diff --git a/training/kunlunxin/faster_rcnn-pytorch/README.md b/training/kunlunxin/faster_rcnn-pytorch/README.md
new file mode 100644
index 000000000..8035e3b89
--- /dev/null
+++ b/training/kunlunxin/faster_rcnn-pytorch/README.md
@@ -0,0 +1,46 @@
+### 模型Checkpoint下载
+[模型Checkpoint下载](../../benchmarks/faster_rcnn/README.md#Resnet50预训练权重)
+### 测试数据集下载
+[测试数据集下载](../../benchmarks/faster_rcnn/README.md#数据集)
+
+### 昆仑芯XPU配置与运行信息参考
+#### 环境配置
+- ##### 硬件环境
+  - 机器型号: 昆仑芯AI加速器组R480-X8
+  - 加速卡型号: 昆仑芯AI加速卡R300
+  - 多机网络类型、带宽: InfiniBand，200Gb/s
+
+- ##### 软件环境
+  - OS版本：Ubuntu 20.04
+  - OS kernel版本: 5.4.0-26-generic
+  - 加速卡驱动版本：4.0.25
+  - Docker镜像和版本：pytorch1.12.1-cpu-ubuntu18.04:v0.04
+  - 训练框架版本：xmlir+e70db8f6
+  - 依赖软件版本：pytorch-1.12.1+cpu
+
+
+* 通用指标
+
+| 指标名称       | 指标值                  | 特殊说明                                    |
+|--------------|-------------------------|---------------------------------------------|
+| 任务类别       | 图像目标检测            |                                             |
+| 模型           | fasterRCNN              |                                             |
+| 数据集         | coco2017                |                                             |
+| 数据精度       | precision,见“性能指标”  | 可选fp32/amp/fp16                           |
+| 超参修改       | fix_hp,见“性能指标”     | 跑满硬件设备评测吞吐量所需特殊超参          |
+| 硬件设备简称   | kunlunxin R300           |                                             |
+| 硬件存储使用   | mem,见“性能指标”        | 通常称为“显存”,单位为GiB                    |
+| 端到端时间     | e2e_time,见“性能指标”   | 总时间+Perf初始化等时间                     |
+| 总吞吐量       | p_whole,见“性能指标”    | 实际训练图片数除以总时间(performance_whole) |
+| 训练吞吐量     | p_train,见“性能指标”    | 不包含每个epoch末尾的评估部分耗时           |
+| **计算吞吐量** | **p_core,见“性能指标”** | 不包含数据IO部分的耗时(p3>p2>p1)            |
+| 训练结果       | map,见“性能指标”        | 单位为平均目标检测正确率                    |
+| 额外修改项     | 无                      |                                             |
+
+* 性能指标
+
+| 配置             | precision | fix_hp        | e2e_time | p_whole | p_train | p_core | map   | mem       |
+|----------------|-----------|---------------|----------|---------|---------|--------|-------|-----------|
+| R300单机单卡（1x1） | fp32      | bs=16,lr=0.16 |          |         |         |        |       | 17.0/32.0 |
+| R300单机8卡（1x8） | fp32      | bs=16,lr=0.16 |          |         |         |        | 36.4% | 28.0/32.0 |
+| R300两机8卡（2x8） | fp32      | bs=16,lr=0.16 |          |         |         |        |       | 15.0/32.0 |
diff --git a/training/kunlunxin/faster_rcnn-pytorch/config/config_R200x1x1.py b/training/kunlunxin/faster_rcnn-pytorch/config/config_R200x1x1.py
deleted file mode 100644
index 23f715329..000000000
--- a/training/kunlunxin/faster_rcnn-pytorch/config/config_R200x1x1.py
+++ /dev/null
