app.py

#%%
import gradio as gr
from PIL import Image
from torchvision import transforms
from siamese_nn import Siamese_nn
import torch, os
import torch.nn.functional as F

model = Siamese_nn()
weights = torch.load('trained_model')
model.load_state_dict(weights)
model.eval()
#%%
file_list = os.listdir('data')
examples = []
usersIndexes = []
for x in file_list:
    if x[0:2] not in usersIndexes:
        usersIndexes.append(x[0:2])
    
for user in usersIndexes:
    usersImages = [x for x in file_list if str(user) in x]
    notUsersImages = [x for x in file_list if str(user) not in x]

    for userImage in usersImages:
        for userImageCopy in usersImages:
            examples.append([userImage, userImageCopy, 0])
            for notUser in notUsersImages:
                examples.append([userImage, notUser, 1])

#%%
def predict(input1, input2, label=None):
    img1_PIL = Image.open(f'data/{input1}')
    img2_PIL = Image.open(f'data/{input2}')
    img1 = transforms.ToTensor()(img1_PIL).unsqueeze(0)
    img2 = transforms.ToTensor()(img2_PIL).unsqueeze(0)

    for el in examples:
        if input1 == input2:
            label = 0
            break
        if input1 in el and input2 in el:
            label = el[2]        
    
    with torch.no_grad():
        out1, out2 = model(img1, img2)
        pred = F.pairwise_distance(out1, out2)
        if pred < 0.6:
            decision = f'Access granted, confidence: {pred.item():4f}'
        else:
            decision = f'Access denied, confidence: {pred.item():4f}'
        return img1_PIL, img2_PIL, decision, label 

#%%
with gr.Blocks() as demo:
    drop1 =  gr.Dropdown(
    choices=file_list,
    label='First image',
    scale=0
    )
    drop2 = gr.Dropdown(
    choices=file_list,
    label='Second image',
    scale=0     
    )
    with gr.Row():
        img1 = gr.Image(value=f'data/{examples[0][0]}', height=153, width=136, interactive=False, scale=0, label='image1')
        img2 = gr.Image(value=f'data/{examples[0][0]}', height=153, width=136, interactive=False, scale=0, label='image2')
        label = gr.Label(label='0 means images represent the same fingerprint')
    output = gr.Label(value=predict(*examples[0])[2], label='Prediction')

    drop1.change(fn=predict, inputs=[drop1, drop2], outputs=[img1, img2, output, label])
    drop2.change(fn=predict, inputs=[drop1, drop2], outputs=[img1, img2, output, label])
    demo.launch()

# %%