vgg16 support

tool/tf_export_model.py

@@ -31,7 +31,7 @@ import numpy
 
 with tf.Session() as sess:
     inputs = tf.placeholder(dtype=tf.float32,
-                            shape=[None, 224, 224, 3],
+                            shape=[None, None, None, 3],
                             name="inputs")
     logits, endpoint = vgg.vgg_16(inputs, num_classes=1000, is_training=False)
     load_model = slim.assign_from_checkpoint_fn(
@@ -45,4 +45,4 @@ with tf.Session() as sess:
     result = sess.run([output_tensor], {input_tensor: data})
     numpy.save("tensorflow.npy", numpy.array(result))
 
-    freeze_model(sess, ["vgg_16/fc8/squeezed"], "vgg16.pb")
+    freeze_model(sess, ["vgg_16/fc8/squeezed"], "vgg16_None.pb")

x2paddle/convert.py

@@ -15,13 +15,12 @@ from x2paddle.parser.tf_parser import TFParser
 from x2paddle.optimizer.tf_optimizer import TFGraphOptimizer
 from x2paddle.emitter.tf_emitter import TFEmitter
 
-parser = TFParser('/ssd2/Jason/github/X2Paddle/tool/vgg16.pb',
+parser = TFParser('/ssd2/Jason/github/X2Paddle/tool/vgg16_None.pb',
                   in_nodes=['inputs'],
                   out_nodes=['output_boxes'],
                   in_shapes=[[-1, 416, 416, 3]])
 
 optimizer = TFGraphOptimizer()
-optimizer.run(parser.tf_graph)
 #parser.tf_graph.print()
 
 emitter = TFEmitter(parser)

x2paddle/core/fluid_code.py

@@ -42,7 +42,8 @@ class Layer(object):
                                 ", ")
                 else:
                     in_list += (input.layer_name + ", ")
-            inlist = in_list.strip(", ") + "], "
+            in_list = in_list.strip(", ") + "], "
+            layer_code += in_list
         elif isinstance(self.inputs, dict):
             for key, input in self.inputs.items():
                 assert isinstance(

x2paddle/core/util.py

@@ -12,14 +12,50 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+from paddle.fluid.proto import framework_pb2
+import struct
+import math
+import os
+
 
 def string(param):
     return "\'{}\'".format(param)
 
 
-def get_same_padding(input_size, kernel_size, stride):
-    new_size = int(math.ceil(input_size * 1.0 / stride))
-    pad_size = (new_size - 1) * stride + filter_size - in_size
+def get_same_padding(in_size, kernel_size, stride):
+    new_size = int(math.ceil(in_size * 1.0 / stride))
+    pad_size = (new_size - 1) * stride + kernel_size - in_size
     pad0 = int(pad_size / 2)
     pad1 = pad_size - pad0
+
     return [pad0, pad1]
+
+
+def export_paddle_param(param, param_name, dir):
+    dtype_map = {
+        "int16": [framework_pb2.VarType.INT16, 'h'],
+        "int32": [framework_pb2.VarType.INT32, 'i'],
+        "int64": [framework_pb2.VarType.INT64, 'q'],
+        "float16": [framework_pb2.VarType.FP16, 'e'],
+        "float32": [framework_pb2.VarType.FP32, 'f'],
+        "float64": [framework_pb2.VarType.FP64, 'd']
+    }
+    shape = param.shape
+    if len(shape) == 0:
+        assert param.size == 1, "Unexpected situation happend!"
+        shape = [1]
+    print("param dtype:", param.dtype)
+    assert str(param.dtype) in dtype_map, "Unknown dtype of params."
+
+    fp = open(os.path.join(dir, param_name), 'wb')
+    fp.write(struct.pack('i', 0))
+    fp.write(struct.pack('L', 0))
+    fp.write(struct.pack('i', 0))
+    tensor_desc = framework_pb2.VarType.TensorDesc()
+    tensor_desc.data_type = dtype_map[str(param.dtype)][0]
+    tensor_desc.dims.extend(shape)
+    desc_size = tensor_desc.ByteSize()
+    fp.write(struct.pack('i', desc_size))
+    fp.write(tensor_desc.SerializeToString())
+    param.tofile(fp)
+    fp.close()

x2paddle/emitter/tf_emitter.py

@@ -16,6 +16,7 @@ from x2paddle.parser.tf_parser import TFGraph
 from x2paddle.core.emitter import Emitter
 from x2paddle.core.fluid_code import FluidCode
 from x2paddle.core.util import *
+import numpy
 
 
 class TFEmitter(Emitter):
@@ -26,6 +27,7 @@ class TFEmitter(Emitter):
         # attr_node is used to record nodes that
         # only for define attribute of op
         self.attr_node = list()
+        self.omit_nodes = list()
         self.weights = dict()
 
     def run(self):
@@ -39,10 +41,17 @@ class TFEmitter(Emitter):
 
         for i in range(len(self.graph.topo_sort)):
             node_name = self.graph.topo_sort[i]
+            if node_name in self.omit_nodes:
+                continue
             node = self.graph.get_node(node_name)
             for layer in node.fluid_code.layers:
                 print(layer.get_code())
 
