tanzf

Results 7 comments of tanzf

No module named 'lib.fast_rcnn'

修改CHINESE-OCR-master\ctpn\ctpn\model.py文件，12-14行代码为： from ..lib.fast_rcnn.config import cfg from ..lib.networks.factory import get_network from ..lib.fast_rcnn.test import test_ctpn 我是这样改的，不报错了

input data/diff size does not match target blob shape, input data/diff size: [ 100 100 1 2 ] vs target blob shape: [ 100 100 1 100 ]

@iscas-lee 我也在编译这个MatAlignment.cpp，能不能把编译的流程详细的介绍一下，编译好久了，一直不成功，麻烦你了，万分感激

input data/diff size does not match target blob shape, input data/diff size: [ 100 100 1 2 ] vs target blob shape: [ 100 100 1 100 ]

哦，好吧，谢谢你了

input data/diff size does not match target blob shape, input data/diff size: [ 100 100 1 2 ] vs target blob shape: [ 100 100 1 100 ]

@iscas-lee 你好，我想问一下你使用MatAlignment.cpp这个对齐程序输进去的图片（比如LFW库的图像）是经过人脸剪裁之后的还是直接没剪裁直接用LFW库原图输进去对齐？？？？谢谢

input data/diff size does not match target blob shape, input data/diff size: [ 100 100 1 2 ] vs target blob shape: [ 100 100 1 100 ]

@iscas-lee 哦，那识别率怎么样呢？LFW库下达到多少？

input data/diff size does not match target blob shape, input data/diff size: [ 100 100 1 2 ] vs target blob shape: [ 100 100 1 100 ]

哦，好吧，谢谢您了

Executing op HashTableV2 in device /job:localhost/replica:0/task:0/device:CPU:0

下载2.0.0-alpha.42的模型文件，去那下载，能给个下载链接吗？谢谢