from pathlib import Path
import torch
import gradio as gr
from torch import nn
import cv2

LABELS = Path("class_names.txt").read_text().splitlines()

model = nn.Sequential(
    nn.Conv2d(1, 32, 3, padding="same"),
    nn.ReLU(),
    nn.MaxPool2d(2),
    nn.Conv2d(32, 64, 3, padding="same"),
    nn.ReLU(),
    nn.MaxPool2d(2),
    nn.Conv2d(64, 128, 3, padding="same"),
    nn.ReLU(),
    nn.MaxPool2d(2),
    nn.Flatten(),
    nn.Linear(1152, 256),
    nn.ReLU(),
    nn.Linear(256, len(LABELS)),
)
 
state_dict = torch.load("pytorch_model.bin", map_location="cpu")
model.load_state_dict(state_dict, strict=False)
model.eval()


def predict(im):    
    if(im is not None):
        # print(im.size)
        im = cv2.resize(im, dsize=(28, 28), interpolation=cv2.INTER_CUBIC)
        x = torch.tensor(im, dtype=torch.float32).unsqueeze(0).unsqueeze(0) / 255.0 
        # print(type(im), im.size)
        with torch.no_grad():
            out = model(x)
        probabilities = torch.nn.functional.softmax(out[0], dim=0)
        values, indices = torch.topk(probabilities, 5)
        return {LABELS[i]: v.item() for i, v in zip(indices, values)}

sp = gr.Sketchpad(shape=(56,56),brush_radius =1)
interface = gr.Interface(
predict,
inputs=sp,
outputs="label",
theme="huggingface",
title="Reconocimiento de garabtosss",
description="Querés jugar al Picdictonary con una AI? Dibujá un objeto cotidiano y mirá los resultados!",
article="<p style='text-align: center'>Reconocimiento de Garabatos | Demo Model</p>",
live=True,
)
interface.launch()