From 6bee09303d48c5b5b3bd1505b90361705eb2e143 Mon Sep 17 00:00:00 2001 From: chengxianbin Date: Tue, 18 Aug 2020 17:01:33 +0800 Subject: [PATCH] fix ssd&yolov3-darknet-quant&yolov3-resnet18 net README file bug --- model_zoo/official/cv/ssd/README.md | 2 +- model_zoo/official/cv/yolov3_darknet53_quant/README.md | 6 +++--- model_zoo/official/cv/yolov3_resnet18/README.md | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/model_zoo/official/cv/ssd/README.md b/model_zoo/official/cv/ssd/README.md index ded107e4992..73ebc5f7f2c 100644 --- a/model_zoo/official/cv/ssd/README.md +++ b/model_zoo/official/cv/ssd/README.md @@ -66,7 +66,7 @@ To train the model, run `train.py`. If the `mindrecord_dir` is empty, it will ge sh run_distribute_train.sh 8 500 0.2 coco /data/hccl.json ``` - The input parameters are device numbers, epoch size, learning rate, dataset mode and [hccl json configuration file](https://www.mindspore.cn/tutorial/en/master/advanced_use/distributed_training.html). **It is better to use absolute path.** + The input parameters are device numbers, epoch size, learning rate, dataset mode and [hccl json configuration file](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/utils/hccl_tools). **It is better to use absolute path.** You will get the loss value of each step as following: diff --git a/model_zoo/official/cv/yolov3_darknet53_quant/README.md b/model_zoo/official/cv/yolov3_darknet53_quant/README.md index 55942c49d60..5e4e6899122 100644 --- a/model_zoo/official/cv/yolov3_darknet53_quant/README.md +++ b/model_zoo/official/cv/yolov3_darknet53_quant/README.md @@ -71,7 +71,7 @@ sh run_distribute_train.sh dataset/coco2014 yolov3_darknet_noquant_ckpt/0-320_10 sh run_standalone_train.sh dataset/coco2014 yolov3_darknet_noquant_ckpt/0-320_102400.ckpt ``` -> About rank_table.json, you can refer to the [distributed training tutorial](https://www.mindspore.cn/tutorial/en/master/advanced_use/distributed_training.html). +> About rank_table.json, You can generate it by using the [hccl json configuration file](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/utils/hccl_tools). #### Result @@ -108,14 +108,14 @@ epoch[134], iter[86500], loss:34.303755, 145.18 imgs/sec, lr:1.6245529650404933e ``` # infer -sh run_eval.sh [DATASET_PATH] [CHECKPOINT_PATH] +sh run_eval.sh [DATASET_PATH] [CHECKPOINT_PATH] [DEVICE_ID] ``` #### Launch ```bash # infer with checkpoint -sh run_eval.sh dataset/coco2014/ checkpoint/0-135.ckpt +sh run_eval.sh dataset/coco2014/ checkpoint/0-131.ckpt 0 ``` diff --git a/model_zoo/official/cv/yolov3_resnet18/README.md b/model_zoo/official/cv/yolov3_resnet18/README.md index 5d5b36de083..17582c5960f 100644 --- a/model_zoo/official/cv/yolov3_resnet18/README.md +++ b/model_zoo/official/cv/yolov3_resnet18/README.md @@ -51,7 +51,7 @@ To train the model, run `train.py` with the dataset `image_dir`, `anno_path` and sh run_distribute_train.sh 8 150 /data/Mindrecord_train /data /data/train.txt /data/hccl.json ``` - The input variables are device numbers, epoch size, mindrecord directory path, dataset directory path, train TXT file path and [hccl json configuration file](https://www.mindspore.cn/tutorial/en/master/advanced_use/distributed_training.html). **It is better to use absolute path.** + The input variables are device numbers, epoch size, mindrecord directory path, dataset directory path, train TXT file path and [hccl json configuration file](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/utils/hccl_tools). **It is better to use absolute path.** You will get the loss value and time of each step as following: