app.py

import requests
import gradio as gr
import torch
from torchvision.models import alexnet
import torch.nn as nn
from torchvision import transforms

LABELS = {0:'Cat', 1:'Dog'}


model = alexnet(pretrained=True)
for param in model.parameters():
    param.requires_grad = False

# # Add a avgpool here
# avgpool = nn.AdaptiveAvgPool2d((7, 7))
# 
# # Replace the classifier layer
# # to customise it according to our output
model.classifier = nn.Sequential(
    nn.Linear( 256*7*7, 1024),
    nn.Linear(1024, 256),
    nn.Linear(256, 2))

checkpoint = torch.load(
    "CatVsDogsModel.pth", map_location=torch.device("cpu")
)

model.load_state_dict(checkpoint["state_dict"])
model = model.to('cpu')



transform = transforms.Compose(
    [transforms.Resize((128, 128)), transforms.ToTensor()]
)



def predict(img):
    img = transform(img).to('cpu')
    img = img.unsqueeze(0)
    with torch.no_grad():
        out=  model(img)
    probability = torch.nn.functional.softmax(out[0],dim=0)
    print(out)
    print(type(img))

    values, indices = torch.topk(probability,k=2)
    return {LABELS[i]: v.item() for i,v in zip(indices,values)}


iface = gr.Interface(fn=predict, inputs=gr.inputs.Image(type='pil'), outputs="label").launch()
iface.launch(share=True)