Create app.py

0c864b9 over 3 years ago

735 Bytes

from huggingface_hub import from_pretrained_fastai
import gradio as gr
# from fastai.vision.all import *
from fastai.text.all import *



# repo_id = "YOUR_USERNAME/YOUR_LEARNER_NAME"
repo_id = "igmarco/LSTM-text-classification"

learner = from_pretrained_fastai(repo_id)
labels = learner.dls.vocab

# Definimos una función que se encarga de llevar a cabo las predicciones
def predict(txt):
    pred,pred_idx,probs = learner.predict(txt)
    return {labels[i]: float(probs[i]) for i in range(len(labels))}
    
# Creamos la interfaz y la lanzamos. 
gr.Interface(fn=predict, inputs=gr.Textbox(lines=2, placeholder="Text Here..."), outputs=gr.outputs.Label(num_top_classes=3),examples=['buildings.jpg','forest.jpg']).launch(share=False)

	from huggingface_hub import from_pretrained_fastai
	import gradio as gr
	# from fastai.vision.all import *
	from fastai.text.all import *



	# repo_id = "YOUR_USERNAME/YOUR_LEARNER_NAME"
	repo_id = "igmarco/LSTM-text-classification"

	learner = from_pretrained_fastai(repo_id)
	labels = learner.dls.vocab

	# Definimos una función que se encarga de llevar a cabo las predicciones
	def predict(txt):
	pred,pred_idx,probs = learner.predict(txt)
	return {labels[i]: float(probs[i]) for i in range(len(labels))}

	# Creamos la interfaz y la lanzamos.
	gr.Interface(fn=predict, inputs=gr.Textbox(lines=2, placeholder="Text Here..."), outputs=gr.outputs.Label(num_top_classes=3),examples=['buildings.jpg','forest.jpg']).launch(share=False)