feat: support PVTV2

ppcls/arch/backbone/__init__.py

@@ -63,6 +63,7 @@ from ppcls.arch.backbone.model_zoo.cspnet import CSPDarkNet53
 from ppcls.arch.backbone.variant_models.resnet_variant import ResNet50_last_stage_stride1
 from ppcls.arch.backbone.variant_models.vgg_variant import VGG19Sigmoid
 from ppcls.arch.backbone.variant_models.pp_lcnet_variant import PPLCNet_x2_5_Tanh
+from ppcls.arch.backbone.model_zoo.pvt_v2 import PVT_V2_B0, PVT_V2_B1, PVT_V2_B2_Linear, PVT_V2_B2, PVT_V2_B3, PVT_V2_B4, PVT_V2_B5
 
 
 # help whl get all the models' api (class type) and components' api (func type)

ppcls/arch/backbone/model_zoo/pvt_v2.py

@@ -0,0 +1,483 @@
+# copyright (c) 2021 PaddlePaddle Authors. All Rights Reserve.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Code was heavily based on https://github.com/whai362/PVT
+
+from functools import partial
+import math
+import paddle
+import paddle.nn as nn
+import paddle.nn.functional as F
+from paddle.nn.initializer import TruncatedNormal, Constant
+
+from .vision_transformer import trunc_normal_, zeros_, ones_, to_2tuple, DropPath, Identity, drop_path
+
+from ppcls.utils.save_load import load_dygraph_pretrain, load_dygraph_pretrain_from_url
+
+MODEL_URLS = {
+    "PVT_V2_B0":
+    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B0_pretrained.pdparams",
+    "PVT_V2_B1":
+    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B1_pretrained.pdparams",
+    "PVT_V2_B2":
+    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B2_pretrained.pdparams",
+    "PVT_V2_B2_Linear":
+    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B2_Linear_pretrained.pdparams",
+    "PVT_V2_B3":
+    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B3_pretrained.pdparams",
+    "PVT_V2_B4":
+    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B4_pretrained.pdparams",
+    "PVT_V2_B5":
+    "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/PVT_V2_B5_pretrained.pdparams",
+}
+
+__all__ = list(MODEL_URLS.keys())
+
+
+def swapdim(x, dim1, dim2):
+    a = list(range(len(x.shape)))
+    a[dim1], a[dim2] = a[dim2], a[dim1]
+    return x.transpose(a)
+
+
+class Mlp(nn.Layer):
+    def __init__(self,
+                 in_features,
+                 hidden_features=None,
+                 out_features=None,
+                 act_layer=nn.GELU,
+                 drop=0.,
+                 linear=False):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Linear(in_features, hidden_features)
+        self.dwconv = DWConv(hidden_features)
+        self.act = act_layer()
+        self.fc2 = nn.Linear(hidden_features, out_features)
+        self.drop = nn.Dropout(drop)
+        self.linear = linear
+        if self.linear:
+            self.relu = nn.ReLU()
+
+    def forward(self, x, H, W):
+        x = self.fc1(x)
+        if self.linear:
+            x = self.relu(x)
+        x = self.dwconv(x, H, W)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x
+
+
+class Attention(nn.Layer):
+    def __init__(self,
+                 dim,
+                 num_heads=8,
+                 qkv_bias=False,
+                 qk_scale=None,
+                 attn_drop=0.,
+                 proj_drop=0.,
+                 sr_ratio=1,
+                 linear=False):
+        super().__init__()
+        assert dim % num_heads == 0, f"dim {dim} should be divided by num_heads {num_heads}."
+
+        self.dim = dim
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+        self.scale = qk_scale or head_dim**-0.5
+
+        self.q = nn.Linear(dim, dim, bias_attr=qkv_bias)
+        self.kv = nn.Linear(dim, dim * 2, bias_attr=qkv_bias)
+        self.attn_drop = nn.Dropout(attn_drop)
+        self.proj = nn.Linear(dim, dim)
+        self.proj_drop = nn.Dropout(proj_drop)
+
+        self.linear = linear
+        self.sr_ratio = sr_ratio
+        if not linear:
+            if sr_ratio > 1:
+                self.sr = nn.Conv2D(
+                    dim, dim, kernel_size=sr_ratio, stride=sr_ratio)