+        for name, param in self.weights.items():
+            node = self.graph.get_node(name)
+            export_paddle_param(param, node.layer_name.replace('/', '_'),
+                                "params1")
+
     def Placeholder(self, node):
         shape = node.out_shapes[0]
         dtype = node.dtype
@@ -57,9 +66,6 @@ class TFEmitter(Emitter):
                                   param_attr=attr)
 
     def Const(self, node):
-        ## TODO
-        return
-
         shape = node.out_shapes[0]
         dtype = node.dtype
         value = node.value
@@ -79,11 +85,13 @@ class TFEmitter(Emitter):
                                   inputs=None,
                                   output=node,
                                   param_attr=attr)
+        self.weights[node.layer_name] = node.value
 
     def Transpose(self, node):
-        return
         input = self.graph.get_node(node.layer.input[0], copy=True)
         perm = self.graph.get_node(node.layer.input[1], copy=True)
+        assert perm.layer_type == "Const", "Perm of transpose OP should be Const"
+        del self.weights[perm.layer_name]
         perm.fluid_code.clear()
         perm = perm.value.tolist()
 
@@ -94,7 +102,6 @@ class TFEmitter(Emitter):
                                   param_attr=attr)
 
     def RealDiv(self, node):
-        return
         x = self.graph.get_node(node.layer.input[0], copy=True)
         y = self.graph.get_node(node.layer.input[1], copy=True)
         inputs = {'x': x, 'y': y}
@@ -104,7 +111,6 @@ class TFEmitter(Emitter):
                                   param_attr=None)
 
     def Relu(self, node):
-        return
         input = self.graph.get_node(node.layer.input[0], copy=True)
         node.fluid_code.add_layer("relu",
                                   inputs=input,
@@ -112,28 +118,24 @@ class TFEmitter(Emitter):
                                   param_attr=None)
 
     def Squeeze(self, node):
-        return
         input = self.graph.get_node(node.layer.input[0], copy=True)
         squeeze_dims = node.get_attr('squeeze_dims')
-        print(squeeze_dims)
-        attr = {'squeeze_dims': squeeze_dims}
+        attr = {'axes': squeeze_dims}
         node.fluid_code.add_layer("squeeze",
                                   inputs=input,
                                   output=node,
                                   param_attr=attr)
 
     def BiasAdd(self, node):
-        return
-        x = self.graph.get_node(node.layer.input[0], copy=True)
-        y = self.graph.get_node(node.layer.input[1], copy=True)
-        inputs = {'x': x, 'y': y}
+        input = self.graph.get_node(node.layer.input[0], copy=True)
+        bias = self.graph.get_node(node.layer.input[1], copy=True)
+        inputs = {'x': input, 'y': bias}
         node.fluid_code.add_layer("elementwise_add",
                                   inputs=inputs,
                                   output=node,
                                   param_attr=None)
 
     def Identity(self, node):
-        return
         input = self.graph.get_node(node.layer.input[0], copy=True)
         node.fluid_code.add_layer("assign",
                                   inputs=input,
@@ -141,99 +143,104 @@ class TFEmitter(Emitter):
                                   param_attr=None)
 
     def MaxPool(self, node):
-        return
         input = self.graph.get_node(node.layer.input[0], copy=True)
         in_shape = input.out_shapes[0]
         k_size = node.get_attr("ksize")
         strides = node.get_attr("strides")
         data_format = node.get_attr("data_format").decode()
         pad_mode = node.get_attr("padding").decode()
+        channel_first = data_format == "NCHW"
 
-        if data_format == "NHWC":
+        if not channel_first:
             attr = {"perm": [0, 3, 1, 2]}
             node.fluid_code.add_layer("transpose",
                                       inputs=input,
                                       output=node,
                                       param_attr=attr)
             in_shape = [in_shape[i] for i in [0, 3, 1, 2]]
-            k_size = [k_size[i] for i in [0, 3, 1, 2]]
             strides = [strides[i] for i in [0, 3, 1, 2]]
 
