| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206 |
- # global configs
- Global:
- checkpoints: null
- pretrained_model: null
- output_dir: ./output
- device: gpu
- save_interval: 1
- eval_during_train: True
- eval_interval: 1
- epochs: 100
- print_batch_step: 20
- use_visualdl: False
- eval_mode: retrieval
- retrieval_feature_from: features # 'backbone' or 'features'
- re_ranking: False
- use_dali: False
- # used for static mode and model export
- image_shape: [3, 224, 224]
- save_inference_dir: ./inference
- # mixed precision
- AMP:
- use_amp: False
- use_fp16_test: False
- scale_loss: 128.0
- use_dynamic_loss_scaling: True
- use_promote: False
- # O1: mixed fp16, O2: pure fp16
- level: O1
- # model architecture
- Arch:
- name: RecModel
- infer_output_key: features
- infer_add_softmax: False
- Backbone:
- name: PPLCNetV2_base_ShiTu
- pretrained: True
- use_ssld: True
- class_expand: &feat_dim 512
- BackboneStopLayer:
- name: flatten
- Neck:
- name: BNNeck
- num_features: *feat_dim
- weight_attr:
- initializer:
- name: Constant
- value: 1.0
- bias_attr:
- initializer:
- name: Constant
- value: 0.0
- learning_rate: 1.0e-20 # NOTE: Temporarily set lr small enough to freeze the bias to zero
- Head:
- name: FC
- embedding_size: *feat_dim
- class_num: 192612
- weight_attr:
- initializer:
- name: Normal
- std: 0.001
- bias_attr: False
- # loss function config for traing/eval process
- Loss:
- Train:
- - CELoss:
- weight: 1.0
- epsilon: 0.1
- - TripletAngularMarginLoss:
- weight: 1.0
- feature_from: features
- margin: 0.5
- reduction: mean
- add_absolute: True
- absolute_loss_weight: 0.1
- normalize_feature: True
- ap_value: 0.8
- an_value: 0.4
- Eval:
- - CELoss:
- weight: 1.0
- Optimizer:
- name: Momentum
- momentum: 0.9
- lr:
- name: Cosine
- learning_rate: 0.06 # for 8gpu x 256bs
- warmup_epoch: 5
- regularizer:
- name: L2
- coeff: 0.00001
- # data loader for train and eval
- DataLoader:
- Train:
- dataset:
- name: ImageNetDataset
- image_root: ./dataset/
- cls_label_path: ./dataset/train_reg_all_data_v2.txt
- relabel: True
- transform_ops:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- size: [224, 224]
- return_numpy: False
- interpolation: bilinear
- backend: cv2
- - RandFlipImage:
- flip_code: 1
- - Pad:
- padding: 10
- backend: cv2
- - RandCropImageV2:
- size: [224, 224]
- - RandomRotation:
- prob: 0.5
- degrees: 90
- interpolation: bilinear
- - ResizeImage:
- size: [224, 224]
- return_numpy: False
- interpolation: bilinear
- backend: cv2
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: hwc
- sampler:
- name: PKSampler
- batch_size: 256
- sample_per_id: 4
- drop_last: False
- shuffle: True
- loader:
- num_workers: 4
- use_shared_memory: True
- Eval:
- Query:
- dataset:
- name: ImageNetDataset
- image_root: ./dataset/Inshop/
- cls_label_path: ./dataset/Inshop/query_list.txt
- transform_ops:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- size: [224, 224]
- return_numpy: False
- interpolation: bilinear
- backend: cv2
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: hwc
- sampler:
- name: DistributedBatchSampler
- batch_size: 64
- drop_last: False
- shuffle: False
- loader:
- num_workers: 4
- use_shared_memory: True
- Gallery:
- dataset:
- name: ImageNetDataset
- image_root: ./dataset/Inshop/
- cls_label_path: ./dataset/Inshop/gallery_list.txt
- transform_ops:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- size: [224, 224]
- return_numpy: False
- interpolation: bilinear
- backend: cv2
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: hwc
- sampler:
- name: DistributedBatchSampler
- batch_size: 64
- drop_last: False
- shuffle: False
- loader:
- num_workers: 4
- use_shared_memory: True
- Metric:
- Eval:
- - Recallk:
- topk: [1, 5]
- - mAP: {}
|