+                self.norm = nn.LayerNorm(dim)
+        else:
+            self.pool = nn.AdaptiveAvgPool2D(7)
+            self.sr = nn.Conv2D(dim, dim, kernel_size=1, stride=1)
+            self.norm = nn.LayerNorm(dim)
+            self.act = nn.GELU()
+
+    def forward(self, x, H, W):
+        B, N, C = x.shape
+        q = self.q(x).reshape(
+            [B, N, self.num_heads, C // self.num_heads]).transpose(
+                [0, 2, 1, 3])
+
+        if not self.linear:
+            if self.sr_ratio > 1:
+                x_ = x.transpose([0, 2, 1]).reshape([B, C, H, W])
+                x_ = self.sr(x_).reshape([B, C, -1]).transpose([0, 2, 1])
+                x_ = self.norm(x_)
+                kv = self.kv(x_).reshape(
+                    [B, -1, 2, self.num_heads, C // self.num_heads]).transpose(
+                        [2, 0, 3, 1, 4])
+            else:
+                kv = self.kv(x).reshape(
+                    [B, -1, 2, self.num_heads, C // self.num_heads]).transpose(
+                        [2, 0, 3, 1, 4])
+        else:
+            x_ = x.transpose([0, 2, 1]).reshape([B, C, H, W])
+            x_ = self.sr(self.pool(x_)).reshape([B, C, -1]).transpose(
+                [0, 2, 1])
+            x_ = self.norm(x_)
+            x_ = self.act(x_)
+            kv = self.kv(x_).reshape(
+                [B, -1, 2, self.num_heads, C // self.num_heads]).transpose(
+                    [2, 0, 3, 1, 4])
+        k, v = kv[0], kv[1]
+
+        attn = (q @swapdim(k, -2, -1)) * self.scale
+        attn = F.softmax(attn, axis=-1)
+        attn = self.attn_drop(attn)
+
+        x = swapdim((attn @v), 1, 2).reshape([B, N, C])
+        x = self.proj(x)
+        x = self.proj_drop(x)
+
+        return x
+
+
+class Block(nn.Layer):
+    def __init__(self,
+                 dim,
+                 num_heads,
+                 mlp_ratio=4.,
+                 qkv_bias=False,
+                 qk_scale=None,
+                 drop=0.,
+                 attn_drop=0.,
+                 drop_path=0.,
+                 act_layer=nn.GELU,
+                 norm_layer=nn.LayerNorm,
+                 sr_ratio=1,
+                 linear=False):
+        super().__init__()
+        self.norm1 = norm_layer(dim)
+        self.attn = Attention(
+            dim,
+            num_heads=num_heads,
+            qkv_bias=qkv_bias,
+            qk_scale=qk_scale,
+            attn_drop=attn_drop,
+            proj_drop=drop,
+            sr_ratio=sr_ratio,
+            linear=linear)
+        # NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
+        self.drop_path = DropPath(drop_path) if drop_path > 0. else Identity()
+        self.norm2 = norm_layer(dim)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = Mlp(in_features=dim,
+                       hidden_features=mlp_hidden_dim,
+                       act_layer=act_layer,
+                       drop=drop,
+                       linear=linear)
+
+    def forward(self, x, H, W):
+        x = x + self.drop_path(self.attn(self.norm1(x), H, W))
+        x = x + self.drop_path(self.mlp(self.norm2(x), H, W))
+
+        return x
+
+
+class OverlapPatchEmbed(nn.Layer):
+    """ Image to Patch Embedding
+    """
+
+    def __init__(self,
+                 img_size=224,
+                 patch_size=7,
+                 stride=4,
+                 in_chans=3,
+                 embed_dim=768):
+        super().__init__()
+        img_size = to_2tuple(img_size)
+        patch_size = to_2tuple(patch_size)
+
+        self.img_size = img_size
+        self.patch_size = patch_size
+        self.H, self.W = img_size[0] // patch_size[0], img_size[
+            1] // patch_size[1]
+        self.num_patches = self.H * self.W
+        self.proj = nn.Conv2D(
+            in_chans,
+            embed_dim,
+            kernel_size=patch_size,
+            stride=stride,
+            padding=(patch_size[0] // 2, patch_size[1] // 2))
+        self.norm = nn.LayerNorm(embed_dim)
+
+    def forward(self, x):
+        x = self.proj(x)
