From a585ffe6a28c3ce87bb3ca3b7b3a141982632d14 Mon Sep 17 00:00:00 2001 From: jiangxing001 <1484736931@qq.com> Date: Fri, 24 Mar 2023 01:27:20 +0000 Subject: [PATCH 1/2] update TensorFlow/built-in/cv/image_classification/InceptionV3_ID0504_for_TensorFlow/README.md. Signed-off-by: jiangxing001 <1484736931@qq.com> --- .../InceptionV3_ID0504_for_TensorFlow/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/TensorFlow/built-in/cv/image_classification/InceptionV3_ID0504_for_TensorFlow/README.md b/TensorFlow/built-in/cv/image_classification/InceptionV3_ID0504_for_TensorFlow/README.md index cf73504a1..f74011f5e 100644 --- a/TensorFlow/built-in/cv/image_classification/InceptionV3_ID0504_for_TensorFlow/README.md +++ b/TensorFlow/built-in/cv/image_classification/InceptionV3_ID0504_for_TensorFlow/README.md @@ -162,14 +162,14 @@ InceptionV4是2016年提出的Inception系列网络的第四个版本，随着Re 3. 8卡训练 - 3.1 配置run_8p.sh脚本中`data_dir`（脚本路径InceptionV3_for_TensorFlow/script/run_8p.sh）,请用户根据实际路径配置，数据集参数如下所示： + 3.1 配置train_performance_8p.sh脚本中`data_dir`（脚本路径InceptionV3_for_TensorFlow/test下）,请用户根据实际路径配置，数据集参数如下所示： --data_dir=/opt/npu/imagenet_data 3.2 8p指令如下: ``` - bash run_8p.sh + train_performance_8p.sh --bind_core=1 ``` - 验证。 -- Gitee From 11f9e9e18ccb217c26fe23558aac57cbfa8381c2 Mon Sep 17 00:00:00 2001 From: jiangxing001 <1484736931@qq.com> Date: Fri, 24 Mar 2023 01:29:23 +0000 Subject: [PATCH 2/2] update TensorFlow/built-in/cv/image_classification/InceptionV4_ID0002_for_TensorFlow/README.md. Signed-off-by: jiangxing001 <1484736931@qq.com> --- .../InceptionV4_ID0002_for_TensorFlow/README.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/TensorFlow/built-in/cv/image_classification/InceptionV4_ID0002_for_TensorFlow/README.md b/TensorFlow/built-in/cv/image_classification/InceptionV4_ID0002_for_TensorFlow/README.md index 1ee0e70a0..8c196f945 100644 --- a/TensorFlow/built-in/cv/image_classification/InceptionV4_ID0002_for_TensorFlow/README.md +++ b/TensorFlow/built-in/cv/image_classification/InceptionV4_ID0002_for_TensorFlow/README.md @@ -151,24 +151,24 @@ InceptionV4是2016年提出的Inception系列网络的第四个版本，随着Re 2. 单卡训练 - 2.1 配置train_1p.sh脚本中`data_dir`（脚本路径InceptionV4_for_TensorFlow/script/train_1p.sh）,请用户根据实际路径配置，数据集参数如下所示： + 2.1 配置train_performance_1p.sh脚本中`data_dir`（脚本路径InceptionV4_for_TensorFlow/test下）,请用户根据实际路径配置，数据集参数如下所示： --data_dir=/path/to/data 2.2 单p指令如下: - bash run_1p.sh + bash train_performance_1p.sh 3. 8卡训练 - 3.1 配置train_8p.sh脚本中`data_dir`（脚本路径InceptionV4_for_TensorFlow/script/train_8p.sh）,请用户根据实际路径配置，数据集参数如下所示： + 3.1 配置train_performance_8p.sh脚本中`data_dir`（脚本路径InceptionV4_for_TensorFlow/test下）,请用户根据实际路径配置，数据集参数如下所示： --data_dir=/path/to/data 3.2 8p指令如下: - bash run_8p.sh + train_performance_8p.sh --bind_core=1 - 验证。 -- Gitee