@@ -1,4 +0,0 @@
-vendor: str = "kunlunxin"
-train_batch_size = 8
-eval_batch_size = 8
-lr = 0.16
diff --git a/training/kunlunxin/faster_rcnn-pytorch/config/config_R200x1x8.py b/training/kunlunxin/faster_rcnn-pytorch/config/config_R200x1x8.py
deleted file mode 100644
index 23f715329..000000000
--- a/training/kunlunxin/faster_rcnn-pytorch/config/config_R200x1x8.py
+++ /dev/null
@@ -1,4 +0,0 @@
-vendor: str = "kunlunxin"
-train_batch_size = 8
-eval_batch_size = 8
-lr = 0.16
diff --git a/training/kunlunxin/faster_rcnn-pytorch/config/config_R200x2x8.py b/training/kunlunxin/faster_rcnn-pytorch/config/config_R200x2x8.py
deleted file mode 100644
index 23f715329..000000000
--- a/training/kunlunxin/faster_rcnn-pytorch/config/config_R200x2x8.py
+++ /dev/null
@@ -1,4 +0,0 @@
-vendor: str = "kunlunxin"
-train_batch_size = 8
-eval_batch_size = 8
-lr = 0.16
diff --git a/training/kunlunxin/faster_rcnn-pytorch/config/config_R300x1x1.py b/training/kunlunxin/faster_rcnn-pytorch/config/config_R300x1x1.py
new file mode 100644
index 000000000..e9d4cb6ca
--- /dev/null
+++ b/training/kunlunxin/faster_rcnn-pytorch/config/config_R300x1x1.py
@@ -0,0 +1,4 @@
+vendor: str = "kunlunxin"
+train_batch_size = 16
+eval_batch_size = 16
+lr = 0.16
diff --git a/training/kunlunxin/faster_rcnn-pytorch/config/config_R300x1x8.py b/training/kunlunxin/faster_rcnn-pytorch/config/config_R300x1x8.py
new file mode 100644
index 000000000..e9d4cb6ca
--- /dev/null
+++ b/training/kunlunxin/faster_rcnn-pytorch/config/config_R300x1x8.py
@@ -0,0 +1,4 @@
+vendor: str = "kunlunxin"
+train_batch_size = 16
+eval_batch_size = 16
+lr = 0.16
diff --git a/training/kunlunxin/faster_rcnn-pytorch/config/config_R300x2x8.py b/training/kunlunxin/faster_rcnn-pytorch/config/config_R300x2x8.py
new file mode 100644
index 000000000..e9d4cb6ca
--- /dev/null
+++ b/training/kunlunxin/faster_rcnn-pytorch/config/config_R300x2x8.py
@@ -0,0 +1,4 @@
+vendor: str = "kunlunxin"
+train_batch_size = 16
+eval_batch_size = 16
+lr = 0.16
diff --git a/training/nvidia/faster_rcnn-pytorch/README.md b/training/nvidia/faster_rcnn-pytorch/README.md
index 27b5d3b73..ac83f7e65 100644
--- a/training/nvidia/faster_rcnn-pytorch/README.md
+++ b/training/nvidia/faster_rcnn-pytorch/README.md
@@ -55,5 +55,5 @@ torchvision.models.resnet.__dict__['model_urls'][
 | ------------------ | --------- | ---- | ---- | ---- | ---- | ---- |  ---- | ---- |
 | A100单机8卡（1x8） | fp32 | / | 14086 | 144     | 150 | 199 | 37.0% | 7.9/40.0 |
 | A100单机8卡（1x8） | fp32 | bs=16,lr=0.16 | 11848 | 187 | 199 | 298 | 36.6% | 38.8/40.0 |
-| A100单机8卡（1x1） | fp32 | bs=16,lr=0.16 |  | 26 | 27    | 45 |  |33.7/40.0 |
+| A100单机单卡（1x1） | fp32 | bs=16,lr=0.16 |  | 26 | 27    | 45 |  |33.7/40.0 |
 | A100两机8卡（2x8） | fp32 | bs=16,lr=0.16 |  | 351 | 383    | 601 |  | 39.0/40.0 |