+        _, _, H, W = x.shape
+        x = x.flatten(2)
+        x = swapdim(x, 1, 2)
+        x = self.norm(x)
+
+        return x, H, W
+
+
+class PyramidVisionTransformerV2(nn.Layer):
+    def __init__(self,
+                 img_size=224,
+                 patch_size=16,
+                 in_chans=3,
+                 class_num=1000,
+                 embed_dims=[64, 128, 256, 512],
+                 num_heads=[1, 2, 4, 8],
+                 mlp_ratios=[4, 4, 4, 4],
+                 qkv_bias=False,
+                 qk_scale=None,
+                 drop_rate=0.,
+                 attn_drop_rate=0.,
+                 drop_path_rate=0.,
+                 norm_layer=nn.LayerNorm,
+                 depths=[3, 4, 6, 3],
+                 sr_ratios=[8, 4, 2, 1],
+                 num_stages=4,
+                 linear=False):
+        super().__init__()
+        self.class_num = class_num
+        self.depths = depths
+        self.num_stages = num_stages
+
+        dpr = [x for x in paddle.linspace(0, drop_path_rate, sum(depths))
+               ]  # stochastic depth decay rule
+        cur = 0
+
+        for i in range(num_stages):
+            patch_embed = OverlapPatchEmbed(
+                img_size=img_size if i == 0 else img_size // (2**(i + 1)),
+                patch_size=7 if i == 0 else 3,
+                stride=4 if i == 0 else 2,
+                in_chans=in_chans if i == 0 else embed_dims[i - 1],
+                embed_dim=embed_dims[i])
+
+            block = nn.LayerList([
+                Block(
+                    dim=embed_dims[i],
+                    num_heads=num_heads[i],
+                    mlp_ratio=mlp_ratios[i],
+                    qkv_bias=qkv_bias,
+                    qk_scale=qk_scale,
+                    drop=drop_rate,
+                    attn_drop=attn_drop_rate,
+                    drop_path=dpr[cur + j],
+                    norm_layer=norm_layer,
+                    sr_ratio=sr_ratios[i],
+                    linear=linear) for j in range(depths[i])
+            ])
+            norm = norm_layer(embed_dims[i])
+            cur += depths[i]
+
+            setattr(self, f"patch_embed{i + 1}", patch_embed)
+            setattr(self, f"block{i + 1}", block)
+            setattr(self, f"norm{i + 1}", norm)
+
+        # classification head
+        self.head = nn.Linear(embed_dims[3],
+                              class_num) if class_num > 0 else Identity()
+
+        self.apply(self._init_weights)
+
+    def _init_weights(self, m):
+        if isinstance(m, nn.Linear):
+            trunc_normal_(m.weight)
+            if isinstance(m, nn.Linear) and m.bias is not None:
+                zeros_(m.bias)
+        elif isinstance(m, nn.LayerNorm):
+            zeros_(m.bias)
+            ones_(m.weight)
+
+    def forward_features(self, x):
+        B = x.shape[0]
+
+        for i in range(self.num_stages):
+            patch_embed = getattr(self, f"patch_embed{i + 1}")
+            block = getattr(self, f"block{i + 1}")
+            norm = getattr(self, f"norm{i + 1}")
+            x, H, W = patch_embed(x)
+            for blk in block:
+                x = blk(x, H, W)
+            x = norm(x)
+            if i != self.num_stages - 1:
+                x = x.reshape([B, H, W, -1]).transpose([0, 3, 1, 2])
+
+        return x.mean(axis=1)
+
+    def forward(self, x):
+        x = self.forward_features(x)
+        x = self.head(x)
+
+        return x
+
+
+class DWConv(nn.Layer):
+    def __init__(self, dim=768):
+        super().__init__()
+        self.dwconv = nn.Conv2D(dim, dim, 3, 1, 1, bias_attr=True, groups=dim)
+
+    def forward(self, x, H, W):
+        B, N, C = x.shape
+        x = swapdim(x, 1, 2)
+        x = x.reshape([B, C, H, W])
+        x = self.dwconv(x)
+        x = x.flatten(2)
+        x = swapdim(x, 1, 2)
+
+        return x
+
+
+def _load_pretrained(pretrained, model, model_url, use_ssld=False):
+    if pretrained is False:
+        pass
+    elif pretrained is True:
