Spaces:
Runtime error
Runtime error
File size: 3,761 Bytes
434511b 4aaa812 434511b 4aaa812 434511b 4aaa812 434511b 4aaa812 434511b 4aaa812 434511b 4aaa812 434511b 4aaa812 434511b 4aaa812 434511b 4aaa812 434511b |
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 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 |
import argparse
import torch
import os
import json
from tqdm import tqdm
import shortuuid
from tinyllava.utils import *
from tinyllava.data import *
from tinyllava.model import *
from PIL import Image
import math
def split_list(lst, n):
"""Split a list into n (roughly) equal-sized chunks"""
chunk_size = math.ceil(len(lst) / n) # integer division
return [lst[i:i+chunk_size] for i in range(0, len(lst), chunk_size)]
def get_chunk(lst, n, k):
chunks = split_list(lst, n)
return chunks[k]
def eval_model(args):
# Model
disable_torch_init()
model_path = os.path.expanduser(args.model_path)
model, tokenizer, image_processor, context_len = load_pretrained_model(model_path)
model.to(device='cuda')
text_processor = TextPreprocess(tokenizer, args.conv_mode)
data_args = model.config
image_processor = ImagePreprocess(image_processor, data_args)
questions = [json.loads(q) for q in open(os.path.expanduser(args.question_file), "r")]
questions = get_chunk(questions, args.num_chunks, args.chunk_idx)
answers_file = os.path.expanduser(args.answers_file)
os.makedirs(os.path.dirname(answers_file), exist_ok=True)
ans_file = open(answers_file, "w")
for line in tqdm(questions):
idx = line["question_id"]
image_file = line["image"]
qs = line["text"]
cur_prompt = qs
qs = DEFAULT_IMAGE_TOKEN + '\n' + qs
msg = Message()
msg.add_message(qs)
result = text_processor(msg.messages, mode='eval')
input_ids = result['input_ids']
prompt = result['prompt']
input_ids = input_ids.unsqueeze(0).cuda()
image = Image.open(os.path.join(args.image_folder, image_file)).convert('RGB')
image_tensor = image_processor(image)
image_tensors = image_tensor.unsqueeze(0).half().cuda()
image_sizes = [image.size]
with torch.inference_mode():
output_ids = model.generate(
input_ids,
images=image_tensors,
image_sizes=image_sizes,
do_sample=True if args.temperature > 0 else False,
temperature=args.temperature,
top_p=args.top_p,
num_beams=args.num_beams,
# no_repeat_ngram_size=3,
max_new_tokens=1024,
use_cache=True)
outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
ans_id = shortuuid.uuid()
ans_file.write(json.dumps({"question_id": idx,
"prompt": prompt,
"text": outputs,
"answer_id": ans_id,
"model_id": args.model_base,
"metadata": {}}) + "\n")
ans_file.flush()
ans_file.close()
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--model-path", type=str, default="facebook/opt-350m")
parser.add_argument("--model-base", type=str, default=None)
parser.add_argument("--image-folder", type=str, default="")
parser.add_argument("--question-file", type=str, default="tables/question.jsonl")
parser.add_argument("--answers-file", type=str, default="answer.jsonl")
parser.add_argument("--conv-mode", type=str, default="llava_v1")
parser.add_argument("--num-chunks", type=int, default=1)
parser.add_argument("--chunk-idx", type=int, default=0)
parser.add_argument("--temperature", type=float, default=0.2)
parser.add_argument("--top_p", type=float, default=None)
parser.add_argument("--num_beams", type=int, default=1)
args = parser.parse_args()
eval_model(args)
|