in xrange(len(model_config.layers)):
+    for i in six.moves.xrange(len(model_config.layers)):
         for l in model_config.layers[i].inputs:
-            print >> f, 'l%s -> l%s [label="%s"];' % (
-                name2id[l.input_layer_name], i, l.input_parameter_name)
+            print(
+                'l%s -> l%s [label="%s"];' % (name2id[l.input_layer_name], i,
+                                              l.input_parameter_name),
+                file=f)
 
-    print >> f, '}'
+    print('}', file=f)
     f.close()
 
 
 def usage():
-    print >> sys.stderr, ("Usage: python show_model_diagram.py" +
-                          " CONFIG_FILE DOT_FILE [config_str]")
+    print(
+        ("Usage: python show_model_diagram.py" +
+         " CONFIG_FILE DOT_FILE [config_str]"),
+        file=sys.stderr)
     exit(1)
 
 

python/paddle/utils/merge_model.py

@@ -70,4 +70,4 @@ def merge_v2_model(net, param_file, output_file):
         for pname in param_names:
             params.serialize(pname, f)
 
-    print 'Generate  %s  success!' % (output_file)
+    print('Generate  %s  success!' % (output_file))

python/paddle/utils/plotcurve.py

@@ -44,6 +44,7 @@ To use this script to generate plot for AvgCost, error:
    python plotcurve.py -i paddle.INFO -o figure.png AvgCost error
 """
 
+import six
 import sys
 import matplotlib
 # the following line is added immediately after import matplotlib
@@ -91,7 +92,7 @@ def plot_paddle_curve(keys, inputfile, outputfile, format='png',
         sys.stderr.write("No data to plot. Exiting!\n")
         return
     m = len(keys) + 1
-    for i in xrange(1, m):
+    for i in six.moves.xrange(1, m):
         pyplot.plot(
             x[:, 0],
             x[:, i],

python/paddle/utils/predefined_net.py

@@ -13,6 +13,7 @@
 # limitations under the License.
 
 import numpy as np
+import six
 import os
 from paddle.trainer.config_parser import *
 from paddle.utils.preprocess_img import \
@@ -112,7 +113,7 @@ def simple_conv_net(data_conf, is_color=False):
         num_classes: num of classes.
         is_color: whether the input images are color.
     """
-    for k, v in data_conf.iteritems():
+    for k, v in six.iteritems(data_conf):
         globals()[k] = v
     data_input, label_input, num_image_channels = \
         image_data_layers(image_size, num_classes, is_color, is_predict)
@@ -340,7 +341,7 @@ def small_vgg(data_conf, is_predict=False):
         num_classes: num of classes.
         is_color: whether the input images are color.
     """
-    for k, v in data_conf.iteritems():
+    for k, v in six.iteritems(data_conf):
         globals()[k] = v
     vgg_conv_net(image_size, num_classes,
                  num_layers=[2, 2, 3, 3],

python/paddle/utils/preprocess_img.py

@@ -17,9 +17,9 @@ import os
 import random
 import numpy as np
 import PIL.Image as Image
-import StringIO
-import preprocess_util
-from image_util import crop_img
+from six.moves import cStringIO as StringIO
+from . import preprocess_util
+from .image_util import crop_img
 
 
 def resize_image(img, target_size):
@@ -52,7 +52,7 @@ class DiskImage:
 
     def read_image(self):
         if self.img is None:
-            print "reading: " + self.path
+            print("reading: " + self.path)
             image = resize_image(Image.open(self.path), self.target_size)
             self.img = image
 
