m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

"add elementwise op support"

Browse Source
mobile_baidu
Dong Zhihong 7 years ago
parent b8f557f283
commit 46c61b35f7
5 changed files with 71 additions and 78 deletions
Show Stats Download Patch File Download Diff File

10
paddle/operators/elementwise_div_op.cc
Unescape View File

@ -35,7 +35,13 @@ REGISTER_OP(elementwise_div, ops::ElementwiseOp, ops::ElementwiseDivOpMaker,
elementwise_div_grad, ops::ElementwiseOpGrad);
REGISTER_OP_CPU_KERNEL(
elementwise_div,
ops::ElementwiseDivKernel<paddle::platform::CPUPlace, float>);
ops::ElementwiseDivKernel<paddle::platform::CPUPlace, float>,
ops::ElementwiseDivKernel<paddle::platform::CPUPlace, double>,
ops::ElementwiseDivKernel<paddle::platform::CPUPlace, int>,
ops::ElementwiseDivKernel<paddle::platform::CPUPlace, int64_t>);
REGISTER_OP_CPU_KERNEL(
elementwise_div_grad,
ops::ElementwiseDivGradKernel<paddle::platform::CPUPlace, float>);
ops::ElementwiseDivGradKernel<paddle::platform::CPUPlace, float>,
ops::ElementwiseDivGradKernel<paddle::platform::CPUPlace, double>,
ops::ElementwiseDivGradKernel<paddle::platform::CPUPlace, int>,
ops::ElementwiseDivGradKernel<paddle::platform::CPUPlace, int64_t>);

8
paddle/operators/elementwise_mul_op.cc
Unescape View File

@ -37,8 +37,12 @@ REGISTER_OP(elementwise_mul, ops::ElementwiseOp, ops::ElementwiseMulOpMaker,
REGISTER_OP_CPU_KERNEL(
elementwise_mul,
ops::ElementwiseMulKernel<paddle::platform::CPUPlace, float>,
ops::ElementwiseMulKernel<paddle::platform::CPUPlace, double>);
ops::ElementwiseMulKernel<paddle::platform::CPUPlace, double>,
ops::ElementwiseMulKernel<paddle::platform::CPUPlace, int>,
ops::ElementwiseMulKernel<paddle::platform::CPUPlace, int64_t>);
REGISTER_OP_CPU_KERNEL(
elementwise_mul_grad,
ops::ElementwiseMulGradKernel<paddle::platform::CPUPlace, float>,
ops::ElementwiseMulGradKernel<paddle::platform::CPUPlace, double>);
ops::ElementwiseMulGradKernel<paddle::platform::CPUPlace, double>,
ops::ElementwiseMulGradKernel<paddle::platform::CPUPlace, int>,
ops::ElementwiseMulGradKernel<paddle::platform::CPUPlace, int64_t>);

10
paddle/operators/elementwise_sub_op.cc
Unescape View File

@ -34,7 +34,13 @@ REGISTER_OP(elementwise_sub, ops::ElementwiseOp, ops::ElementwiseSubOpMaker,
elementwise_sub_grad, ops::ElementwiseOpGrad);
REGISTER_OP_CPU_KERNEL(
elementwise_sub,
ops::ElementwiseSubKernel<paddle::platform::CPUPlace, float>);
ops::ElementwiseSubKernel<paddle::platform::CPUPlace, float>,
ops::ElementwiseSubKernel<paddle::platform::CPUPlace, double>,
ops::ElementwiseSubKernel<paddle::platform::CPUPlace, int>,
ops::ElementwiseSubKernel<paddle::platform::CPUPlace, int64_t>);
REGISTER_OP_CPU_KERNEL(
elementwise_sub_grad,
ops::ElementwiseSubGradKernel<paddle::platform::CPUPlace, float>);
ops::ElementwiseSubGradKernel<paddle::platform::CPUPlace, float>,
ops::ElementwiseSubGradKernel<paddle::platform::CPUPlace, double>,
ops::ElementwiseSubGradKernel<paddle::platform::CPUPlace, int>,
ops::ElementwiseSubGradKernel<paddle::platform::CPUPlace, int64_t>);

95
python/paddle/v2/framework/evaluator.py
Unescape View File

@ -1,3 +1,4 @@
import numpy as np
from paddle.v2.framework.framework import Program, g_main_program, unique_name, Variable
import paddle.v2.framework.core as core
@ -31,12 +32,8 @@ class Evaluator(object):
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._eval_program = Program()
def _update_ops(self):
def _update_ops(self, *args, **kwargs):
"""
append update ops to the global states
"""
@ -64,13 +61,12 @@ class Evaluator(object):
})
block.append_op(
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):
"""
Merge the mini-batch statistics to form the evaluation result for multiple mini-batches.
"""
Merge the mini-batch statistics to form the evaluation result for multiple mini-batches.
"""
raise NotImplementedError()
@ -81,7 +77,6 @@ class Accuracy(Evaluator):
def __init__(self, *args, **kwargs):
super(Accuracy, self).__init__("accuracy", **kwargs)
# block = self._eval_program.global_block()
block = self._main_program.global_block()
g_total = block.create_var(
name=unique_name("Total"),
@ -122,21 +117,13 @@ 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,
"in_data_type": 5, # float32
"out_data_type": 2, #int32
})
block.append_op(
type="cast",
@ -158,44 +145,40 @@ class Accuracy(Evaluator):
"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):
block = self._eval_program.global_block()
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._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})
e_total = _clone_var_in_block_(block, self._states["Total"])
e_correct = _clone_var_in_block_(block, self._states["Correct"])
block.append_op(
type="cast",
inputs={"X": [e_total]},
outputs={"Out": [e_total]},
attrs={
"in_data_type": 2, #int32
"out_data_type": 5, #float32
})
block.append_op(
type="cast",
inputs={"X": [e_correct]},
outputs={"Out": [e_correct]},
attrs={
"in_data_type": 2,
"out_data_type": 5,
})
block.append_op(
type="elementwise_div",
inputs={"X": e_total,
"Y": e_correct},
inputs={"X": e_correct,
"Y": e_total},
outputs={"Out": eval_out})
return executor.run(self._eval_program, fetch_list=[eval_out])
out = executor.run(eval_program, fetch_list=[eval_out])
return np.array(out[0])
# Demo for composing low level ops to compute the F1 metric
@ -235,8 +218,8 @@ class FScore(Evaluator):
persistable=True)
# def register():
accuracy = Accuracy
# def accuracy(*args, **kwargs):
# acc = Accuracy(**kwargs)
# return acc._update_ops(*args, **kwargs)
# FIXME(dzh): add a decorator to call _update_ops automatically
def accuracy(*args, **kwargs):
cls = Accuracy(*args, **kwargs)
out = cls._update_ops(*args, **kwargs)
return cls, out

26
python/paddle/v2/framework/tests/test_recognize_digits_conv.py
Unescape View File

@ -55,23 +55,14 @@ 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)
# 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(
accuracy, acc_out = 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
@ -105,11 +96,14 @@ for pass_id in range(PASS_NUM):
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
pass_acc = accuracy.eval(exe)
print "pass id : ", pass_id, 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)
pass_acc = accuracy.eval(exe)
print "pass id : ", pass_id, pass_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)
exit(1)

Write Preview
Loading…
Cancel
Save