diff --git a/configs/mmseg/segmentation_ncnn-int8_static-1024x2048.py b/configs/mmseg/segmentation_ncnn-int8_static-1024x2048.py
new file mode 100644
index 000000000..9dc64ee02
--- /dev/null
+++ b/configs/mmseg/segmentation_ncnn-int8_static-1024x2048.py
@@ -0,0 +1,3 @@
+_base_ = ['./segmentation_static.py', '../_base_/backends/ncnn-int8.py']
+
+onnx_config = dict(input_shape=[2048, 1024])
diff --git a/docs/en/03-benchmark/quantization.md b/docs/en/03-benchmark/quantization.md
index 8e3d101fe..6e9cbab00 100644
--- a/docs/en/03-benchmark/quantization.md
+++ b/docs/en/03-benchmark/quantization.md
@@ -47,3 +47,14 @@ Note: MMPose models are tested with `flip_test` explicitly set to `False` in mod
 | :-----------------------------------------------------------------------------------------------------------------: | :-----: | :------------: | :------------: |
 | [EDSRx2](https://github.com/open-mmlab/mmediting/blob/master/configs/restorers/edsr/edsr_x2c64b16_g1_300k_div2k.py) |  Set5   | 35.7733/0.9365 | 35.4266/0.9334 |
 | [EDSRx4](https://github.com/open-mmlab/mmediting/blob/master/configs/restorers/edsr/edsr_x4c64b16_g1_300k_div2k.py) |  Set5   | 30.2194/0.8498 | 29.9340/0.8409 |
+
+### mmseg
+
+|                                                             model                                                              |  dataset   | fp32 mIoU | int8 mIoU |
+| :----------------------------------------------------------------------------------------------------------------------------: | :--------: | :-------: | :-------: |
+| [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py) | cityscapes |   70.96   |   70.24   |
+
+Note:
+
+- Int8 models of the Fast-SCNN requires ncnnoptimize.
+- NCNN will extract 512 images from the train as a calibration dataset
diff --git a/docs/zh_cn/03-benchmark/quantization.md b/docs/zh_cn/03-benchmark/quantization.md
index ee6a8c06c..a4ff31b13 100644
--- a/docs/zh_cn/03-benchmark/quantization.md
+++ b/docs/zh_cn/03-benchmark/quantization.md
@@ -47,3 +47,14 @@
 | :-----------------------------------------------------------------------------------------------------------------: | :-----: | :------------: | :------------: |
 |  [EDSR](https://github.com/open-mmlab/mmediting/blob/master/configs/restorers/edsr/edsr_x2c64b16_g1_300k_div2k.py)  |  Set5   | 35.7733/0.9365 | 35.4266/0.9334 |
 | [EDSRx4](https://github.com/open-mmlab/mmediting/blob/master/configs/restorers/edsr/edsr_x4c64b16_g1_300k_div2k.py) |  Set5   | 30.2194/0.8498 | 29.9340/0.8409 |
+
+### 语义分割任务
+
+|                                                             model                                                              |  dataset   | fp32 mIoU | int8 mIoU |
+| :----------------------------------------------------------------------------------------------------------------------------: | :--------: | :-------: | :-------: |
+| [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py) | cityscapes |   70.96   |   70.24   |
+
+备注：
+
+- Fast-SCNN 的int8模型需要使用ncnnoptimize优化。
+- NCNN将会从train中抽取512张图片作为校准集。
diff --git a/mmdeploy/pytorch/functions/interpolate.py b/mmdeploy/pytorch/functions/interpolate.py
index 253b59316..9cc016ed8 100644
--- a/mmdeploy/pytorch/functions/interpolate.py
+++ b/mmdeploy/pytorch/functions/interpolate.py
@@ -22,13 +22,16 @@ def interpolate__ncnn(ctx,
     """Rewrite `interpolate` for ncnn backend.
 
     ncnn require `size` should be constant in ONNX Node. We use `scale_factor`
-    instead of `size` to avoid dynamic size.
+    instead of `size` to avoid dynamic size. To avoid rounding errors, add a
+    small number when `scale_factor` is not an integer
     """
 
     input_size = input.shape
     if scale_factor is None:
         scale_factor = [
-            s_out / s_in for s_out, s_in in zip(size, input_size[2:])
+            s_out / s_in if int(s_out / s_in) == s_out / s_in else
+            (s_out / s_in + 0.00001)
+            for s_out, s_in in zip(size, input_size[2:])
         ]
 
     return ctx.origin_func(
diff --git a/mmdeploy/pytorch/ops/adaptive_pool.py b/mmdeploy/pytorch/ops/adaptive_pool.py
index d27049576..340cbccd4 100644
--- a/mmdeploy/pytorch/ops/adaptive_pool.py
+++ b/mmdeploy/pytorch/ops/adaptive_pool.py
@@ -10,4 +10,8 @@ def adaptive_avg_pool2d__ncnn(ctx, g, x, output_size):
 
     Align symbolic of adaptive_avg_pool2d in ncnn.
     """
-    return g.op('mmdeploy::AdaptiveAvgPool2d', x, output_size)
+    size = getattr(output_size.node(), 't')('value').tolist()
+    if size != [1, 1]:
+        return g.op('mmdeploy::AdaptiveAvgPool2d', x, output_size)
+    else:
+        return g.op('GlobalAveragePool', x)