search

bcmi / F2GAN-Few-Shot-Image-Generation

Fusing-and-Filling GAN (F2GAN) for few-shot image generation, ACM MM2020
78 stars 11 forks source link

段错误 #3

Closed jinzhenmu closed 4 years ago

jinzhenmu commented 4 years ago

python3 train_dagan_with_matchingclassifier.py --dataset emnist --image_width 28 --batch_size 20 --experiment_title MMF2GAN/emnist1way3shot --selected_classes 1 --support_number 3 --loss_G 1 --loss_D 1 --loss_CLA 1 --loss_recons_B 1 --loss_matching_G 0.01 --loss_matching_D 1 --loss_sim 1

2020-10-19 17:10:01.832958: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set. If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU. To confirm that XLA is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile. time for initializing global parameters: 28.6798198223114 0%| | 0/600 [00:00<?, ?it/s]段错误

hy-zpg commented 4 years ago

you should update your tensorflow-gpu version to 1.7.

jinzhenmu commented 4 years ago

thank you！ IT is a nice job！

牟金震 邮箱：jinzhen_mu@163.com

签名由 网易邮箱大师 定制

在2020年10月19日 20:49，Hong Yan 写道：

you should update your tensorflow-gpu version to 1.7.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.