InsightFace_TF
InsightFace_TF copied to clipboard
what is output_node_names about mode D
i want to product model pb file
i find the name, in the issues one man said is resnet_v1_50/E_BN2/Identity:0 but in my freeze_graph file i just use resnet_v1_50/E_BN2/Identity as output_node_names. thanks this man said that , if i have time i will read the code
Hello, have you succeeded? I freeze model D to a pb file , but it works bad.
Not working! My pb file is for Android app, and using SVM on Android app is almost ineffective. But I use it in Python but it works.
@Yaque It works in fact. I made some mistakes in my code. But after I fixed them, the .pb file works well.
I think this may help you https://github.com/LJXLJXLJX/InsightFace_TF_opencv_dnn/blob/master/my_test.py
I have modified the L_Resnet_E_IR_fix_issue9.py at line 334
if keep_rate == None:
keep_rate = 1.0
@LJXLJXLJX Do you use Python?
@Yaque All languages that support opencv(4.0.1) works.
Oh, maybe my code has a problem.
LJX [email protected] 于 2019年2月27日周三 上午11:20写道:
@Yaque https://github.com/Yaque All languages that support opencv(4.0.1) works.
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/auroua/InsightFace_TF/issues/35#issuecomment-467708383, or mute the thread https://github.com/notifications/unsubscribe-auth/AWE2hRdlVGCMHKGZD6gGd-zkUP-ZclkSks5vRfmTgaJpZM4VT3Bw .