add swinv2

ppcls/arch/backbone/model_zoo/swin_transformer_v2.py

@@ -883,8 +883,7 @@ def SwinTransformerV2_base_patch4_window8_256(pretrained=False,
         pretrained,
         model,
         MODEL_URLS["SwinTransformerV2_base_patch4_window8_256"],
-        use_ssld=use_ssld,
-        use_imagenet22k_pretrained=use_imagenet22k_pretrained)
+        use_ssld=use_ssld)
     return model
 
 

ppcls/configs/ImageNet/SwinTransformerV2/SwinTransformerV2_base_patch4_window12to16_256.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
-  # training model under @to_static
-  to_static: False
-
-# model architecture
-Arch:
-  name:  SwinTransformerV2_base_patch4_window12to16_256
-  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: 0.05
-  no_weight_decay_name: absolute_pos_embed relative_position_bias_table .bias norm 
-  one_dim_param_no_weight_decay: True
-  lr:
-    # for 8 cards
-    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: 256
-            interpolation: bicubic
-            backend: pil
-        - RandFlipImage:
-            flip_code: 1
-        - TimmAutoAugment:
-            config_str: rand-m9-mstd0.5-inc1
-            interpolation: bicubic
-            img_size: 256
-        - 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: 292
-            interpolation: bicubic
-            backend: pil
-        - CropImage:
-            size: 256
-        - 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/inference_deployment/whl_demo.jpg
-  batch_size: 10
-  transforms:
-    - DecodeImage:
-        to_rgb: True
-        channel_first: False
-    - ResizeImage:
-        resize_short: 292
-        interpolation: bicubic
-        backend: pil
-    - CropImage:
-        size: 256
-    - 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]

test_tipc/configs/SwinTransformerV2/SwinTransformerV2_base_patch4_window12to16_256_train_infer_python.txt

-===========================train_params===========================
-model_name:SwinTransformerV2_base_patch4_window12to16_256
-python:python3.7
-gpu_list:0|0,1
--o Global.device:gpu
--o Global.auto_cast:null
--o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120
--o Global.output_dir:./output/
--o DataLoader.Train.sampler.batch_size:8
--o Global.pretrained_model:null
-train_model_name:latest
-train_infer_img_dir:./dataset/ILSVRC2012/val
-null:null
-##
-trainer:norm_train
-norm_train:tools/train.py -c ppcls/configs/ImageNet/SwinTransformerV2/SwinTransformerV2_base_patch4_window12to16_256.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.eval_during_train=False -o Global.save_interval=2
-pact_train:null
-fpgm_train:null
-distill_train:null
-null:null
-null:null
-##
-===========================eval_params=========================== 
-eval:tools/eval.py -c ppcls/configs/ImageNet/SwinTransformerV2/SwinTransformerV2_base_patch4_window12to16_256.yaml
-null:null
-##
-===========================infer_params==========================
--o Global.save_inference_dir:./inference
--o Global.pretrained_model:
-norm_export:tools/export_model.py -c ppcls/configs/ImageNet/SwinTransformerV2/SwinTransformerV2_base_patch4_window12to16_256.yaml
-quant_export:null
-fpgm_export:null
-distill_export:null
-kl_quant:null
-export2:null
-pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SwinTransformerV2_base_patch4_window12to16_256_22kto1k_pretrained.pdparams
-infer_model:../inference/
-infer_export:True
-infer_quant:Fasle
-inference:python/predict_cls.py -c configs/inference_cls.yaml
--o Global.use_gpu:True|False
--o Global.enable_mkldnn:False
--o Global.cpu_num_threads:1
--o Global.batch_size:1
--o Global.use_tensorrt:False
--o Global.use_fp16:False
--o Global.inference_model_dir:../inference
--o Global.infer_imgs:../dataset/ILSVRC2012/val/ILSVRC2012_val_00000001.JPEG
--o Global.save_log_path:null
--o Global.benchmark:False
-null:null
-null:null
-===========================train_benchmark_params==========================
-batch_size:104|128
-fp_items:fp32|fp16
-epoch:1
---profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
-flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
-===========================infer_benchmark_params==========================
-random_infer_input:[{float32,[3,256,256]}]
\ No newline at end of file