Closed Pravesh001 closed 5 years ago
The project is working, there are steps in the README with commands to download the pre-trained model and dataset, and then start the web server for the demo. I'll write the commands here again in case your having trouble.
Download the dependencies(for conda users)
conda env create -f projenv.yml
They can be installed using pip via
pip install -r requirements.txt
Then download the pretrained model and dataset
python DownloadData.py
After setting the environment and downloading the pre-trained model, start the web server using
python main.py
The demo starts at port 5000. Links to upload and verification page are under the menu.
I didn't quite understand what you meant by 'in working' but if you want to use the pre-trained model for inference, you'll need to find a threshold value which gives the best accuracy and then have the model predict true or false if the Euclidean distance between the two feature vectors is greater or lesser than the threshold respectively. You can look into Test.py
as to how to do all this.
Closing this issue. Reopen it if you please, in case they are any mistakes in the implementation.
Thanks for your response and help. I'm clear now.
On Wed, Apr 3, 2019, 8:00 PM Aftaab Zia notifications@github.com wrote:
Closing this issue. Reopen it if you please, in case they are any mistakes in the implementation.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/Aftaab99/OfflineSignatureVerification/issues/2#issuecomment-479514523, or mute the thread https://github.com/notifications/unsubscribe-auth/AeuU8IWLFw5-8QzLG1Zx-Hkfl3PL5RT2ks5vdLr1gaJpZM4cE5DQ .
I’m not sure how to implement this project in working. I checked the help docs (Readme.md) and didn’t find any mentions.