mirror of https://github.com/PyRetri/PyRetri.git
84 lines
2.8 KiB
YAML
84 lines
2.8 KiB
YAML
# retrieval settings
|
|
|
|
datasets:
|
|
# number of images in a batch.
|
|
batch_size: 16
|
|
|
|
# function for stacking images in a batch.
|
|
collate_fn:
|
|
name: "CollateFn" # name of the collate_fn.
|
|
|
|
# function for loading images.
|
|
folder:
|
|
name: "Folder" # name of the folder.
|
|
|
|
# a list of data augmentation functions.
|
|
transformers:
|
|
names: ["ShorterResize", "CenterCrop", "ToCaffeTensor", "Normalize"] # names of transformers.
|
|
ShorterResize:
|
|
size: 256 # target size of the shorter edge.
|
|
CenterCrop:
|
|
size: 224 # target size of the crop img.
|
|
Normalize:
|
|
mean: [104, 116, 124]
|
|
std: [1.0, 1.0, 1.0]
|
|
|
|
model:
|
|
name: "vgg16" # name of the model.
|
|
vgg16:
|
|
load_checkpoint: "/data/places365_model/vgg16_hybrid1365.pt" # path of the model checkpoint, If it is started with "torchvision://", the model will be loaded from torchvision.
|
|
|
|
extract:
|
|
# way to assemble features if transformers produce multiple images (e.g. TwoFlip, TenCrop). 0 means concat these features and 1 means sum these features.
|
|
assemble: 0
|
|
|
|
# function for assigning output features.
|
|
extractor:
|
|
name: "VggSeries" # name of the extractor.
|
|
VggSeries:
|
|
extract_features: ["pool5"] # name of the output feature map. If it is ["all"], then all available features will be output.
|
|
|
|
# function for splitting the output features (e.g. PCB).
|
|
splitter:
|
|
name: "Identity" # name of the function for splitting features.
|
|
|
|
# a list of pooling functions.
|
|
aggregators:
|
|
names: ["GAP"] # names of aggregators.
|
|
|
|
index:
|
|
# path of the query set features and gallery set features.
|
|
query_fea_dir: "/data/features/best_features/oxford/query"
|
|
gallery_fea_dir: "/data/features/best_features/oxford/gallery"
|
|
|
|
# name of the features to be loaded. It should be "output feature map" + "_" + "aggregation".
|
|
# If there are multiple elements in the list, they will be concatenated on the channel-wise.
|
|
feature_names: ["pool5_GAP"]
|
|
|
|
# a list of dimension process functions.
|
|
dim_processors:
|
|
names: ["L2Normalize", "SVD", "L2Normalize"]
|
|
SVD:
|
|
proj_dim: 511 # the dimension after reduction. If it is 0, then no reduction will be done.
|
|
whiten: True # whether do whiten when using SVD.
|
|
train_fea_dir: "/data/features/best_features/paris" # path of the features for training SVD.
|
|
l2: True # whether do l2-normalization on the training features.
|
|
|
|
# function for enhancing the quality of features.
|
|
feature_enhancer:
|
|
name: "Identity" # name of the feature enhancer.
|
|
|
|
# function for calculating the distance between query features and gallery features.
|
|
metric:
|
|
name: "KNN" # name of the metric.
|
|
|
|
# function for re-ranking the results.
|
|
re_ranker:
|
|
name: "Identity" # name of the re-ranker.
|
|
|
|
evaluate:
|
|
# function for evaluating results.
|
|
evaluator:
|
|
name: "OxfordOverAll" # name of the evaluator.
|
|
|