File size: 1,574 Bytes
175924e eb0dc26 175924e 3a6bc73 175924e 3a6bc73 eb0dc26 175924e eb0dc26 175924e 3a6bc73 eb0dc26 3a6bc73 eb0dc26 175924e 3a6bc73 175924e 3a6bc73 |
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 |
import numpy as np
import tensorflow as tf
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.preprocessing.text import tokenizer_from_json
import json
import os
# Hugging Face expects a class named Pipeline with __call__(self, inputs)
class Pipeline:
def __init__(self):
# Load tokenizer
with open("tokenizer.json", "r", encoding="utf-8") as f:
tokenizer_json = f.read()
self.tokenizer = tokenizer_from_json(tokenizer_json)
self.max_len = 150
# Load model (SavedModel format)
self.model = tf.keras.models.load_model(".")
# Load label map if available
self.label_map = None
if os.path.exists("label_map.json"):
with open("label_map.json", "r", encoding="utf-8") as f:
self.label_map = json.load(f)
def __call__(self, inputs):
# Accepts a dict with keys 'text' and 'image_desc'
text = inputs.get("text", "")
image_desc = inputs.get("image_desc", "")
input_text = text + " " + image_desc
seq = self.tokenizer.texts_to_sequences([input_text])
padded = pad_sequences(seq, maxlen=self.max_len, padding='post', truncating='post')
pred_probs = self.model.predict(padded)
pred_label = int(np.argmax(pred_probs, axis=1)[0])
score = float(np.max(pred_probs))
if self.label_map:
label = self.label_map.get(str(pred_label), pred_label)
else:
label = pred_label
return {"label": label, "score": score}
|