Nigel
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

fix params ck_file

This commit is contained in:
yuyiyang_3418 2021-05-31 15:19:55 +08:00
parent 209a6e1df6
commit 0a31edfb52
5 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
model_zoo/research/hpc/pinns/README.md
View File

@ -83,7 +83,7 @@ After installing MindSpore via the official website, you can start training and
bash /scripts/run_standalone_Schrodinger_train.sh Schrodinger
# Running evaluation example
python eval.py [CHECKPOINT_PATH] --scenario=Schrodinger ----datapath=[DATASET_PATH] > eval.log
python eval.py --ckpoint_path=[CHECKPOINT_PATH] --scenario=Schrodinger --datapath=[DATASET_PATH] > eval.log
OR
bash /scriptsrun_standalone_Schrodinger_eval.sh [CHECKPOINT_PATH] [DATASET_PATH]
```
@ -160,7 +160,7 @@ For more configuration details, please refer the script `config.py`.
Before running the command below, please check the checkpoint path used for evaluation. Please set the checkpoint path to be the absolute full path, e.g., “./ckpt/checkpoint_PINNs_Schrodinger-50000_1.ckpt”。
```bash
python eval.py [CHECKPOINT_PATH] --scenario=Schrodinger ----datapath=[DATASET_PATH] > eval.log
python eval.py --ckpoint_path=[CHECKPOINT_PATH] --scenario=Schrodinger --datapath=[DATASET_PATH] > eval.log
```
The above python command will run in the background. You can view the results through the file "eval.log". The error of evaluation is as follows:

4
model_zoo/research/hpc/pinns/README_CN.md
View File

@ -83,7 +83,7 @@ PINNs是针对偏微分方程问题构造神经网络的思路，具体的模型
bash /scripts/run_standalone_Schrodinger_train.sh [DATASET_PATH]
# 运行评估示例
python eval.py [CHECKPOINT_PATH] --scenario=Schrodinger ----datapath=[DATASET_PATH] > eval.log
python eval.py --ckpoint_path=[CHECKPOINT_PATH] --scenario=Schrodinger --datapath=[DATASET_PATH] > eval.log
OR
bash /scriptsrun_standalone_Schrodinger_eval.sh [CHECKPOINT_PATH] [DATASET_PATH]
```
@ -161,7 +161,7 @@ PINNs是针对偏微分方程问题构造神经网络的思路，具体的模型
在运行以下命令之前，请检查用于评估的检查点路径。请将检查点路径设置为绝对全路径，例如“./ckpt/checkpoint_PINNs_Schrodinger-50000_1.ckpt”。
```bash
python eval.py [CHECKPOINT_PATH] --scenario=Schrodinger ----datapath=[DATASET_PATH] > eval.log
python eval.py --ckpoint_path=[CHECKPOINT_PATH] --scenario=Schrodinger --datapath=[DATASET_PATH] > eval.log
```
上述python命令将在后台运行，您可以通过eval.log文件查看结果。测试误差如下：

2
model_zoo/research/hpc/pinns/eval.py
View File

@ -58,7 +58,7 @@ def eval_PINNs_sch(ckpoint_name, num_neuron=100, path='./Data/NLS.mat'):
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Evaluate PINNs for Schrodinger equation scenario')
parser.add_argument('ck_file', type=str, help='model checkpoint(ckpt) filename')
parser.add_argument('--ckpoint_path', type=str, help='model checkpoint(ckpt) filename')
#only support 'Schrodinger' for now
parser.add_argument('--scenario', type=str, help='scenario for PINNs', default='Schrodinger')

2
model_zoo/research/hpc/pinns/scripts/run_standalone_Schrodinger_eval.sh
View File

@ -42,4 +42,4 @@ fi
ck_path=$(get_real_path $1)
data_set_path=$(get_real_path $2)
python ${PROJECT_DIR}/../eval.py $ck_path --scenario=Schrodinger --datapath=$data_set_path > eval.log 2>&1 &
python ${PROJECT_DIR}/../eval.py --ckpoint_path=$ck_path --scenario=Schrodinger --datapath=$data_set_path > eval.log 2>&1 &