+        load_dygraph_pretrain_from_url(model, model_url, use_ssld=use_ssld)
+    elif isinstance(pretrained, str):
+        load_dygraph_pretrain(model, pretrained)
+    else:
+        raise RuntimeError(
+            "pretrained type is not available. Please use `string` or `boolean` type."
+        )
+
+
+def PVT_V2_B0(pretrained=False, use_ssld=False, **kwargs):
+    model = PyramidVisionTransformerV2(
+        patch_size=4,
+        embed_dims=[32, 64, 160, 256],
+        num_heads=[1, 2, 5, 8],
+        mlp_ratios=[8, 8, 4, 4],
+        qkv_bias=True,
+        norm_layer=partial(
+            nn.LayerNorm, epsilon=1e-6),
+        depths=[2, 2, 2, 2],
+        sr_ratios=[8, 4, 2, 1],
+        **kwargs)
+    _load_pretrained(
+        pretrained, model, MODEL_URLS["PVT_V2_B0"], use_ssld=use_ssld)
+    return model
+
+
+def PVT_V2_B1(pretrained=False, use_ssld=False, **kwargs):
+    model = PyramidVisionTransformerV2(
+        patch_size=4,
+        embed_dims=[64, 128, 320, 512],
+        num_heads=[1, 2, 5, 8],
+        mlp_ratios=[8, 8, 4, 4],
+        qkv_bias=True,
+        norm_layer=partial(
+            nn.LayerNorm, epsilon=1e-6),
+        depths=[2, 2, 2, 2],
+        sr_ratios=[8, 4, 2, 1],
+        **kwargs)
+    _load_pretrained(
+        pretrained, model, MODEL_URLS["PVT_V2_B1"], use_ssld=use_ssld)
+    return model
+
+
+def PVT_V2_B2(pretrained=False, use_ssld=False, **kwargs):
+    model = PyramidVisionTransformerV2(
+        patch_size=4,
+        embed_dims=[64, 128, 320, 512],
+        num_heads=[1, 2, 5, 8],
+        mlp_ratios=[8, 8, 4, 4],
+        qkv_bias=True,
+        norm_layer=partial(
+            nn.LayerNorm, epsilon=1e-6),
+        depths=[3, 4, 6, 3],
+        sr_ratios=[8, 4, 2, 1],
+        **kwargs)
+    _load_pretrained(
+        pretrained, model, MODEL_URLS["PVT_V2_B2"], use_ssld=use_ssld)
+    return model
+
+
+def PVT_V2_B3(pretrained=False, use_ssld=False, **kwargs):
+    model = PyramidVisionTransformerV2(
+        patch_size=4,
+        embed_dims=[64, 128, 320, 512],
+        num_heads=[1, 2, 5, 8],
+        mlp_ratios=[8, 8, 4, 4],
+        qkv_bias=True,
+        norm_layer=partial(
+            nn.LayerNorm, epsilon=1e-6),
+        depths=[3, 4, 18, 3],
+        sr_ratios=[8, 4, 2, 1],
+        **kwargs)
+    _load_pretrained(
+        pretrained, model, MODEL_URLS["PVT_V2_B3"], use_ssld=use_ssld)
+    return model
+
+
+def PVT_V2_B4(pretrained=False, use_ssld=False, **kwargs):
+    model = PyramidVisionTransformerV2(
+        patch_size=4,
+        embed_dims=[64, 128, 320, 512],
+        num_heads=[1, 2, 5, 8],
+        mlp_ratios=[8, 8, 4, 4],
+        qkv_bias=True,
+        norm_layer=partial(
+            nn.LayerNorm, epsilon=1e-6),
+        depths=[3, 8, 27, 3],
+        sr_ratios=[8, 4, 2, 1],
+        **kwargs)
+    _load_pretrained(
+        pretrained, model, MODEL_URLS["PVT_V2_B4"], use_ssld=use_ssld)
+    return model
+
+
+def PVT_V2_B5(pretrained=False, use_ssld=False, **kwargs):
+    model = PyramidVisionTransformerV2(
+        patch_size=4,
+        embed_dims=[64, 128, 320, 512],
+        num_heads=[1, 2, 5, 8],
+        mlp_ratios=[4, 4, 4, 4],
+        qkv_bias=True,
+        norm_layer=partial(
+            nn.LayerNorm, epsilon=1e-6),
+        depths=[3, 6, 40, 3],
+        sr_ratios=[8, 4, 2, 1],
+        **kwargs)
+    _load_pretrained(
+        pretrained, model, MODEL_URLS["PVT_V2_B5"], use_ssld=use_ssld)
+    return model
+
+
+def PVT_V2_B2_Linear(pretrained=False, use_ssld=False, **kwargs):
+    model = PyramidVisionTransformerV2(
+        patch_size=4,
+        embed_dims=[64, 128, 320, 512],
+        num_heads=[1, 2, 5, 8],
+        mlp_ratios=[8, 8, 4, 4],
+        qkv_bias=True,
+        norm_layer=partial(
+            nn.LayerNorm, epsilon=1e-6),
+        depths=[3, 4, 6, 3],
+        sr_ratios=[8, 4, 2, 1],
+        linear=True,
+        **kwargs)
+    _load_pretrained(
+        pretrained, model, MODEL_URLS["PVT_V2_B2_Linear"], use_ssld=use_ssld)
+    return model

ppcls/configs/ImageNet/PVTV2/pvt_v2_b0.yaml

@@ -0,0 +1,161 @@
+# 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_B0
+  class_num: 1000
+  drop_path_rate: 0.1
+  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
+  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]

ppcls/configs/ImageNet/PVTV2/pvt_v2_b1.yaml

@@ -0,0 +1,161 @@
+# 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_B1
+  class_num: 1000
+  drop_path_rate: 0.1
+  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
+  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]

ppcls/configs/ImageNet/PVTV2/pvt_v2_b2.yaml

@@ -0,0 +1,161 @@
+# 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_B2
+  class_num: 1000
+  drop_path_rate: 0.1
+  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
+  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]

ppcls/configs/ImageNet/PVTV2/pvt_v2_b2_linear.yaml

@@ -0,0 +1,161 @@
+# 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_B2_Linear
+  class_num: 1000
+  drop_path_rate: 0.1
+  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
+  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]

ppcls/configs/ImageNet/PVTV2/pvt_v2_b3.yaml

@@ -0,0 +1,162 @@
+# 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_B3
+  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]

ppcls/configs/ImageNet/PVTV2/pvt_v2_b4.yaml

@@ -0,0 +1,162 @@
+# 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]

ppcls/configs/ImageNet/PVTV2/pvt_v2_b5.yaml

@@ -0,0 +1,162 @@
+# 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_B5
+  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]