File size: 1,480 Bytes
256a159 |
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 |
from opencompass.multimodal.models.minigpt_4 import (MiniGPT4MMEPostProcessor, MiniGPT4MMEPromptConstructor)
# dataloader settings
val_pipeline = [
dict(type='mmpretrain.LoadImageFromFile'),
dict(type='mmpretrain.ToPIL', to_rgb=True),
dict(type='mmpretrain.torchvision/Resize',
size=(224, 224),
interpolation=3),
dict(type='mmpretrain.torchvision/ToTensor'),
dict(type='mmpretrain.torchvision/Normalize',
mean=(0.48145466, 0.4578275, 0.40821073),
std=(0.26862954, 0.26130258, 0.27577711)),
dict(type='mmpretrain.PackInputs',
algorithm_keys=[
'question', 'answer', 'task'
])
]
dataset = dict(type='opencompass.MMEDataset',
data_dir='/path/to/MME',
pipeline=val_pipeline)
minigpt_4_mme_dataloader = dict(batch_size=1,
num_workers=4,
dataset=dataset,
collate_fn=dict(type='pseudo_collate'),
sampler=dict(type='DefaultSampler', shuffle=False))
# model settings
minigpt_4_model = dict(
type='minigpt-4',
low_resource=False,
llama_model='/path/to/vicuna/',
prompt_constructor=dict(type=MiniGPT4MMEPromptConstructor),
post_processor=dict(type=MiniGPT4MMEPostProcessor))
# evaluation settings
minigpt_4_mme_evaluator = [
dict(type='opencompass.MMEMetric')
]
minigpt_4_load_from = '/path/to/prerained_minigpt4_7b.pth' # noqa
|