Spaces:
Sleeping
Sleeping
File size: 1,995 Bytes
20b7679 e048c03 20b7679 e048c03 20b7679 e048c03 20b7679 e048c03 20b7679 e048c03 20b7679 e048c03 20b7679 |
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 53 54 55 56 57 58 59 60 61 62 63 |
import nltk
import spacy
# nltk.download('wordnet')
# spacy.cli.download('en_core_web_sm')
from const import name_map
from demo import run_gradio
from model import get_model
from options import parse_args
import numpy as np
from transformers import T5Tokenizer
import torch
import joblib
def process_examples(samples, full_names):
for i in range(len(samples)):
sample = samples[i]
input_text = tokenizer.decode(sample['sentence1_input_ids'], skip_special_tokens=True)
ling1 = scaler.inverse_transform([sample['sentence1_ling']])[0]
ling2 = scaler.inverse_transform([sample['sentence2_ling']])[0]
ling = pd.DataFrame({'Index': full_names, 'Source': ling1, 'Target': ling2})
samples[i] = [input_text, ling]
return list(samples)
args, args_list, lng_names = parse_args(ckpt='./ckpt/model.pt')
print(args)
exit()
tokenizer = T5Tokenizer.from_pretrained(args.model_name)
device = 'cuda' if torch.cuda.is_available() else 'cpu'
full_names = [name_map[x] for x in lng_names]
# samples = joblib.load('assets/samples.bin')
# examples = process_examples(samples, full_names)
# ling_collection = np.load('assets/ling_collection.npy')
scaler = joblib.load('assets/scaler.bin')
model, ling_disc, sem_emb = get_model(args, tokenizer, device)
state = torch.load(args.ckpt, map_location=torch.device('cpu'))
model.load_state_dict(state['model'], strict=True)
model.eval()
print(model is not None, ling_disc is not None, sem_emb is not None)
exit()
if args.disc_type == 't5':
state = torch.load(args.disc_ckpt)
if 'model' in state:
ling_disc.load_state_dict(state['model'], strict=False)
else:
ling_disc.load_state_dict(state, strict=False)
ling_disc.eval()
state = torch.load(args.sem_ckpt)
if 'model' in state:
sem_emb.load_state_dict(state['model'], strict=False)
else:
sem_emb.load_state_dict(state, strict=False)
sem_emb.eval()
run_gradio(model, tokenizer, scaler, ling_collection, examples, full_names)
|