Floetry / app.py
Basiluisco's picture
Initial commit
4f65503
Raw History Blame Contribute Delete
1.73 kB
import torch
import torch.nn as nn
from torchvision import models, transforms
from PIL import Image
import numpy as np
import gradio as gr
class_labels = ['daisy', 'dandelion', 'rose', 'sunflower', 'tulip', 'unknown']
def load_model(path='model.pth'):
model = models.resnet50(weights='IMAGENET1K_V1')
model.fc = nn.Linear(model.fc.in_features, len(class_labels) - 1)
model.load_state_dict(torch.load(path, map_location=torch.device('cpu')))
model.eval()
return model
model = load_model()
val_transform = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406],
[0.229, 0.224, 0.225])
])
def predict(image):
image = Image.fromarray(image.astype('uint8'), 'RGB')
input_tensor = val_transform(image).unsqueeze(0)
with torch.no_grad():
outputs = model(input_tensor)
probs = torch.nn.functional.softmax(outputs[0], dim=0)
confidence, predicted_idx = torch.max(probs, dim=0)
if confidence.item() < 0.85:
return f"No registrado (Confianza: {confidence:.2f})"
else:
return f"{class_labels[predicted_idx]} (Confianza: {confidence:.2f})"
with gr.Blocks() as demo:
gr.Markdown("# Floetry")
gr.Markdown("Clasificador de especies de flores con aprendizaje profundo.")
with gr.Row():
image_input = gr.Image(label="Sube una imagen", type="numpy")
output_box = gr.Textbox(label="Predicción", placeholder="Aquí aparecerá el resultado")
submit_button = gr.Button("Clasificar")
submit_button.click(fn=predict, inputs=image_input, outputs=output_box)
demo.launch()