File size: 1,416 Bytes
c5da81d d98e05f 5bf9261 c5da81d d98e05f c5da81d 4829d4c a8f9ede 5bf9261 a8f9ede c5da81d d98e05f c5da81d d98e05f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
import streamlit as st
import torch
from transformers import AutoTokenizer, AutoModel, pipeline
from torch import nn
st.markdown("### Articles classificator.")
# st.markdown("<img width=200px src='https://rozetked.me/images/uploads/dwoilp3BVjlE.jpg'>", unsafe_allow_html=True)
@st.cache
def get_bert_and_tokenizer():
model_name = 'bert-base-uncased'
return AutoModel.from_pretrained(model_name), AutoTokenizer.from_pretrained(model_name)
bert, tokenizer = get_bert_and_tokenizer()
class devops_model(nn.Module):
def __init__(self):
super(devops_model, self).__init__()
self.bert = bert
self.fc = nn.Sequential(
nn.Linear(768, 768),
nn.ReLU(),
nn.Dropout(0.3),
nn.BatchNorm1d(768),
nn.Linear(768, 5),
nn.LogSoftmax(dim=-1)
)
def forward(self, train_batch):
emb = self.bert(**train_batch)['pooler_output']
return self.fc(emb)
@st.cache
def LoadModel():
return torch.load('model.pt')
model = LoadModel()
def process(title, summary):
text = title + summary
model.eval()
lines = [text]
X = tokenizer(lines, padding=True, truncation=True, return_tensors="pt")
out = model(X)
probs = torch.exp(out[0])
return probs
title = st.text_area("Title")
summary = st.text_area("Summary")
st.markdown(f"{process(title, summary)}") |