aftaab99/offlinesignatureverification

Writer independent offline signature verification using convolutional siamese networks

Shaik Aftaab Zia

Backend developer skilled primarily in NodeJs, Python and Java. Also experienced in Machine learning and NLP.

Connect with me here

Languages and Tools:

offlinesignatureverification's Issues

Error downloading Trained model

Hi,

there's an error download trained model.
This is the error:
python DownloadData.py Downloading dataset... Extracting data... Traceback (most recent call last): File "/Users/politom/Downloads/OfflineSignatureVerification-master/DownloadData.py", line 55, in <module> extract('./Datasets/cedar1.zip') File "/Users/politom/Downloads/OfflineSignatureVerification-master/DownloadData.py", line 39, in extract zip_ref = zipfile.ZipFile(file_path, 'r') File "/Users/politom/.pyenv/versions/3.10.4/lib/python3.10/zipfile.py", line 1267, in __init__ self._RealGetContents() File "/Users/politom/.pyenv/versions/3.10.4/lib/python3.10/zipfile.py", line 1334, in _RealGetContents raise BadZipFile("File is not a zip file") zipfile.BadZipFile: File is not a zip file

Can you restore file download?

Thanks you for all your work. Great job.

PARAM SIZE MISMATCH

RuntimeError: Error(s) in loading state_dict for SiameseConvNet:
Unexpected key(s) in state_dict: "conv4.weight", "conv4.bias", "fc1.bias", "fc2.bias".
size mismatch for conv1.weight: copying a param with shape torch.Size([48, 1, 11, 11]) from checkpoint, the shape in current model is torch.Size([5, 1, 11, 11]).
size mismatch for conv1.bias: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([5]).
size mismatch for conv2.weight: copying a param with shape torch.Size([128, 48, 5, 5]) from checkpoint, the shape in current model is torch.Size([12, 5, 5, 5]).
size mismatch for conv2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([12]).
size mismatch for conv3.weight: copying a param with shape torch.Size([256, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 12, 3, 3]).
size mismatch for conv3.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for fc1.weight: copying a param with shape torch.Size([1024, 40800]) from checkpoint, the shape in current model is torch.Size([1024, 28560]).

Im getting this error in the torch.load call

Working Implementation ?

I’m not sure how to implement this project in working. I checked the help docs (Readme.md) and didn’t find any mentions.

python DownloadData showing error

zipfile.BadZipFile: File is not a zip file
It is showing this error and when i checked the zip locally it is showing unknown format or damaged.

Internal Server Error

hi, i am trying to run this project I am facing these errors,
1st dataset is not getting downloaded
" raise ConnectionError(e, request=request)
requests.exceptions.ConnectionError: HTTPSConnectionPool(host='drive.google.com', port=443): Max retries exceeded with url: /uc?export=download&id=1w2DEYX2pBhBNS2l4sqrl8j-Am4cNSBoZ (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x000001CC6940D0A0>: Failed to establish a new connection: [WinError 10060] A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond'))
"
2nd i tried to run this project , i found server error.
" Internal Server Error
The server encountered an internal error and was unable to complete your request. Either the server is overloaded or there is an error in the application."

Please tell me how to resolve this issue,
I couldn't run the project at all.
Thank you in advance

fronted

hello I want to ask how to use the web demo.
npm install
npm run build
these two command how to use in pycharm or how to get the enviroment.
thank u

how to create file user_signatures.db

please give me the file user_signatures.db

invalid load key, '\xef'.

Server error in VS code

About the dataset splitting way

In the paper [SigNet:.... Signature Verification], its author use the way that 'select 50 signer in total 55 signer' to split the train set and test set.
However in this project code, you use the random select 13500*2 positive and negtive sample, and then 'train_test_split(data, test_size=0.15)'. By your way, it's more easy too much than the original method in the paper!!

So, in order to prove the effect of SigNet, I suggest that Reappearance must be same！

model.load_state_dict(torch.load('Models/model_epoch_2', map_location=device))

While running test.py error related to model.load_state_dict(torch.load('Models/model_epoch_2', map_location=device)) is showing .

Error: FileNotFoundError: [Errno 2] No such file or directory: 'model_epoch_%d'

numpy version

thank you for this wonderful repo

can you please share exact version of libraries you have used.

pre trained model

hi aftab i tried ur pre trained model on my dataset, but it giving me match = true on every verification pic. I tried on real, forge and fake data and reduce threshold too but nothing work

real

real

real

fake

forge

forge

forge
can u please check and if you have new saved model can u please give link with threshold value.
Thank you.

No check to see if customer doesn't exist

While clicking verify I am getting error that Something wrong with the server and in terminal, I got "NoneType" object is not iterable in the line
anchor_images = [Image.open(BytesIO(x)) for x in get_file_from_db(buffer(customer_id))]

Not working on local signatures

I've tested this network on my signatures and forged versions of those signature.
Its not giving good results.