Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

segmentation fault #43

Open
menghuadeng opened this issue Sep 4, 2018 · 2 comments
Open

segmentation fault #43

menghuadeng opened this issue Sep 4, 2018 · 2 comments

Comments

@menghuadeng
Copy link

menghuadeng commented Sep 4, 2018

Hi, I copied my dataset to ./data/train folder, then I ran the sh inference_SRGAN command, but the code not work, it reminded "segmentaion fault" and no other error. The detail is as follows, can you tell what the problem may be, thank you. @brade31919

/PycharmProjects/SRGAN-tensorflow$ sh inference_SRGAN.sh
/home/menghua/anaconda3/lib/python3.6/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as _register_converters
[Configurations]:
output_dir: <absl.flags._flag.Flag object at 0x7f0e9163d1d0>
summary_dir: <absl.flags._flag.Flag object at 0x7f0e50c65c18>
mode: <absl.flags._flag.Flag object at 0x7f0e50c65c88>
checkpoint: <absl.flags._flag.Flag object at 0x7f0e50c74048>
pre_trained_model: <absl.flags._flag.BooleanFlag object at 0x7f0e50c74128>
pre_trained_model_type: <absl.flags._flag.Flag object at 0x7f0e50c869b0>
is_training: <absl.flags._flag.BooleanFlag object at 0x7f0e50c86e48>
vgg_ckpt: <absl.flags._flag.Flag object at 0x7f0e50c22630>
task: <absl.flags._flag.Flag object at 0x7f0e50c226a0>
batch_size: <absl.flags._flag.Flag object at 0x7f0e50c22748>
input_dir_LR: <absl.flags._flag.Flag object at 0x7f0e50c227f0>
input_dir_HR: <absl.flags._flag.Flag object at 0x7f0e50c22860>
flip: <absl.flags._flag.BooleanFlag object at 0x7f0e50c22898>
random_crop: <absl.flags._flag.BooleanFlag object at 0x7f0e50c22908>
crop_size: <absl.flags._flag.Flag object at 0x7f0e50c229b0>
name_queue_capacity: <absl.flags._flag.Flag object at 0x7f0e50c22a58>
image_queue_capacity: <absl.flags._flag.Flag object at 0x7f0e50c22b00>
queue_thread: <absl.flags._flag.Flag object at 0x7f0e50c22ba8>
num_resblock: <absl.flags._flag.Flag object at 0x7f0e50c22c50>
perceptual_mode: <absl.flags._flag.Flag object at 0x7f0e50c22cf8>
EPS: <absl.flags._flag.Flag object at 0x7f0e50c22dd8>
ratio: <absl.flags._flag.Flag object at 0x7f0e50c22e80>
vgg_scaling: <absl.flags._flag.Flag object at 0x7f0e50c22f28>
learning_rate: <absl.flags._flag.Flag object at 0x7f0e50c22f98>
decay_step: <absl.flags._flag.Flag object at 0x7f0e50c2b048>
decay_rate: <absl.flags._flag.Flag object at 0x7f0e50c2b0b8>
stair: <absl.flags._flag.BooleanFlag object at 0x7f0e50c2b0f0>
beta: <absl.flags._flag.Flag object at 0x7f0e50c2b1d0>
max_epoch: <absl.flags._flag.Flag object at 0x7f0e50c2b278>
max_iter: <absl.flags._flag.Flag object at 0x7f0e50c2b2e8>
display_freq: <absl.flags._flag.Flag object at 0x7f0e50c2b358>
summary_freq: <absl.flags._flag.Flag object at 0x7f0e50c2b400>
save_freq: <absl.flags._flag.Flag object at 0x7f0e50c2b4a8>
End of configuration
Finish building the network
2018-09-04 16:08:21.109872: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2018-09-04 16:08:21.114524: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
Loading weights from the pre-trained model
Evaluation starts!!
Segmentation fault

@lxk1990727
Copy link

same too

@CognitiveClouds-Prasad
Copy link

Same here. I am facing the same problem for few of the images only though.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants