diff --git a/configs/ResNeSt/ResNeSt101.yaml b/configs/ResNeSt/ResNeSt101.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..1881f41cc954ca1bb79658cc1b4dee97297ff9b2
--- /dev/null
+++ b/configs/ResNeSt/ResNeSt101.yaml
@@ -0,0 +1,78 @@
+mode: 'train'
+ARCHITECTURE:
+    name: 'ResNeSt101'
+
+pretrained_model: ""
+model_save_dir: "./output/"
+classes_num: 1000
+total_images: 1281167
+save_interval: 1
+validate: True
+valid_interval: 1
+epochs: 300
+topk: 5
+image_shape: [3, 224, 224]
+
+use_mix: True
+ls_epsilon: 0.1
+
+LEARNING_RATE:
+    function: 'CosineWarmup'          
+    params:                   
+        lr: 0.1               
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000070
+
+TRAIN:
+    batch_size: 256
+    num_workers: 4
+    file_list: "./dataset/ILSVRC2012/train_list.txt"
+    data_dir: "./dataset/ILSVRC2012/"
+    shuffle_seed: 0
+    transforms:
+        - DecodeImage:
+            to_rgb: True
+            to_np: False
+            channel_first: False
+        - RandCropImage:
+            size: 224
+        - RandFlipImage:
+            flip_code: 1
+        - AutoAugment:
+        - NormalizeImage:
+            scale: 1./255.
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - ToCHWImage:
+    mix:                       
+        - CutmixOperator:    
+            alpha: 0.2      
+
+VALID:
+    batch_size: 64
+    num_workers: 4
+    file_list: "./dataset/ILSVRC2012/val_list.txt"
+    data_dir: "./dataset/ILSVRC2012/"
+    shuffle_seed: 0
+    transforms:
+        - DecodeImage:
+            to_rgb: True
+            to_np: False
+            channel_first: False
+        - ResizeImage:
+            resize_short: 288
+        - 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:
diff --git a/ppcls/modeling/architectures/__init__.py b/ppcls/modeling/architectures/__init__.py
index 3c166ebb3420f8b1abb5c7238c739024ca9e83f0..73d9646ef3fbaf91b9ec502eb50dc164c829a650 100644
--- a/ppcls/modeling/architectures/__init__.py
+++ b/ppcls/modeling/architectures/__init__.py
@@ -26,7 +26,7 @@ from .dpn import DPN68, DPN92, DPN98, DPN107, DPN131
 from .densenet import DenseNet121, DenseNet161, DenseNet169, DenseNet201, DenseNet264
 from .hrnet import HRNet_W18_C, HRNet_W30_C, HRNet_W32_C, HRNet_W40_C, HRNet_W44_C, HRNet_W48_C, HRNet_W60_C, HRNet_W64_C, SE_HRNet_W18_C, SE_HRNet_W30_C, SE_HRNet_W32_C, SE_HRNet_W40_C, SE_HRNet_W44_C, SE_HRNet_W48_C, SE_HRNet_W60_C, SE_HRNet_W64_C
 from .efficientnet import EfficientNetB0, EfficientNetB1, EfficientNetB2, EfficientNetB3, EfficientNetB4, EfficientNetB5, EfficientNetB6, EfficientNetB7
-from .resnest import ResNeSt50_fast_1s1x64d, ResNeSt50
+from .resnest import ResNeSt50_fast_1s1x64d, ResNeSt50, ResNeSt101
 from .googlenet import GoogLeNet
 from .ghostnet import GhostNet_x0_5, GhostNet_x1_0, GhostNet_x1_3
 from .mobilenet_v1 import MobileNetV1_x0_25, MobileNetV1_x0_5, MobileNetV1_x0_75, MobileNetV1
diff --git a/ppcls/modeling/architectures/resnest.py b/ppcls/modeling/architectures/resnest.py
index 88465d521d05ea85acc27955d553a78fd4830945..0820ba2866dd889ed0ba3996c22b668c67487608 100644
--- a/ppcls/modeling/architectures/resnest.py
+++ b/ppcls/modeling/architectures/resnest.py
@@ -27,7 +27,7 @@ from paddle.nn import Conv2D, BatchNorm, Linear, Dropout
 from paddle.nn import AdaptiveAvgPool2D, MaxPool2D, AvgPool2D
 from paddle.regularizer import L2Decay
 
-__all__ = ["ResNeSt50_fast_1s1x64d", "ResNeSt50"]
+__all__ = ["ResNeSt50_fast_1s1x64d", "ResNeSt50", "ResNeSt101"]
 
 
 class ConvBNLayer(nn.Layer):
@@ -685,3 +685,19 @@ def ResNeSt50(**args):
         final_drop=0.0,
         **args)
     return model
+
+
+def ResNeSt101(**args):
+    model = ResNeSt(
+        layers=[3, 4, 23, 3],
+        radix=2,
+        groups=1,
+        bottleneck_width=64,
+        deep_stem=True,
+        stem_width=64,
+        avg_down=True,
+        avd=True,
+        avd_first=False,
+        final_drop=0.0,
+        **args)
+    return model