VlSomers / bpbreid

A strong baseline for body part-based person re-identification (check out our WACV23 paper)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About test Occluded-ReID datasets

xiaoxiaowannote opened this issue · comments

how can i test Occluded-ReID datasets with this codes, what should do for cfg, my bpbreid_occ_reid_test.yaml like this
data:
root: '/root/bpbreid-main_modify/datasets/reid'
sources: ['market1501']
targets: ['occluded_reid']
height: 384
width: 128
transforms: ['rc', 're']

model:
name: 'bpbreid'
load_weights: 'pretrained_models/'
load_config: True
bpbreid:
mask_filtering_training: False
mask_filtering_testing: True
learnable_attention_enabled: True
backbone: 'hrnet32'
test_embeddings: ['bn_foreg', 'parts']
masks:
dir: 'pifpaf_maskrcnn_filtering'
preprocess: 'five_v'

test:
evaluate: True
batch_size: 4
visrank: True

and my dir likes this
datasets
——reid
————Market-1501-v15.09.15
——whole_body_images
——occluded_body_images
——masks
___pifpaf
——occluded_body_images
——whole_body_images
thanks !

put the datasets occluded in dir of reid