         if pad_mode == "SAME":
-            pad_h = get_same_padding(in_shape[2], k_size[2], strides[2])
-            pad_w = get_same_padding(in_shape[3], k_size[3], strides[3])
+            pad_h = get_same_padding(in_shape[2], k_size[0], strides[2])
+            pad_w = get_same_padding(in_shape[3], k_size[1], strides[3])
             pad_h = pad_h[0] + pad_h[1]
             pad_w = pad_w[0] + pad_w[1]
             attr = {"paddings": [0, pad_h, 0, pad_w], "pad_value": -10000.0}
-            node.fluid_code.add_layer("pad2d",
-                                      inputs=input,
+            if pad_h + pad_w != 0:
+                node.fluid_code.add_layer(
+                    "pad2d",
+                    inputs=input if channel_first else node,
                     output=node,
                     param_attr=attr)
         attr = {
             "pool_size": k_size[1:3],
             "pool_type": string("max"),
-            "pool_stride": strides[1:3]
+            "pool_stride": strides[2:4]
         }
         node.fluid_code.add_layer("pool2d",
-                                  inputs=input,
+                                  inputs=input if channel_first else node,
                                   output=node,
                                   param_attr=attr)
 
-        if data_format == "NHWC":
+        if not channel_first:
             attr = {"perm": [0, 2, 3, 1]}
+            node.fluid_code.add_layer("transpose",
+                                      inputs=node,
+                                      output=node,
+                                      param_attr=attr)
+
+    def Conv2D(self, node):
+        input = self.graph.get_node(node.layer.input[0], copy=True)
+        kernel = self.graph.get_node(node.layer.input[1], copy=True)
+        assert kernel.layer_type == "Const", "Kernel of Conv2D should be Const"
+        self.omit_nodes.append(kernel.layer_name)
+
+        in_shape = input.out_shapes[0]
+        k_size = kernel.out_shapes[0]
+        strides = node.get_attr("strides")
+        dilations = node.get_attr("dilations")
+        data_format = node.get_attr("data_format").decode()
+        pad_mode = node.get_attr("padding").decode()
+        channel_first = data_format == "NCHW"
+
+        if not channel_first:
+            self.weights[kernel.layer_name] = numpy.transpose(
+                kernel.value, (3, 2, 0, 1))
+            attr = {"perm": [0, 3, 1, 2]}
             node.fluid_code.add_layer("transpose",
                                       inputs=input,
                                       output=node,
                                       param_attr=attr)
+            in_shape = [in_shape[i] for i in [0, 3, 1, 2]]
+            strides = [strides[i] for i in [0, 3, 1, 2]]
+            dilations = [dilations[i] for i in [0, 3, 1, 2]]
 
+        if pad_mode == "SAME":
+            pad_h = get_same_padding(in_shape[2], k_size[0], strides[2])
+            pad_w = get_same_padding(in_shape[3], k_size[1], strides[3])
+            attr = {"paddings": pad_h + pad_w, "pad_value": 0.0}
+            if pad_h[0] + pad_h[1] + pad_w[0] + pad_w[1] != 0:
+                node.fluid_code.add_layer(
+                    "pad2d",
+                    inputs=input if channel_first else node,
+                    output=node,
+                    param_attr=attr)
+        attr = {
+            "bias_attr": False,
+            "param_attr": string(kernel.layer_name),
+            "num_filters": k_size[3],
+            "filter_size": k_size[0:2],
+            "stride": strides[2:4],
+            "dilation": dilations[2:4]
+        }
+        node.fluid_code.add_layer("conv2d",
+                                  inputs=input if channel_first else node,
+                                  output=node,
+                                  param_attr=attr)
 
-#    def Conv2D(self, node):
-#        input = self.graph.get_node(node.layer.input[0], copy=True)
-#        in_shape = input.out_shapes[0]
-#        k_size = node.get_attr("ksize")
-#        strides = node.get_attr("strides")
-#        dilations = node.get_attr("dilations")
-#        data_format = node.get_attr("data_format").decode()
-#        pad_mode = node.get_attr("padding").decode()
-#
-#        if data_format == "NHWC":
-#            attr = {"perm": [0, 3, 1, 2]}
-#            node.fluid_code.add_layer("transpose",
-#                                      inputs=input,
-#                                      output=node,
-#                                      param_attr=attr)
-#            in_shape = [in_shape[i] for i in [0, 3, 1, 2]]
-#            k_size = [k_size[i] for i in [0, 3, 1, 2]]
-#            strides = [strides[i] for i in [0, 3, 1, 2]]
-#            dilations = [dilations[i] for i in [0, 3, 1, 2]]
-#
-#        if pad_mode == "SAME":
-#            pad_h = get_same_padding(in_shape[2], k_size[2], strides[2])
-#            pad_w = get_same_padding(in_shape[3], k_size[3], strides[3])
-#            pad_h = pad_h[0] + pad_h[1]
-#            pad_w = pad_w[0] + pad_w[1]
-#            attr = {"paddings": pad_h+pad_w, "pad_value": 0.0}
-#            node.fluid_code.add_layer("pad2d",
-#                                inputs=input,
-#                                output=node,
-#                                param_attr=attr)
-#        attr = {
-#            "pool_stride": strides[1:3],
-#            "bias_attr": False,
-#            "param_attr":,
-#            "num_filters":,
-#            "filter_size":,
-#            "stride":,
-#            "dilation":
-#            }
-#        node.fluid_code.add_layer("conv2d",
-#                            inputs=input,
-#                            output=node,
-#                            param_attr=attr)
-#
-#        if data_format == "NHWC":
-#            attr = {"perm": [0, 2, 3, 1]}
-#            node.fluid_code.add_layer("transpose",
-#                                      inputs=input,
-#                                      output=node,
-#                                      param_attr=attr)
+        if not channel_first:
+            attr = {"perm": [0, 2, 3, 1]}
+            node.fluid_code.add_layer("transpose",
+                                      inputs=node,
+                                      output=node,
+                                      param_attr=attr)

