search

LeeDoYup / AnoGAN-tf

Unofficial Tensorflow Implementation of AnoGAN (Anomaly GAN)
MIT License
273 stars 90 forks source link

Thank you for your AnoGAN............ #33

Open meanzee opened 5 years ago

meanzee commented 5 years ago

First of all, thank you for your ANOGAN. I have a one problem. I'm sure the learning went well, but there's an error.

Exception: [!] Train a model first, then run test mode

Do you know what the problem is? Thank you .

LeeDoYup commented 5 years ago

could i let me know your command in terminal?

matak07 commented 5 years ago

@meanzee : I am having the same error. How did you solve that issue?

burgetrm commented 5 years ago

Check your checkpoint directory, if you already trained the model, you will see something like mnist_64_28_28

To use this model for anomaly detection provide parameters for batch size of 64, and output dimension 28x28

Example: 1) Download training data: python download.py mnist 2) Train your model
python main.py --dataset mnist --input_height=28 --output_height=28 --train 3) Prepare test data Downloaded sample images and put them to test_data folder 4) Run anomaly detection python main.py --dataset mnist --batch_size=64 --input_height=28 --output_height=28 --crop --anomaly_test