app.py

"""import gradio as gr
import onnxruntime as rt
from transformers import AutoTokenizer
import torch, json

tokenizer = AutoTokenizer.from_pretrained("neuralmind/bert-large-portuguese-cased")

with open("genre_types_encoded.json", "r") as fp:
  encode_genre_types = json.load(fp)

genres = list(encode_genre_types.keys())

inf_session = rt.InferenceSession('movie-classifier-quantized.onnx')
input_name = inf_session.get_inputs()[0].name
output_name = inf_session.get_outputs()[0].name

def classify_movie_genre(sinopse):
  input_ids = tokenizer(sinopse)['input_ids'][:512]
  logits = inf_session.run([output_name], {input_name: [input_ids]})[0]
  logits = torch.FloatTensor(logits)
  probs = torch.sigmoid(logits)[0]
  return dict(zip(genres, map(float, probs))) 

label = gr.outputs.Label(num_top_classes=5)
iface = gr.Interface(fn=classify_movie_genre, inputs="text", outputs=label)
iface.launch(inline=False)"""

import gradio as gr
import onnxruntime as rt
from transformers import AutoTokenizer
import torch, json

tokenizer = AutoTokenizer.from_pretrained("neuralmind/bert-large-portuguese-cased")

with open("genre_types_encoded.json", "r") as fp:
  encode_genre_types = json.load(fp)

genres = list(encode_genre_types.keys())

inf_session = rt.InferenceSession('movie-classifier-quantized.onnx')
input_name = inf_session.get_inputs()[0].name
output_name = inf_session.get_outputs()[0].name

def classify_movie_genre(sinopse):
  input_ids = tokenizer(sinopse)['input_ids'][:512]
  logits = inf_session.run([output_name], {input_name: [input_ids]})[0]
  logits = torch.FloatTensor(logits)
  probs = torch.sigmoid(logits)[0]
  return dict(zip(genres, map(float, probs))) 


app_examples = [
    ["asasasa"],
    ["ddddd"],
    ["fffff"],
    ["ggggg"],
    ["aaaaaa"]
    
]

inputs = [
    gr.Textbox(label="text", value=app_examples[0][0]),

]


label = gr.outputs.Label(num_top_classes=4)
iface = gr.Interface(fn=classify_movie_genre, inputs=inputs, outputs=label, examples=app_examples)
iface.launch(inline=False)