"add elementwise_add more type"

paddle/operators/accuracy_op.h

@@ -45,9 +45,9 @@ class AccuracyKernel : public framework::OpKernel<T> {
     auto* correct = ctx.Output<Tensor>("Correct");
     auto* total = ctx.Output<Tensor>("Total");
 
-    float* correct_data = correct->mutable_data<float>(ctx.GetPlace());
-    int* accuracy_data = accuracy->mutable_data<int>(ctx.GetPlace());
+    int* correct_data = correct->mutable_data<int>(ctx.GetPlace());
     int* total_data = total->mutable_data<int>(ctx.GetPlace());
+    float* accuracy_data = accuracy->mutable_data<float>(ctx.GetPlace());
 
     const int64_t* indices_data = indices->data<int64_t>();
     const int64_t* label_data = label->data<int64_t>();

paddle/operators/elementwise_add_op.cc

@@ -34,7 +34,13 @@ REGISTER_OP(elementwise_add, ops::ElementwiseOp, ops::ElementwiseAddOpMaker,
             elementwise_add_grad, ops::ElementwiseOpGrad);
 REGISTER_OP_CPU_KERNEL(
     elementwise_add,
-    ops::ElementwiseAddKernel<paddle::platform::CPUPlace, float>);
+    ops::ElementwiseAddKernel<paddle::platform::CPUPlace, float>,
+    ops::ElementwiseAddKernel<paddle::platform::CPUPlace, double>,
+    ops::ElementwiseAddKernel<paddle::platform::CPUPlace, int>,
+    ops::ElementwiseAddKernel<paddle::platform::CPUPlace, int64_t>);
 REGISTER_OP_CPU_KERNEL(
     elementwise_add_grad,
-    ops::ElementwiseAddGradKernel<paddle::platform::CPUPlace, float>);
+    ops::ElementwiseAddGradKernel<paddle::platform::CPUPlace, float>,
+    ops::ElementwiseAddGradKernel<paddle::platform::CPUPlace, double>,
+    ops::ElementwiseAddGradKernel<paddle::platform::CPUPlace, int>,
+    ops::ElementwiseAddGradKernel<paddle::platform::CPUPlace, int64_t>);

python/paddle/v2/framework/evaluator.py

-from paddle.v2.framework.framework import Program, g_main_program, unique_name
-from paddle.v2.framework.layer_helper import LayerHelper
+from paddle.v2.framework.framework import Program, g_main_program, unique_name, Variable
 import paddle.v2.framework.core as core
 
 
+def _clone_var_in_block_(block, var):
+    assert isinstance(var, Variable)
+    return block.create_var(
+        name=var.name,
+        shape=var.shape,
+        dtype=var.data_type,
+        type=var.type,
+        lod_level=var.lod_level,
+        persistable=True)
+
+
 class Evaluator(object):
     """
     Evalutor Base class.
@@ -13,11 +23,24 @@ class Evaluator(object):
     """
 
     def __init__(self, name, **kwargs):
+        """
+        init the global states
+        """
         self._states = {}
-        if kwargs.has_key("program"):
-            self._program = kwargs.get("program")
+        if kwargs.has_key("main_program"):
+            self._main_program = kwargs.get("main_program")
+        else:
+            self._main_program = g_main_program
+        if kwargs.has_key("eval_program"):
+            self._eval_program = kwargs.get("eval_program")
         else:
-            self._program = g_main_program
+            self._eval_program = Program()
+
+    def _update_ops(self):
+        """
+        append update ops to the global states
+        """
+        raise NotImplementedError()
 
     def reset(self, executor, program=None):
         """
@@ -29,17 +52,20 @@ class Evaluator(object):
             reset_program = program
         block = reset_program.global_block()
         for k, var in self._states.iteritems():
-            zeros = block.create_var(dtype=var.data_type)
+            g_var = _clone_var_in_block_(block, var)
+            zeros = block.create_var(dtype="float32", persistable=True)
             block.append_op(
                 type="fill_constant",
                 outputs={"Out": [zeros]},
                 attrs={
-                    "shape": var.shape,
-                    "value": 0,
+                    "shape": g_var.shape,
+                    "value": .0,
+                    "data_type": 5,
                 })
             block.append_op(
-                type="scale", inputs={"X": zeros}, outputs={"Out": var})
-        executor.run(reset_program)
+                type="scale", inputs={"X": zeros}, outputs={"Out": g_var})
+        print reset_program
+        executor.run(reset_program, fetch_list=self._states.values())
 
