mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
44 lines
1.5 KiB
Python
44 lines
1.5 KiB
Python
![]() |
from opencompass.multimodal.models.qwen import QwenVLChatScienceQAPromptConstructor
|
||
|
|
||
|
# dataloader settings
|
||
|
val_pipeline = [
|
||
|
dict(type='mmpretrain.LoadImageFromFile'),
|
||
|
dict(type='mmpretrain.ToPIL', to_rgb=True),
|
||
|
dict(type='mmpretrain.torchvision/Resize',
|
||
|
size=(448, 448),
|
||
|
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', 'gt_answer', 'choices', 'hint', 'lecture', 'solution'
|
||
|
])
|
||
|
]
|
||
|
|
||
|
dataset = dict(type='mmpretrain.ScienceQA',
|
||
|
data_root='./data/scienceqa',
|
||
|
split='val',
|
||
|
split_file='pid_splits.json',
|
||
|
ann_file='problems.json',
|
||
|
image_only=True,
|
||
|
data_prefix=dict(img_path='val'),
|
||
|
pipeline=val_pipeline)
|
||
|
|
||
|
qwen_scienceqa_dataloader = dict(batch_size=1,
|
||
|
num_workers=4,
|
||
|
dataset=dataset,
|
||
|
collate_fn=dict(type='pseudo_collate'),
|
||
|
sampler=dict(type='DefaultSampler', shuffle=False))
|
||
|
|
||
|
# model settings
|
||
|
qwen_scienceqa_model = dict(
|
||
|
type='qwen-vl-chat',
|
||
|
pretrained_path='Qwen/Qwen-VL-Chat', # or Huggingface repo id
|
||
|
prompt_constructor=dict(type=QwenVLChatScienceQAPromptConstructor)
|
||
|
)
|
||
|
|
||
|
# evaluation settings
|
||
|
qwen_scienceqa_evaluator = [dict(type='mmpretrain.ScienceQAMetric')]
|