sednn
sednn copied to clipboard
the problem of main_dnn.py
the program main_dnn.py, eval_te_gen and eval_tr_gen is same, both of their type is 'test', i think eval_tr_gen's type should changed to 'train'
Hi, thanks for your interest. Both eval_tr_gen and eval_te_gen should use 'test' in the argument because both of them should use the test data generator. The 'train' will use the data generator for training.
Best wishes,
Qiuqiang
From: FFXZ [email protected] Sent: 16 January 2019 03:36:41 To: yongxuUSTC/sednn Cc: Subscribed Subject: [yongxuUSTC/sednn] the problem of main_dnn.py (#25)
[image]https://user-images.githubusercontent.com/16372416/51224788-876cad00-1982-11e9-89e7-7982c282f05c.png the program main_dnn.py, eval_te_gen and eval_tr_gen is same, both of their type is 'test', i think eval_tr_gen's type should changed to 'train'
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/yongxuUSTC/sednn/issues/25, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AMt5yV3nCUr3UpdssT_JFrdgSWfRWiqiks5vDp5JgaJpZM4aCQB0.
Hi, thanks for your interest. Both eval_tr_gen and eval_te_gen should use 'test' in the argument because both of them should use the test data generator. The 'train' will use the data generator for training. Best wishes, Qiuqiang … ________________________________ From: FFXZ [email protected] Sent: 16 January 2019 03:36:41 To: yongxuUSTC/sednn Cc: Subscribed Subject: [yongxuUSTC/sednn] the problem of main_dnn.py (#25) [image]https://user-images.githubusercontent.com/16372416/51224788-876cad00-1982-11e9-89e7-7982c282f05c.png the program main_dnn.py, eval_te_gen and eval_tr_gen is same, both of their type is 'test', i think eval_tr_gen's type should changed to 'train' — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub<#25>, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AMt5yV3nCUr3UpdssT_JFrdgSWfRWiqiks5vDp5JgaJpZM4aCQB0.
but if both of them use 'test', the tr_loss equals to te_loss, why do you test it twice? thanks for your explaining.