train #28

New Issue

claunia · 2026-01-29T21:38:01Z

claunia commented

2026-01-29 21:38:01 +00:00

Originally created by @ZZFanya-DWR on GitHub (Jul 13, 2021).

This training process looks a bit strange, is there something wrong with my configuration file, I am based on 1024 resolution

021-07-13 16:20:56,380 INFO: [train..][epoch: 0, iter: 100, lr:(2.000e-03,)] [eta: 112 days, 17:17:33, time (data): 1.796 (0.015)] l_g_pix: inf l_p_8: nan l_p_16: nan l_p_32: nan l_p_64: nan l_p_128: nan l_p_256: nan l_p_512: inf l_p_1024: inf l_g_percep: inf l_g_style: inf l_g_gan: nan l_g_gan_left_eye: nan l_g_gan_right_eye: nan l_g_gan_mouth: nan l_g_comp_style_loss: nan l_identity: nan l_d: nan real_score: nan fake_score: nan l_d_left_eye: nan l_d_right_eye: nan l_d_mouth: nan

Originally created by @ZZFanya-DWR on GitHub (Jul 13, 2021). This training process looks a bit strange, is there something wrong with my configuration file, I am based on 1024 resolution > 021-07-13 16:20:56,380 INFO: [train..][epoch: 0, iter: 100, lr:(2.000e-03,)] [eta: 112 days, 17:17:33, time (data): 1.796 (0.015)] l_g_pix: inf l_p_8: nan l_p_16: nan l_p_32: nan l_p_64: nan l_p_128: nan l_p_256: nan l_p_512: inf l_p_1024: inf l_g_percep: inf l_g_style: inf l_g_gan: nan l_g_gan_left_eye: nan l_g_gan_right_eye: nan l_g_gan_mouth: nan l_g_comp_style_loss: nan l_identity: nan l_d: nan real_score: nan fake_score: nan l_d_left_eye: nan l_d_right_eye: nan l_d_mouth: nan

claunia closed this issue

2026-01-29 21:38:02 +00:00

claunia commented

2026-01-29 21:38:04 +00:00

@xinntao commented on GitHub (Jul 27, 2021):

try to debug it, it seems that the loss is too large, do you use a pretrained model ~

@xinntao commented on GitHub (Jul 27, 2021): try to debug it, it seems that the loss is too large, do you use a pretrained model ~

claunia commented

2026-01-29 21:38:06 +00:00

@BruceZhou95 commented on GitHub (Apr 12, 2023):

This training process looks a bit strange, is there something wrong with my configuration file, I am based on 1024 resolution

021-07-13 16:20:56,380 INFO: [train..][epoch: 0, iter: 100, lr:(2.000e-03,)] [eta: 112 days, 17:17:33, time (data): 1.796 (0.015)] l_g_pix: inf l_p_8: nan l_p_16: nan l_p_32: nan l_p_64: nan l_p_128: nan l_p_256: nan l_p_512: inf l_p_1024: inf l_g_percep: inf l_g_style: inf l_g_gan: nan l_g_gan_left_eye: nan l_g_gan_right_eye: nan l_g_gan_mouth: nan l_g_comp_style_loss: nan l_identity: nan l_d: nan real_score: nan fake_score: nan l_d_left_eye: nan l_d_right_eye: nan l_d_mouth: nan

Hello, may I ask where needs to be modified when using 1024*1024 images for training, looking forward to your reply, thanks

@BruceZhou95 commented on GitHub (Apr 12, 2023): > This training process looks a bit strange, is there something wrong with my configuration file, I am based on 1024 resolution > > > 021-07-13 16:20:56,380 INFO: [train..][epoch: 0, iter: 100, lr:(2.000e-03,)] [eta: 112 days, 17:17:33, time (data): 1.796 (0.015)] l_g_pix: inf l_p_8: nan l_p_16: nan l_p_32: nan l_p_64: nan l_p_128: nan l_p_256: nan l_p_512: inf l_p_1024: inf l_g_percep: inf l_g_style: inf l_g_gan: nan l_g_gan_left_eye: nan l_g_gan_right_eye: nan l_g_gan_mouth: nan l_g_comp_style_loss: nan l_identity: nan l_d: nan real_score: nan fake_score: nan l_d_left_eye: nan l_d_right_eye: nan l_d_mouth: nan Hello, may I ask where needs to be modified when using 1024*1024 images for training, looking forward to your reply, thanks

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: TencentARC/GFPGAN#28