Add tf2paddle to convert models

image_classification/tf2paddle/README.md

+## 使用说明
+
+`tf2paddle.py`提供了将TensorFlow训练的模型转换为PaddlePaddle可使用的模型的接口`TFModelConverter`，其封装了图像领域常用的Convolution、BatchNorm等layer的转换函数，可以完成VGG、ResNet等常用模型的转换。模型转换的基本过程是：基于TensorFlow的Python API获取variable，将各variable对应到PaddlePaddle中layer的参数，进行适配后序列化保存输出可以直接为PaddlePaddle的Python API加载使用的模型文件。
+
+为使TensorFlow模型中的variable能够正确对应到PaddlePaddle模型中layer的参数，正确完成转换，模型转换具有如下约束：
+
+- 支持TensorFlow中conv2d，batchnorm，fc这三种带有trainable variable的Operator中参数的转换。
- TensorFlow配置中同一Operator内的variable属于相同的scope，以此将variable划分到不同的layer。
+- conv2d、batchnorm、fc的scope需分别包含conv、bn、fc，以此获取对应layer的type；亦可以通过为`TFModelConverter`传入`layer_type_map`的`dict`，将scope映射到对应的layer type来规避此项约束。
+- conv2d、fc中variable的顺序为先weight后bias，batchnorm中variable的顺序为scale、shift、mean、var，以此将variable对应到layer中相应位置的参数。
+- TensorFlow网络拓扑顺序需和PaddlePaddle网络拓扑顺序一致，尤其注意具有分支时左右分支的顺序。这是针对模型转换和PaddlePaddle网络配置均使用PaddlePaddle默认参数命名的情况，此时将根据拓扑顺序进行参数命名；若PaddlePaddle网络配置中自定义了param的name，可以通过为`TFModelConverter`传入`layer_name_map`或`param_name_map`的`dict`，在模型转换时将variable的name映射为PaddlePaddle配置中param的name。
+
+此外，要求提供`build_model`接口以从此构建TensorFlow网络，加载模型并返回session。可参照如下示例：
+
+```python
+def build_model():
+    build_graph()
+    sess = tf.Session(config=tf.ConfigProto(allow_soft_placement=True))
+    sess.run(tf.tables_initializer())
+    saver = tf.train.Saver()
+    saver.restore(sess, 'model/model.ckpt')
+    return sess
+```
+
+在完成以上内容后，`TFModelConverter`使用如下：
+
+```python
+# 定义相关变量
+tf_net = "TF_ResNet50"                       # 提供build_model的module名
+paddle_tar_name = "Paddle_ResNet50.tar.gz"   # 输出的Paddle模型的文件名
+
+# 初始化并加载模型
+converter = TFModelConverter(tf_net=tf_net,
+                             paddle_tar_name=paddle_tar_name)
+# 进行模型转换
+converter.convert()
+```
+
+`tf2paddle.py`中已提供以上步骤，修改其中相关变量的值后执行`python tf2paddle.py`即可完成模型转换。
+
+此外，在使用转换得到的模型时需要注意：
+
+- 由于TensorFlow中的padding机制较为特殊，在编写PaddlePaddle网络配置时对conv这种需要padding的layer可能需要推算size后在conv外使用pad_layer进行padding。
- 与TensorFlow多使用NHWC的data_format不同，PaddlePaddle使用NCHW的输入数据。

