173 lines
3.8 KiB
YAML
173 lines
3.8 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: 300
|
|
print_batch_step: 10
|
|
use_visualdl: False
|
|
# used for static mode and model export
|
|
image_shape: [3, 256, 256]
|
|
save_inference_dir: ./inference
|
|
use_dali: False
|
|
|
|
# mixed precision training
|
|
AMP:
|
|
scale_loss: 65536
|
|
use_dynamic_loss_scaling: True
|
|
# O1: mixed fp16, O2: pure fp16
|
|
level: O1
|
|
|
|
# model ema
|
|
EMA:
|
|
decay: 0.9995
|
|
|
|
# model architecture
|
|
Arch:
|
|
name: MobileViTV3_x1_0
|
|
class_num: 1000
|
|
classifier_dropout: 0.
|
|
|
|
# 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: 0.05
|
|
one_dim_param_no_weight_decay: True
|
|
lr:
|
|
name: Cosine
|
|
learning_rate: 0.002 # for total batch size 1020 by referring to official
|
|
eta_min: 0.0002
|
|
warmup_epoch: 16 # 20000 iterations
|
|
warmup_start_lr: 1e-6
|
|
clip_norm: 10
|
|
|
|
# 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:
|
|
to_rgb: True
|
|
channel_first: False
|
|
backend: pil
|
|
- RandCropImage:
|
|
size: 256
|
|
interpolation: bicubic
|
|
backend: pil
|
|
use_log_aspect: True
|
|
- RandFlipImage:
|
|
flip_code: 1
|
|
- RandAugmentV3:
|
|
num_layers: 2
|
|
interpolation: bicubic
|
|
- NormalizeImage:
|
|
scale: 1.0/255.0
|
|
mean: [0.0, 0.0, 0.0]
|
|
std: [1.0, 1.0, 1.0]
|
|
order: ''
|
|
- RandomErasing:
|
|
EPSILON: 0.25
|
|
sl: 0.02
|
|
sh: 1.0/3.0
|
|
r1: 0.3
|
|
attempt: 10
|
|
use_log_aspect: True
|
|
mode: const
|
|
batch_transform_ops:
|
|
- OpSampler:
|
|
MixupOperator:
|
|
alpha: 0.2
|
|
prob: 0.25
|
|
CutmixOperator:
|
|
alpha: 1.0
|
|
prob: 0.25
|
|
sampler:
|
|
name: DistributedBatchSampler
|
|
batch_size: 128
|
|
drop_last: False
|
|
shuffle: True
|
|
loader:
|
|
num_workers: 4
|
|
use_shared_memory: True
|
|
Eval:
|
|
dataset:
|
|
name: ImageNetDataset
|
|
image_root: ./dataset/ILSVRC2012/
|
|
cls_label_path: ./dataset/ILSVRC2012/val_list.txt
|
|
transform_ops:
|
|
- DecodeImage:
|
|
to_np: False
|
|
channel_first: False
|
|
backend: pil
|
|
- ResizeImage:
|
|
resize_short: 288
|
|
interpolation: bicubic
|
|
backend: pil
|
|
- CropImage:
|
|
size: 256
|
|
- NormalizeImage:
|
|
scale: 1.0/255.0
|
|
mean: [0.0, 0.0, 0.0]
|
|
std: [1.0, 1.0, 1.0]
|
|
order: ''
|
|
sampler:
|
|
name: DistributedBatchSampler
|
|
batch_size: 128
|
|
drop_last: False
|
|
shuffle: False
|
|
loader:
|
|
num_workers: 4
|
|
use_shared_memory: True
|
|
|
|
Infer:
|
|
infer_imgs: docs/images/inference_deployment/whl_demo.jpg
|
|
batch_size: 10
|
|
transforms:
|
|
- DecodeImage:
|
|
to_np: False
|
|
channel_first: False
|
|
backend: pil
|
|
- ResizeImage:
|
|
resize_short: 288
|
|
interpolation: bicubic
|
|
backend: pil
|
|
- CropImage:
|
|
size: 256
|
|
- NormalizeImage:
|
|
scale: 1.0/255.0
|
|
mean: [0.0, 0.0, 0.0]
|
|
std: [1.0, 1.0, 1.0]
|
|
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]
|