Closed hajime-te closed 4 years ago
Hi @hajime-te
sorry, I cannot understand why that is a problem, The version of TF what I used to test the test.py :) was 1.13.1, and last week I tested on 1.15.2. Now the PC that I am using has TensorFlow 2.1.
When you change the structure of checkpoints did you change the code also? if don't it should be as follow:
├─checkpoints
│ └─DXN_BIPED
│ └─train
│ ├─data_lists
│ │ └─MDBD
│ │ test_pair.lst
│ │
│ └─train_1
│ checkpoint
│ DXN-149736.data-00000-of-00001
│ DXN-149736.index
│ DXN-149736.meta
For the successful opening of checkpoints, the container dir must be structured as you see above.
Thanks for your help. Your answer solved my problem!
Hi.
When I try the command:
python run_model.py --image_width=512 --image_height=512
result file will not be created because the process is completed without any error message.When I checked it with the VScode debugger, the process ended at the place where
saver.restore(session, meta_model_file)
in test.py was executedHow can I solve this error?
My environment is as follows OS Windows10 1903 Python 3.7.5 tensorflow 1.15.0 gpu_py37hc3743a6_0 tensorflow-base 1.15.0 gpu_py37h1afeea4_0 tensorflow-estimator 1.15.1 pyh2649769_0 tensorflow-gpu 1.15.0 h0d30ee6_0
Folder structure is as follows
Console message is as follow