     def eval(self, executor, program=None):
         """
@@ -53,15 +79,16 @@ class Accuracy(Evaluator):
     Accuracy need two state variable Total, Correct
     """
 
-    def __init__(self, input, label, k=1, **kwargs):
+    def __init__(self, *args, **kwargs):
         super(Accuracy, self).__init__("accuracy", **kwargs)
-        block = self._program.global_block()
+        # block = self._eval_program.global_block()
+        block = self._main_program.global_block()
         g_total = block.create_var(
             name=unique_name("Total"),
             persistable=True,
             dtype="int64",
             shape=[1])
-        g_correct = helper.create_global_variable(
+        g_correct = block.create_var(
             name=unique_name("Correct"),
             persistable=True,
             dtype="int64",
@@ -69,6 +96,8 @@ class Accuracy(Evaluator):
         self._states["Total"] = g_total
         self._states["Correct"] = g_correct
 
+    def _update_ops(self, input, label, k=1, **kwargs):
+        block = self._main_program.global_block()
         topk_out = block.create_var(dtype=input.data_type)
         topk_indices = block.create_var(dtype="int64")
         block.append_op(
@@ -77,8 +106,9 @@ class Accuracy(Evaluator):
             outputs={"Out": [topk_out],
                      "Indices": [topk_indices]},
             attrs={"k": k})
-        acc_out_dtype = kwargs.get("out_dtype", "float32")
-        acc_out = block.create_var(dtype=acc_out_dtype)
+        acc_out = block.create_var(dtype=kwargs.get("out_dtype", "float32"))
+        correct = block.create_var(dtype="int64", persistable=True)
+        total = block.create_var(dtype="int64", persistable=True)
         block.append_op(
             type="accuracy",
             inputs={
@@ -92,39 +122,121 @@ class Accuracy(Evaluator):
                 "Total": [total],
             })
 
+        # block = self._eval_program.global_block()
+        # e_correct = _clone_var_in_block_(block, correct)
+        # e_total = _clone_var_in_block_(block, total)
+
+        # block.append_op(
+        #     type="sum",
+        #     inputs={"X": [self._states["Total"], total]},
+        #     outputs={"Out": [self._states["Total"]]})
+        block.append_op(
+            type="cast",
+            inputs={"X": [self._states["Total"]]},
+            outputs={"Out": [self._states["Total"]]},
+            attrs={
+                "in_data_type": 5,
+                "out_data_type": 2,
+            })
+        block.append_op(
+            type="cast",
+            inputs={"X": [self._states["Correct"]]},
+            outputs={"Out": [self._states["Correct"]]},
+            attrs={
+                "in_data_type": 5,
+                "out_data_type": 2,
+            })
+
         block.append_op(
-            type="sum",
-            inputs={"X": [g_total, total]},
-            outputs={"Out": [g_total]})
+            type="elementwise_add",
+            inputs={"X": [self._states["Total"]],
+                    "Y": [total]},
+            outputs={"Out": [self._states["Total"]]})
         block.append_op(
-            type="sum",
-            inputs={"X": [g_correct, correct]},
-            outputs={"Out": [g_total]})
+            type="elementwise_add",
+            inputs={"X": [self._states["Correct"]],
+                    "Y": [correct]},
+            outputs={"Out": [self._states["Correct"]]})
+
+        # g_total = self._states["Total"]
+        # print g_total
+        # print total
+
+        # print "*" * 100
+        # print g_total.block.program == total.block.program
+
+        # g_total = _clone_var_in_block_(block, self._states["Total"])
+        # e_total = _clone_var_in_block_(block, total)
+
+        # block.append_op(
+        #     type="sum",
+        #     inputs={"X": [g_total, e_total]},
+        #     outputs={"Out": [g_total]})
+
+        # block.append_op(
+        #     type="sum",
+        #     inputs={"X": [self._states["Correct"], correct]},
+        #     outputs={"Out": [self._states["Correct"]]})
+        # print self._main_program
         return acc_out
 
-    def eval(self, executor, program=None):
-        if program == None:
-            eval_program = Program()
-        else:
-            eval_program = program
-        block = eval_program.global_block()
-        eval_out = block.create_var(dtype=self._helper.input_dtype())
+    def eval(self, executor):
+        block = self._eval_program.global_block()
+        eval_out = block.create_var(dtype=self._states["Total"].data_type)
+        e_correct = _clone_var_in_block_(block, correct)
+        e_total = _clone_var_in_block_(block, total)
+        # block.append_op(
+        #     type="elementwise_div",
+        #     inputs={"X": self._states["Total"],
+        #             "Y": self._states["Correct"]},
+        #     outputs={"Out": eval_out})
         block.append_op(
             type="elementwise_div",
-            inputs={"X": self._states["Total"],
-                    "Y": self._states["Correct"]},
+            inputs={"X": e_total,
+                    "Y": e_correct},
             outputs={"Out": eval_out})
-        return executor.run(eval_program, fetch_list=[eval_out])
+        return executor.run(self._eval_program, fetch_list=[eval_out])
 
 
-# Demo for composing low level op to compute the F1 metric
-class F1(Evaluator):
-    def __init__(self, input, label, **kwargs):
-        super(F1, self).__init__("F1", **kwargs)
-        g_tp = helper.create_global_variable(
+# Demo for composing low level ops to compute the F1 metric
+class FScore(Evaluator):
+    def __init__(self, input, label, beta=1.0, **kwargs):
+        super(F1, self).__init__("FScore", **kwargs)
+        block = self._program.global_block()
+        g_tp = block.create_var(
             name=unique_name("Tp"), persistable=True, dtype="int64", shape=[1])
-        g_fp = helper.create_global_variable(
+        g_fn = block.create_var(
+            name=unique_name("Fn"), persistable=True, dtype="int64", shape=[1])
+        g_fp = block.create_var(
             name=unique_name("Fp"), persistable=True, dtype="int64", shape=[1])
 
         self._states["Tp"] = g_tp
         self._states["Fp"] = g_fp
+        self._states["Fn"] = g_fn
+
+    def _update_ops(self):
+        block = self._program.global_block()
+        equal_out = block.create_var()
+        block.append_op(
+            type="equal",
+            inputs={"X": [input],
+                    "Y": [label]},
+            outputs={"Out": equal_out})
+
+        positive = block.create_var()
+        block.append_op(
+            type="sequence_pool",
+            inputs={"X": [equal_out]},
+            outputs={"Out": positive},
+            attrs={"pooltype": "SUM"})
+        batch = block.create_var(
+            name=feed_var_name,
+            type=core.VarDesc.VarType.FEED_MINIBATCH,
+            persistable=True)
+
+
+# def register():
+accuracy = Accuracy
+# def accuracy(*args, **kwargs):
+#     acc = Accuracy(**kwargs)
+#     return acc._update_ops(*args, **kwargs)

python/paddle/v2/framework/framework.py

@@ -550,7 +550,7 @@ class Parameter(Variable):
                 raise ValueError("Parameter shape should not be related with "
                                  "batch-size")
 
