notAI-tech / NudeNet

Lightweight nudity detection
https://nudenet.notai.tech/
GNU Affero General Public License v3.0
1.81k stars 352 forks source link

No training configuration found in save file: the model was *not* compiled. Compile it manually. #44

Closed negonix closed 4 years ago

negonix commented 4 years ago

Describe the bug and error messages (if any)

/home/negonix/anaconda3/envs/nude-net-github/lib/python3.6/site-packages/keras/engine/saving.py:292: UserWarning: No training configuration found in save file: the model was not compiled. Compile it manually. warnings.warn('No training configuration found in save file: '

Specify versions of the following libraries

  1. nudenet = 2.0.1
  2. tensorflow/ tensorflow-gpu 1.14
  3. keras 2.2.4

This happened with this code:

from nudenet import NudeDetector detector = NudeDetector()

bedapudi6788 commented 4 years ago

@negonix this is just a keras warning for inference checkpoint. This is expected and the detector will work fine after that.

negonix commented 4 years ago

Hello friend, the problem is that it does not work after this. The next line in the code did not get executed, and it was detector.detect(“sample.jpg”)

On Thu, Aug 13, 2020 at 3:59 AM Bedapudi Praneeth notifications@github.com wrote:

@negonix https://github.com/negonix this is just a keras warning for inference checkpoint. This is expected and the detector will work fine after that.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/notAI-tech/NudeNet/issues/44#issuecomment-673325969, or unsubscribe https://github.com/notifications/unsubscribe-auth/ALXGYG7IWNKNPGTBATBDUNLSAOMPRANCNFSM4P5MUTJQ .

bedapudi6788 commented 4 years ago

Can you copy paste the entire output, error and warning messages you got.

negonix commented 4 years ago

Hey I'm so sorry for the trouble, it turns out it works actually, I just forgot to print the output. I followed the example on the readme and I assumed that detector.detect() would automatically print for some reason. Rookie mistake man I'm sorry.

Thank you for this program and all your help!