faster-rcnn錯(cuò)誤信息 ：?tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [21] rhs shape= [2]
1
Traceback (most recent call last):
2
File
"
C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\training\saver.py
"
, line 1276,
in
restore
3
{self.saver_def.filename_tensor_name: save_path})
4
File
"
C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\client\session.py
"
, line 929,
in
run
5
run_metadata_ptr)
6
File
"
C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\client\session.py
"
, line 1152,
in
_run
7
feed_dict_tensor, options, run_metadata)
8
File
"
C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\client\session.py
"
, line 1328,
in
_do_run
9
run_metadata)
10
File
"
C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\client\session.py
"
, line 1348,
in
_do_call
11
raise
type(e)(node_def, op, message)
12
tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [21] rhs shape= [2
]
13
[[node save/Assign_517 (defined at G:/jianfeng/project/rubblish_det/faster_rcnn/tf-faster-rcnn-master/tools/demo.py:149) ]]
我的代碼來自?https://github.com/endernewton/tf-faster-rcnn
這是由于類別數(shù)目不一致，導(dǎo)致的 ；看錯(cuò)誤信息倒數(shù)第二行，lhs為21類 rhs為2類?
解決方法：在demo.py文件中找到下面兩行代碼，將 "TEST"后的21改為 2? ?因?yàn)槲业臄?shù)據(jù)類別是? background+單類別=2
1
net.create_architecture(
"
TEST
"
, 21
,
2
tag=
'
default
'
, anchor_scales=[8, 16, 32])
?
更多文章、技術(shù)交流、商務(wù)合作、聯(lián)系博主
微信掃碼或搜索：z360901061
微信掃一掃加我為好友
QQ號聯(lián)系： 360901061
您的支持是博主寫作最大的動(dòng)力，如果您喜歡我的文章，感覺我的文章對您有幫助，請用微信掃描下面二維碼支持博主2元、5元、10元、20元等您想捐的金額吧，狠狠點(diǎn)擊下面給點(diǎn)支持吧，站長非常感激您！手機(jī)微信長按不能支付解決辦法：請將微信支付二維碼保存到相冊，切換到微信，然后點(diǎn)擊微信右上角掃一掃功能，選擇支付二維碼完成支付。
【本文對您有幫助就好】元