@@ -69,7 +69,7 @@ class DiskImage:
         convert the image into the paddle batch format.
         """
         self.read_image()
-        output = StringIO.StringIO()
+        output = StringIO()
         self.img.save(output, "jpeg")
         contents = output.getvalue()
         return contents
@@ -127,7 +127,7 @@ class ImageClassificationDatasetCreater(preprocess_util.DatasetCreater):
             image_path = items[0]
             label_name = items[1]
             if not label_name in label_set:
-                label_set[label_name] = len(label_set.keys())
+                label_set[label_name] = len(list(label_set.keys()))
             img = DiskImage(path=image_path, target_size=self.target_size)
             label = preprocess_util.Lablel(
                 label=label_set[label_name], name=label_name)
@@ -144,7 +144,7 @@ class ImageClassificationDatasetCreater(preprocess_util.DatasetCreater):
             return create_dataset_from_list(path)
         label_set = preprocess_util.get_label_set_from_dir(path)
         data = []
-        for l_name in label_set.keys():
+        for l_name in list(label_set.keys()):
             image_paths = preprocess_util.list_images(
                 os.path.join(path, l_name))
             for p in image_paths:

python/paddle/utils/preprocess_util.py

@@ -14,7 +14,7 @@
 
 import os
 import math
-import cPickle as pickle
+import six.moves.cPickle as pickle
 import random
 import collections
 
@@ -169,7 +169,7 @@ class Dataset:
             random.shuffle(keyvalue_indices[k])
 
         num_data_per_key_batch = \
-            math.ceil(num_per_batch / float(len(keyvalue_indices.keys())))
+            math.ceil(num_per_batch / float(len(list(keyvalue_indices.keys()))))
 
         if num_data_per_key_batch < 2:
             raise Exception("The number of data in a batch is too small")
@@ -182,8 +182,8 @@ class Dataset:
                 end_idx = int(
                     min(begin_idx + num_data_per_key_batch,
                         len(keyvalue_indices[k])))
-                print "begin_idx, end_idx"
-                print begin_idx, end_idx
+                print("begin_idx, end_idx")
+                print(begin_idx, end_idx)
                 for idx in range(begin_idx, end_idx):
                     permuted_data.append(self.data[keyvalue_indices[k][idx]])
                 keyvalue_readpointer[k] = end_idx
@@ -357,6 +357,6 @@ class DatasetCreater(object):
             data_batcher.create_batches_and_list(
                 self.output_path, self.train_list_name, self.test_list_name,
                 self.label_set_name)
-            self.num_classes = len(train_label_set.keys())
+            self.num_classes = len(list(train_label_set.keys()))
             self.create_meta_file(train_data)
         return out_path

python/paddle/utils/show_pb.py

@@ -15,6 +15,8 @@
 Show the content of proto buffer data file of PADDLE
 """
 
+from __future__ import print_function
+
 import os
 import sys
 from google.protobuf.internal.decoder import _DecodeVarint
@@ -39,7 +41,7 @@ def read_proto(file, message):
 
 
 def usage():
-    print >> sys.stderr, "Usage: python show_pb.py PROTO_DATA_FILE"
+    print("Usage: python show_pb.py PROTO_DATA_FILE", file=sys.stderr)
     exit(1)
 
 
@@ -50,8 +52,8 @@ if __name__ == '__main__':
     f = open(sys.argv[1])
     header = DataFormat.DataHeader()
     read_proto(f, header)
-    print header
+    print(header)
 
     sample = DataFormat.DataSample()
     while read_proto(f, sample):
-        print sample
+        print(sample)

python/paddle/utils/torch2paddle.py

@@ -24,7 +24,7 @@ import sys
 import struct
 import numpy as np
 import torchfile
-import cPickle as pickle
+import six.moves.cPickle as pickle
 import argparse
 
 
@@ -48,7 +48,7 @@ def save_net_parameters(layers, params, output_path):
         biases = params[i * 2 + 1]
         weight_file = os.path.join(output_path, '_%s.w0' % layers[i])
         biases_file = os.path.join(output_path, '_%s.wbias' % layers[i])
-        print "Saving for layer %s." % layers[i]
+        print("Saving for layer %s." % layers[i])
         save_layer_parameters(weight_file, [weight])
         save_layer_parameters(biases_file, biases)