PaddleClas/ppcls/configs/ImageNet/PVTV2/pvt_v2_b4.yaml

163 lines
3.6 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, 224, 224]
save_inference_dir: ./inference
# training model under @to_static
to_static: False
# model architecture
Arch:
name: PVT_V2_B4
class_num: 1000
drop_path_rate: 0.3
drop_rate: 0.0
# 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
clip_grad: 1.0
no_weight_decay_name: pos_embed1 pos_embed2 pos_embed3 pos_embed4 cls_token
one_dim_param_no_weight_decay: True
lr:
name: Cosine
learning_rate: 1e-3
eta_min: 1e-5
warmup_epoch: 20
warmup_start_lr: 1e-6
# 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
- RandCropImage:
size: 224
interpolation: bicubic
backend: pil
- RandFlipImage:
flip_code: 1
- TimmAutoAugment:
config_str: rand-m9-mstd0.5-inc1
interpolation: bicubic
img_size: 224
- NormalizeImage:
scale: 1.0/255.0
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: ''
- RandomErasing:
EPSILON: 0.25
sl: 0.02
sh: 1.0/3.0
r1: 0.3
attempt: 10
use_log_aspect: True
mode: pixel
batch_transform_ops:
- OpSampler:
MixupOperator:
alpha: 0.8
prob: 0.5
CutmixOperator:
alpha: 1.0
prob: 0.5
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_rgb: True
channel_first: False
- ResizeImage:
resize_short: 256
interpolation: bicubic
backend: pil
- CropImage:
size: 224
- NormalizeImage:
scale: 1.0/255.0
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: 4
use_shared_memory: True
Infer:
infer_imgs: docs/images/whl/demo.jpg
batch_size: 10
transforms:
- DecodeImage:
to_rgb: True
channel_first: False
- ResizeImage:
resize_short: 256
interpolation: bicubic
backend: pil
- 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:
Eval:
- TopkAcc:
topk: [1, 5]