image_classification/tf2paddle/tf2paddle.py

+import os
+import re
+import collections
+import struct
+import gzip
+import tarfile
+import cStringIO
+import numpy as np
+from paddle.proto.ParameterConfig_pb2 import ParameterConfig
+from paddle.trainer_config_helpers.default_decorators import wrap_name_default
+import tensorflow as tf
+
+
+class ModelConverter(object):
+    def __init__(self,
+                 paddle_tar_name,
+                 param_name_map=None,
+                 layer_name_map=None,
+                 layer_type_map=None):
+        self.tar_name = paddle_tar_name
+        self.param_name_map = param_name_map
+        self.layer_name_map = layer_name_map
+        self.layer_type_map = layer_type_map
+        self.params = dict()
+
+    def convert(self):
+        layers_params = self.arrange_layer_params()
+        for layer_name in layers_params.keys():
+            layer_params, layer_params_names, layer_type = layers_params[
+                layer_name]
+            if len(layer_params) > 0:
+                if not layer_type:
+                    assert layer_type_map and (
+                        layer_type_map.get(layer_name) in ["conv", "bn", "fc"])
+                    layer_type = layer_type_map[layer_name]
+                self.pre_layer_name = getattr(
+                    self, "convert_" + layer_type + "_layer")(
+                        layer_params,
+                        params_names=[
+                            self.param_name_map.get(name)
+                            if self.param_name_map else None
+                            for name in layer_params_names
+                        ],
+                        name=None if self.layer_name_map == None else
+                        self.layer_name_map.get(layer_name))
+        with gzip.open(self.tar_name, 'w') as f:
+            self.to_tar(f)
+        return
+
+    def to_tar(self, f):
+        tar = tarfile.TarFile(fileobj=f, mode='w')
+        for param_name in self.params.keys():
+            param_conf, param_data = self.params[param_name]
+
+            confStr = param_conf.SerializeToString()
+            tarinfo = tarfile.TarInfo(name="%s.protobuf" % param_name)
+            tarinfo.size = len(confStr)
+            buf = cStringIO.StringIO(confStr)
+            buf.seek(0)
+            tar.addfile(tarinfo, fileobj=buf)
+
+            buf = cStringIO.StringIO()
+            self.serialize(param_data, buf)
+            tarinfo = tarfile.TarInfo(name=param_name)
+            buf.seek(0)
+            tarinfo.size = len(buf.getvalue())
+            tar.addfile(tarinfo, buf)
+
+    @staticmethod
+    def serialize(data, f):
+        f.write(struct.pack("IIQ", 0, 4, data.size))
+        f.write(data.tobytes())
+
+
+class TFModelConverter(ModelConverter):
+    def __init__(self,
+                 tf_net,
+                 paddle_tar_name,
+                 param_name_map=None,
+                 layer_name_map=None,
+                 layer_type_map=None):
+        super(TFModelConverter, self).__init__(paddle_tar_name, param_name_map,
+                                               layer_name_map, layer_type_map)
+        self.sess = __import__(tf_net).build_model()
+
+    def arrange_layer_params(self):
+        all_vars = tf.global_variables()
+        layers_params = collections.OrderedDict()
+        for var in all_vars:
+            var_name = var.name
+            scope_pos = var_name.rfind('/')
+            if scope_pos != -1:
+                layer_scope = var_name[:scope_pos]
+                if layers_params.has_key(layer_scope):
+                    layer_params, layer_params_names, layer_type = layers_params[
+                        layer_scope]
+                    layer_params.append(var.eval(self.sess))
+                    layer_params_names.append(var_name)
+                else:
+                    layer_type = re.search('conv|bn|fc', layer_scope)
+                    layers_params[layer_scope] = ([var.eval(self.sess)],
+                                                  [var_name], layer_type.group()
+                                                  if layer_type else None)
+        return layers_params
+
+    @wrap_name_default("conv")
+    def convert_conv_layer(self, params, params_names=None, name=None):
+        for i in range(len(params)):
+            data = np.transpose(params[i], (3, 2, 0, 1))
+            if len(params) == 2:
+                suffix = "0" if i == 0 else "bias"
+                file_name = "_%s.w%s" % (name, suffix) if not (
+                    params_names and params_names[i]) else params_names[i]
+            else:
+                file_name = "_%s.w%s" % (name, str(i)) if not (
+                    params_names and params_names[i]) else params_names[i]
+            param_conf = ParameterConfig()
+            param_conf.name = file_name
+            dims = list(data.shape)
+            if len(dims) == 1:
+                dims.insert(1, 1)
+                param_conf.dims.extend(dims)
+            param_conf.size = reduce(lambda a, b: a * b, data.shape)
+            self.params[file_name] = (param_conf, data.flatten())
+
+    @wrap_name_default("fc_layer")
+    def convert_fc_layer(self, params, params_names=None, name=None):
+        for i in range(len(params)):
+            data = params[i]
+            if len(params) == 2:
+                suffix = "0" if i == 0 else "bias"
+                file_name = "_%s.w%s" % (name, suffix) if not (
+                    params_names and params_names[i]) else params_names[i]
+            else:
+                file_name = "_%s.w%s" % (name, str(i)) if not (
+                    params_names and params_names[i]) else params_names[i]
+            param_conf = ParameterConfig()
+            param_conf.name = file_name
+            dims = list(data.shape)
+            if len(dims) < 2:
+                dims.insert(0, 1)
+            param_conf.size = reduce(lambda a, b: a * b, dims)
+            param_conf.dims.extend(dims)
+            self.params[file_name] = (param_conf, data.flatten())
+        return name
+
+    @wrap_name_default("batch_norm")
+    def convert_bn_layer(self, params, params_names=None, name=None):
+        params = [params[i] for i in (0, 2, 3, 1)]
+        params_names = [params_names[i]
+                        for i in (0, 2, 3, 1)] if params_names else params_names
+        for i in range(len(params)):
+            data = params[i]
+            file_name = "_%s.w%s" % (name, str(i)) if i < 3 else "_%s.w%s" % (
+                name, "bias")
+            file_name = file_name if not (params_names and
+                                          params_names[i]) else params_names[i]
+            param_conf = ParameterConfig()
+            param_conf.name = file_name
+            dims = list(data.shape)
+            assert len(dims) == 1
+            dims.insert(0, 1)
+            param_conf.size = reduce(lambda a, b: a * b, dims)
+            param_conf.dims.extend(dims)
+            self.params[file_name] = (param_conf, data.flatten())
+        return name
+
+
+if __name__ == "__main__":
+    tf_net = "TF_ResNet"
+    paddle_tar_name = "Paddle_ResNet50.tar.gz"
+
+    converter = TFModelConverter(tf_net=tf_net, paddle_tar_name=paddle_tar_name)
+    converter.convert()