-        super(Parameter, self).__init__(
+        Variable.__init__(
             self, block, persistable=True, shape=shape, dtype=dtype, **kwargs)
         self.trainable = kwargs.get('trainable', True)
 

python/paddle/v2/framework/layers.py

@@ -263,7 +263,9 @@ def accuracy(input, label, k=1, **kwargs):
                  "Indices": [topk_indices]},
         attrs={"k": k})
     acc_out_dtype = kwargs.get("out_dtype", "float32")
-    acc_out = helper.create_tmp_variable(dtype=acc_out_dtype)
+    acc_out = helper.create_tmp_variable(dtype="float32")
+    correct = helper.create_tmp_variable(dtype="int64")
+    total = helper.create_tmp_variable(dtype="int64")
     helper.append_op(
         type="accuracy",
         inputs={
@@ -271,7 +273,11 @@ def accuracy(input, label, k=1, **kwargs):
             "Indices": [topk_indices],
             "Label": [label]
         },
-        outputs={"Accuracy": [acc_out]})
+        outputs={
+            "Accuracy": [acc_out],
+            "Correct": [correct],
+            "Total": [total],
+        })
     return acc_out
 
 

python/paddle/v2/framework/tests/test_accuracy_op.py

@@ -19,7 +19,8 @@ class TestAccuracyOp(OpTest):
                     break
         self.outputs = {
             'Accuracy': np.array([num_correct / float(n)]).astype("float32"),
-            'Correct': np.array([num_correct]).astype("int32")
+            'Correct': np.array([num_correct]).astype("int32"),
+            'Total': np.array([n]).astype("int32")
         }
 
     def test_check_output(self):
@@ -27,5 +28,4 @@ class TestAccuracyOp(OpTest):
 
 
 if __name__ == '__main__':
-    exit(0)
     unittest.main()

python/paddle/v2/framework/tests/test_recognize_digits_conv.py

@@ -3,6 +3,7 @@ import paddle.v2.framework.layers as layers
 import paddle.v2.framework.nets as nets
 import paddle.v2.framework.core as core
 import paddle.v2.framework.optimizer as optimizer
+import paddle.v2.framework.evaluator as evaluator
 
 from paddle.v2.framework.framework import Program, g_main_program
 from paddle.v2.framework.executor import Executor
@@ -54,17 +55,24 @@ cost = layers.cross_entropy(
     main_program=main_program,
     startup_program=startup_program)
 avg_cost = layers.mean(x=cost, main_program=main_program)
-accuracy = layers.accuracy(
-    input=predict,
-    label=label,
-    main_program=main_program,
-    startup_program=startup_program)
-
+# accuracy = layers.accuracy(
+#     input=predict,
+#     label=label,
+#     main_program=main_program,
+#     startup_program=startup_program)
 # optimizer = optimizer.MomentumOptimizer(learning_rate=0.1 / 128.0,
 # momentum=0.9)
 optimizer = optimizer.AdamOptimizer(learning_rate=0.01, beta1=0.9, beta2=0.999)
 opts = optimizer.minimize(avg_cost, startup_program)
 
+accuracy = evaluator.accuracy(
+    input=predict,
+    label=label,
+    main_program=main_program,
+    startup_program=startup_program)
+acc_out = accuracy._update_ops(
+    input=predict, label=label, main_program=main_program)
+
 BATCH_SIZE = 50
 PASS_NUM = 3
 train_reader = paddle.batch(
@@ -79,6 +87,7 @@ exe.run(startup_program, feed={}, fetch_list=[])
 
 for pass_id in range(PASS_NUM):
     count = 0
+    accuracy.reset(exe)
     for data in train_reader():
         img_data = np.array(map(lambda x: x[0].reshape([1, 28, 28]),
                                 data)).astype("float32")
@@ -93,11 +102,14 @@ for pass_id in range(PASS_NUM):
         outs = exe.run(main_program,
                        feed={"pixel": tensor_img,
                              "label": tensor_y},
-                       fetch_list=[avg_cost, accuracy])
+                       fetch_list=[avg_cost, acc_out])
         loss = np.array(outs[0])
         acc = np.array(outs[1])
+        # pass_acc = accuracy.eval(exe)
+        # print pass_acc
+        print loss, acc
 
-        if loss < 10.0 and acc > 0.9:
-            # if avg cost less than 10.0 and accuracy is larger than 0.9, we think our code is good.
-            exit(0)
+        # if loss < 10.0 and acc > 0.9:
+        #     # if avg cost less than 10.0 and accuracy is larger than 0.9, we think our code is good.
+        #     exit(0)
 exit(1)