提交 2be7ec9f 编写于 作者: Y Yu Yang 提交者: GitHub

Merge pull request #713 from wangyang59/improveMnistDemo

improve demo/mnist dataProvider speed
2 合并请求!11636[IMPORTANT] MKLDNN layout: Support for sum operator,!2081Release/0.10.0
from paddle.trainer.PyDataProvider2 import *
import numpy
# Define a py data provider
@provider(
input_types={'pixel': dense_vector(28 * 28),
'label': integer_value(10)})
'label': integer_value(10)},
cache=CacheType.CACHE_PASS_IN_MEM)
def process(settings, filename): # settings is not used currently.
imgf = filename + "-images-idx3-ubyte"
labelf = filename + "-labels-idx1-ubyte"
......@@ -20,12 +22,13 @@ def process(settings, filename): # settings is not used currently.
else:
n = 10000
for i in range(n):
label = ord(l.read(1))
pixels = []
for j in range(28 * 28):
pixels.append(float(ord(f.read(1))) / 255.0)
yield {"pixel": pixels, 'label': label}
images = numpy.fromfile(
f, 'ubyte', count=n * 28 * 28).reshape((n, 28 * 28)).astype('float32')
images = images / 255.0 * 2.0 - 1.0
labels = numpy.fromfile(l, 'ubyte', count=n).astype("int")
for i in xrange(n):
yield {"pixel": images[i, :], 'label': labels[i]}
f.close()
l.close()
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部