update README

c71d1885 · qianyj · 3d61d6b3 · c71d1885
Commit c71d1885 authored Mar 30, 2023 by qianyj
Hide whitespace changes
Inline Side-by-side

Showing with 48 additions and 30 deletions

README.md README.md +48 -30

No files found.
--- a/README.md
+++ b/README.md
-# 模型名称(此处需修改，用英文全称与简写)
+# 模型名称
 ## 模型介绍
 使用TensorFlow2进行ResNet50的训练
 ## 模型结构
@@ -11,80 +11,98 @@ ImageNet数据集转成TFRecord格式，可以参考以下[script](https://githu
 ## 训练
 ### 环境配置
 使用[光源](https://www.sourcefind.cn/#/service-details)拉取训练的docker镜像：
-* 训练镜像：docker pull image.sourcefind.cn:5000/dcu/admin/base/tensorflow:2.7.0-centos7.6-dtk-22.10.1-py37-latest
+训练镜像：docker pull image.sourcefind.cn:5000/dcu/admin/base/tensorflow:2.7.0-centos7.6-dtk-22.10.1-py37-latest

 python依赖安装：

    pip install -r requirement.txt
 ### fp32训练
 #### 单机单卡训练命令：
+
 不打开xla:
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH  
-python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=128 --num_gpus=1  --use_synthetic_data=false --dtype=fp32
+
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH  
+    python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=128 --num_gpus=1  --use_synthetic_data=false --dtype=fp32

 打开xla:
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
-TF_XLA_FLAGS="--tf_xla_auto_jit=2" python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=128 --num_gpus=1  --use_synthetic_data=false --dtype=fp32
+
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
+    TF_XLA_FLAGS="--tf_xla_auto_jit=2" python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=128 --num_gpus=1  --use_synthetic_data=false --dtype=fp32

 #### 单机四卡训练指令：
 不打开xla:
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
-python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=512 --num_gpus=4  --use_synthetic_data=false --dtype=fp32
+
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
+    python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=512 --num_gpus=4  --use_synthetic_data=false --dtype=fp32

 打开xla:
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
-TF_XLA_FLAGS="--tf_xla_auto_jit=2" python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=512 --num_gpus=4  --use_synthetic_data=false --dtype=fp32
+
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
+    TF_XLA_FLAGS="--tf_xla_auto_jit=2" python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=512 --num_gpus=4  --use_synthetic_data=false --dtype=fp32

 #### 多机多卡训练指令(以单机四卡模拟四卡四进程为例)：
+
 sed指令只需要执行一次，添加支持多卡运行的代码
-sed -i '100 r configfile' models-master/official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py
+    sed -i '100 r configfile' models-master/official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py

 不打开xla：
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
-mpirun -np 4 --hostfile hostfile  -mca btl self,tcp  --allow-run-as-root  --bind-to none scripts-run/single_process.sh
+
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
+    mpirun -np 4 --hostfile hostfile  -mca btl self,tcp  --allow-run-as-root  --bind-to none scripts-run/single_process.sh

 打开xla：
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
-mpirun -np 4 --hostfile hostfile  -mca btl self,tcp  --allow-run-as-root  --bind-to none scripts-run/single_process_xla.sh
+
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
+    mpirun -np 4 --hostfile hostfile  -mca btl self,tcp  --allow-run-as-root  --bind-to none scripts-run/single_process_xla.sh
    
 ### fp16训练
 #### 单机单卡训练指令
+
 不打开xla：
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
-python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=128 --num_gpus=1  --use_synthetic_data=false --dtype=fp16
+   
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
+    python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=128 --num_gpus=1  --use_synthetic_data=false --dtype=fp16

 打开xla：
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
-TF_XLA_FLAGS="--tf_xla_auto_jit=2" python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=128 --num_gpus=1  --use_synthetic_data=false --dtype=fp16
+  
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
+    TF_XLA_FLAGS="--tf_xla_auto_jit=2" python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=128 --num_gpus=1  --use_synthetic_data=false --dtype=fp16

 #### 单机四卡训练指令
+
 不打开xla:
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
-python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=512 --num_gpus=4  --use_synthetic_data=false --dtype=fp16
+  
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
+    python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=512 --num_gpus=4  --use_synthetic_data=false --dtype=fp16

 打开xla：
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
-TF_XLA_FLAGS="--tf_xla_auto_jit=2" python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=512 --num_gpus=4  --use_synthetic_data=false --dtype=fp16
+
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
+    TF_XLA_FLAGS="--tf_xla_auto_jit=2" python3 official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py --data_dir=/path/to/{ImageNet-tensorflow_data_dir} --model_dir=/path/to/{model_save_dir} --batch_size=512 --num_gpus=4  --use_synthetic_data=false --dtype=fp16

 #### 多机多卡训练指令(以单机四卡模拟四卡四进程为例)
+
 sed指令只需要执行一次，添加支持多卡运行的代码
-sed -i '100 r configfile' models-master/official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py
+    sed -i '100 r configfile' models-master/official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py
 修改scripts-run/single_process.sh和scripts-run/single_process_xla.sh文件里的--dtype=fp16

 不打开xla:
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
-mpirun -np 4 --hostfile hostfile  -mca btl self,tcp  --allow-run-as-root  --bind-to none scripts-run/single_process.sh
+
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
+    mpirun -np 4 --hostfile hostfile  -mca btl self,tcp  --allow-run-as-root  --bind-to none scripts-run/single_process.sh
+
 打开xla：
-export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
-mpirun -np 4 --hostfile hostfile  -mca btl self,tcp  --allow-run-as-root  --bind-to none scripts-run/single_process_xla.sh
+
+    export PYTHONPATH=/path/to/ResNet50_TensorFlow2:$PYTHONPATH
+    mpirun -np 4 --hostfile hostfile  -mca btl self,tcp  --allow-run-as-root  --bind-to none scripts-run/single_process_xla.sh


 ## 性能和准确率数据
 测试数据：[ImageNet的测试数据集](https://image-net.org/ "ImageNet数据集官网")，使用的加速卡:DCU-Z00-16G

 根据模型情况填写表格：
-| 卡数 | batch size | 类型 | 性能 | Accuracy | 是否打开xla | | 进程数 |
-| :------: | :------: | :------: | :------: |:------: |
+| 卡数 | batch size | 类型 | 性能 | Accuracy | 是否打开xla | 进程数 |
+| :------: | :------: | :------: | :------: |:------: | :------: |
 | 4 | 512 | fp32 | 843 examples/second | 0.7628 | 否 | 单进程 |
 | 4 | 512 | fp16 | - | 0.7616 | 否 | 单进程 |
 | 4 | 512 | fp32 | - | 0.7608 | 否 | 四进程 |