152 lines
3.5 KiB
YAML
152 lines
3.5 KiB
YAML
# global configs
|
|
Global:
|
|
checkpoints: null
|
|
pretrained_model: null
|
|
output_dir: "./output/"
|
|
device: "gpu"
|
|
save_interval: 1
|
|
eval_during_train: True
|
|
eval_interval: 1
|
|
epochs: 120
|
|
print_batch_step: 10
|
|
use_visualdl: False
|
|
# used for static mode and model export
|
|
image_shape: [3, 224, 224]
|
|
save_inference_dir: "./inference"
|
|
eval_mode: "retrieval"
|
|
|
|
# model architecture
|
|
Arch:
|
|
name: "RecModel"
|
|
infer_output_key: "features"
|
|
infer_add_softmax: False
|
|
Backbone:
|
|
name: "ResNet50_last_stage_stride1"
|
|
pretrained: True
|
|
BackboneStopLayer:
|
|
name: "adaptive_avg_pool2d_0"
|
|
Neck:
|
|
name: "VehicleNeck"
|
|
in_channels: 2048
|
|
out_channels: 512
|
|
Head:
|
|
name: "CircleMargin"
|
|
margin: 0.35
|
|
scale: 64
|
|
embedding_size: 512
|
|
class_num: 3000
|
|
|
|
# loss function config for traing/eval process
|
|
Loss:
|
|
Train:
|
|
- CELoss:
|
|
weight: 1.0
|
|
- PairwiseCosface:
|
|
margin: 0.35
|
|
gamma: 64
|
|
weight: 1.0
|
|
Eval:
|
|
- CELoss:
|
|
weight: 1.0
|
|
|
|
Optimizer:
|
|
name: Momentum
|
|
momentum: 0.9
|
|
lr:
|
|
name: Cosine
|
|
learning_rate: 0.04
|
|
regularizer:
|
|
name: 'L2'
|
|
coeff: 0.0001
|
|
|
|
# data loader for train and eval
|
|
DataLoader:
|
|
Train:
|
|
dataset:
|
|
name: LogoDataset
|
|
image_root: "dataset/LogoDet-3K-crop/train/"
|
|
cls_label_path: "dataset/LogoDet-3K-crop/LogoDet-3K+train.txt"
|
|
transform_ops:
|
|
- DecodeImage:
|
|
to_rgb: True
|
|
channel_first: False
|
|
- ResizeImage:
|
|
size: 224
|
|
- RandFlipImage:
|
|
flip_code: 1
|
|
- AugMix:
|
|
prob: 0.5
|
|
- NormalizeImage:
|
|
scale: 0.00392157
|
|
mean: [0.485, 0.456, 0.406]
|
|
std: [0.229, 0.224, 0.225]
|
|
order: ''
|
|
- RandomErasing:
|
|
EPSILON: 0.5
|
|
sampler:
|
|
name: PKSampler
|
|
batch_size: 128
|
|
sample_per_id: 2
|
|
drop_last: True
|
|
|
|
loader:
|
|
num_workers: 6
|
|
use_shared_memory: True
|
|
Eval:
|
|
Query:
|
|
dataset:
|
|
name: LogoDataset
|
|
image_root: "dataset/LogoDet-3K-crop/val/"
|
|
cls_label_path: "dataset/LogoDet-3K-crop/LogoDet-3K+val.txt"
|
|
transform_ops:
|
|
- DecodeImage:
|
|
to_rgb: True
|
|
channel_first: False
|
|
- ResizeImage:
|
|
size: 224
|
|
- NormalizeImage:
|
|
scale: 0.00392157
|
|
mean: [0.485, 0.456, 0.406]
|
|
std: [0.229, 0.224, 0.225]
|
|
order: ''
|
|
sampler:
|
|
name: DistributedBatchSampler
|
|
batch_size: 128
|
|
drop_last: False
|
|
shuffle: False
|
|
loader:
|
|
num_workers: 8
|
|
use_shared_memory: True
|
|
|
|
Gallery:
|
|
dataset:
|
|
name: LogoDataset
|
|
image_root: "dataset/LogoDet-3K-crop/train/"
|
|
cls_label_path: "dataset/LogoDet-3K-crop/LogoDet-3K+train.txt"
|
|
transform_ops:
|
|
- DecodeImage:
|
|
to_rgb: True
|
|
channel_first: False
|
|
- ResizeImage:
|
|
size: 224
|
|
- NormalizeImage:
|
|
scale: 0.00392157
|
|
mean: [0.485, 0.456, 0.406]
|
|
std: [0.229, 0.224, 0.225]
|
|
order: ''
|
|
sampler:
|
|
name: DistributedBatchSampler
|
|
batch_size: 128
|
|
drop_last: False
|
|
shuffle: False
|
|
loader:
|
|
num_workers: 8
|
|
use_shared_memory: True
|
|
|
|
Metric:
|
|
Eval:
|
|
- Recallk:
|
|
topk: [1, 5]
|
|
- mAP: {}
|
|
|