Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import torch
|
| 2 |
+
import torch.nn as nn
|
| 3 |
+
import gradio as gr
|
| 4 |
+
from huggingface_hub import hf_hub_download
|
| 5 |
+
|
| 6 |
+
REPO_ID = "SentilyticsOPJ/lstm_model" # <-- change to your model repo
|
| 7 |
+
FILENAME = "lstm_model.pt"
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
class TextBiLSTM(nn.Module):
|
| 11 |
+
def __init__(self, vocab_size, embed_dim, hidden_dim, num_classes):
|
| 12 |
+
super().__init__()
|
| 13 |
+
self.embedding = nn.Embedding(vocab_size, embed_dim, padding_idx=0)
|
| 14 |
+
self.lstm = nn.LSTM(embed_dim, hidden_dim, batch_first=True, bidirectional=True)
|
| 15 |
+
self.fc = nn.Linear(hidden_dim * 2, num_classes)
|
| 16 |
+
|
| 17 |
+
def forward(self, x):
|
| 18 |
+
x = self.embedding(x)
|
| 19 |
+
_, (hidden, _) = self.lstm(x)
|
| 20 |
+
x = torch.cat([hidden[0], hidden[1]], dim=1)
|
| 21 |
+
return self.fc(x)
|
| 22 |
+
|
| 23 |
+
path = hf_hub_download(repo_id=REPO_ID, filename=FILENAME)
|
| 24 |
+
obj = torch.load(path, map_location="cpu", weights_only=False)
|
| 25 |
+
sd = obj["state_dict"]
|
| 26 |
+
|
| 27 |
+
vocab_size, embed_dim = sd["embedding.weight"].shape
|
| 28 |
+
hidden_dim = sd["lstm.weight_hh_l0"].shape[1]
|
| 29 |
+
num_classes = sd["fc.weight"].shape[0]
|
| 30 |
+
|
| 31 |
+
model = TextBiLSTM(vocab_size, embed_dim, hidden_dim, num_classes)
|
| 32 |
+
model.load_state_dict(sd)
|
| 33 |
+
model.eval()
|
| 34 |
+
|
| 35 |
+
word2id = obj["word2id"]
|
| 36 |
+
labels = obj["label_classes"]
|
| 37 |
+
max_len = obj["max_len"]
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
def predict(text):
|
| 41 |
+
if not text.strip():
|
| 42 |
+
return {}
|
| 43 |
+
ids = [word2id.get(t, 1) for t in text.lower().split()][:max_len]
|
| 44 |
+
ids += [0] * (max_len - len(ids))
|
| 45 |
+
with torch.no_grad():
|
| 46 |
+
probs = torch.softmax(model(torch.tensor(ids).unsqueeze(0)), dim=1)[0]
|
| 47 |
+
return {labels[i]: float(probs[i]) for i in range(len(labels))}
|
| 48 |
+
|
| 49 |
+
gr.Interface(fn=predict, inputs="text", outputs="text").launch()
|