x2paddle/optimizer/tf_optimizer.py

@@ -18,7 +18,7 @@ from x2paddle.parser.tf_parser import TFGraph
 
 class TFGraphOptimizer(object):
     def __init__(self):
-        self.identity_ops = ['Identity']
+        print("Doint Nothing")
 
     def remove_isolated_node(self, graph):
         # delete isolated nodes
@@ -30,8 +30,33 @@ class TFGraphOptimizer(object):
 
         graph.remove_node(node_name)
 
+    def remove_identity_node(self, graph):
+        identity_node = list()
+        for node_name, node in graph.node_map.items():
+            if node.layer_type == "Identity":
+                identity_node.append(node_name)
+
+        for node_name in identity_node:
+            node = graph.get_node(node_name)
+            # Remind: Only 1 input for Identity node
+            input_node = graph.get_node(node.inputs[0])
+
+            # remove identity node from graph
+            idx = input_node.outputs.index(node_name)
+            del input_node.outputs[idx]
+
+            output_names = node.outputs
+            for output_name in output_names:
+                output_node = graph.get_node(output_name)
+                idx = output_node.inputs.index(node_name)
+                output_node.inputs[idx] = input_node.layer_name
+
+            idx = graph.topo_sort.index(node_name)
+            del graph.topo_sort[idx]
+
     def run(self, graph):
         self.remove_isolated_node(graph)
+        self.remove_identity_node(graph)
 
 
 # TODO identity node remove
@@ -39,3 +64,7 @@ class TFGraphOptimizer(object):
 # TODO subgraph optimize
 
 # TODO compute optimize
+
+# activation merge
+
+# biasadd merge

x2paddle/parser/tf_parser.py

@@ -82,6 +82,7 @@ class TFGraphNode(GraphNode):
 class TFGraph(Graph):
     def __init__(self, model):
         super(TFGraph, self).__init__(model)
+        self.identity_map = dict()
 
     def build(self):
         for layer in self.model.node:
@@ -101,6 +102,52 @@ class TFGraph(Graph):
 
         super(TFGraph, self).build()
 
+        # tensorflow graph optimize
+        self._remove_isolated_node()
+        self._remove_identity_node()
+
+    def get_node(self, node_name, copy=False):
+        items = node_name.strip().split(':')
+        if items[0] in self.identity_map:
+            items[0] = self.identity_map[items[0]]
+        new_node_name = ":".join(items)
+        return super(TFGraph, self).get_node(new_node_name, copy)
+
+    def _remove_isolated_node(self):
+        # delete isolated nodes
+        isolated_nodes = list()
+        for node_name in self.node_map.keys():
+            if len(self.get_node(node_name).inputs) == 0 or len(
+                    self.get_node(node_name).outputs) == 0:
+                isolated_nodes.append(node_name)
+
+        self.remove_node(node_name)
+
+    def _remove_identity_node(self):
+        identity_node = list()
+        for node_name, node in self.node_map.items():
+            if node.layer_type == "Identity":
+                identity_node.append(node_name)
+
+        for node_name in identity_node:
+            node = self.get_node(node_name)
+            # Remind: Only 1 input for Identity node
+            input_node = self.get_node(node.inputs[0])
+
+            # remove identity node from graph
+            self.identity_map[node_name] = input_node.layer_name
+            idx = input_node.outputs.index(node_name)
+            del input_node.outputs[idx]
+
+            output_names = node.outputs
+            for output_name in output_names:
+                output_node = self.get_node(output_name)
+                idx = output_node.inputs.index(node_name)
+                output_node.inputs[idx] = input_node.layer_name
+
+            idx = self.topo_sort.index(node_name)
+            del self.topo_sort[idx]
+
 
 class TFParser(object):
     def __init__(self, pb_model, in_nodes=None, out_nodes=None, in_shapes=None):