| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163 |
- # global configs
- Global:
- checkpoints: null
- pretrained_model: null
- output_dir: ./output/
- device: gpu
- save_interval: 1
- eval_during_train: False
- eval_interval: 1
- epochs: 300
- print_batch_step: 10
- use_visualdl: False
- # used for static mode and model export
- image_shape: [3, 224, 224]
- save_inference_dir: ./inference
- # mixed precision
- AMP:
- use_amp: True
- 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: FasterNet_T0
- class_num: 1000
- # loss function config for traing/eval process
- Loss:
- Train:
- - CELoss:
- weight: 1.0
- epsilon: 0.1
- Eval:
- - CELoss:
- weight: 1.0
- Optimizer:
- name: AdamW
- beta1: 0.9
- beta2: 0.999
- epsilon: 1e-8
- weight_decay: 0.005
- clip_grad: null
- no_weight_decay_name: null
- one_dim_param_no_weight_decay: True
- lr:
- name: Cosine
- learning_rate: 0.0006 # 8gpu
- warmup_start_lr: 0.000001
- warmup_epoch: 20
- eta_min: 0.00001
- # data loader for train and eval
- DataLoader:
- Train:
- dataset:
- name: ImageNetDataset
- image_root: ./dataset/ILSVRC2012/
- cls_label_path: ./dataset/ILSVRC2012/train_list.txt
- transform_ops:
- - DecodeImage:
- backend: pil
- channel_first: False
- - RandCropImage:
- size: 224
- interpolation: bicubic
- backend: pil
- - RandFlipImage:
- flip_code: 1
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- batch_transform_ops:
- - OpSampler:
- MixupOperator:
- alpha: 0.05
- prob: 0.5
- CutmixOperator:
- alpha: 1.0
- prob: 0.5
- sampler:
- name: DistributedBatchSampler
- batch_size: 64
- drop_last: False
- shuffle: True
- loader:
- num_workers: 12
- use_shared_memory: True
- Eval:
- dataset:
- name: ImageNetDataset
- image_root: ./dataset/ILSVRC2012/
- cls_label_path: ./dataset/ILSVRC2012/val_list.txt
- transform_ops:
- - DecodeImage:
- backend: pil
- to_np: False
- channel_first: False
- - ResizeImage:
- interpolation: bicubic
- backend: pil
- resize_short: 248
- - CropImage:
- size: 224
- - 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: 4
- drop_last: False
- shuffle: False
- loader:
- num_workers: 6
- use_shared_memory: True
- Infer:
- infer_imgs: docs/images/inference_deployment/whl_demo.jpg
- batch_size: 10
- transforms:
- - DecodeImage:
- to_rgb: True
- channel_first: False
- - ResizeImage:
- interpolation: bicubic
- backend: pil
- resize_short: 248
- - CropImage:
- size: 224
- - NormalizeImage:
- scale: 1.0/255.0
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- order: ''
- - ToCHWImage:
- PostProcess:
- name: Topk
- topk: 5
- class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
- Metric:
- Train:
- - TopkAcc:
- topk: [1, 5]
- Eval:
- - TopkAcc:
- topk: [1, 5]
|
