yujunjun/PaddleOCR
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleOCR.git synced 2025-12-27 15:08:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix doc and delete run_process_type

Browse Source
This commit is contained in:
LDOUBLEV 2022-02-08 07:43:52 +00:00
parent 117b85ac22
commit e795567261
3 changed files with 11 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
test_tipc/benchmark_train.sh
View File

@ -134,16 +134,16 @@ if [ ! -n "$PARAMS" ] ;then
device_num_list=(N1C4)
run_mode="DP"
else
# parser params from input: modeltype_bs${bs_item}_${fp_item}_${run_process_type}_${run_mode}_${device_num}
# parser params from input: modeltype_bs${bs_item}_${fp_item}_${run_mode}_${device_num}
IFS="_"
params_list=(${PARAMS})
model_type=${params_list[0]}
batch_size=${params_list[1]}
batch_size=`echo ${batch_size} | tr -cd "[0-9]" `
precision=${params_list[2]}
run_process_type=${params_list[3]}
run_mode=${params_list[4]}
device_num=${params_list[5]}
# run_process_type=${params_list[3]}
run_mode=${params_list[3]}
device_num=${params_list[4]}
IFS=";"
if [ ${precision} = "null" ];then

15
test_tipc/docs/benchmark_train.md
View File

@ -19,27 +19,24 @@ bash test_tipc/prepare.sh test_tipc/configs/det_mv3_db_v2_0/train_benchmark.txt
# 运行格式：bash test_tipc/benchmark_train.sh train_benchmark.txt mode
bash test_tipc/benchmark_train.sh test_tipc/configs/det_mv3_db_v2_0/train_infer_python.txt benchmark_train
# 单机多卡训练，MultiP 表示多进程；单卡训练用SingleP
# 运行格式：bash test_tipc/benchmark_train.sh train_benchmark.txt mode
bash test_tipc/benchmark_train.sh test_tipc/configs/det_mv3_db_v2_0/train_infer_python.txt benchmark_train
```
`test_tipc/benchmark_train.sh`支持根据传入的第三个参数实现只运行某一个训练配置，如下：
```shell
# 运行格式：bash test_tipc/benchmark_train.sh train_benchmark.txt mode
bash test_tipc/benchmark_train.sh test_tipc/configs/det_mv3_db_v2_0/train_infer_python.txt benchmark_train dynamic_bs8_null_SingleP_DP_N1C1
bash test_tipc/benchmark_train.sh test_tipc/configs/det_mv3_db_v2_0/train_infer_python.txt benchmark_train dynamic_bs8_fp32_DP_N1C1
```
dynamic_bs8_null_SingleP_DP_N1C1为test_tipc/benchmark_train.sh传入的参数，格式如下：
`${modeltype}_${batch_size}_${fp_item}_${run_process_type}_${run_mode}_${device_num}`
包含的信息有：模型类型、batchsize大小、训练精度如fp32,fp16等、分布式训练进程类型、分布式运行模式以及分布式训练使用的机器信息如单机单卡（N1C1）。
dynamic_bs8_fp32_DP_N1C1为test_tipc/benchmark_train.sh传入的参数，格式如下：
`${modeltype}_${batch_size}_${fp_item}_${run_mode}_${device_num}`
包含的信息有：模型类型、batchsize大小、训练精度如fp32,fp16等、分布式运行模式以及分布式训练使用的机器信息如单机单卡（N1C1）。
## 2. 日志输出
运行后将输出模型的训练日志和日志解析日志，使用 `test_tipc/configs/det_mv3_db_v2_0/train_benchmark.txt` 参数文件的训练日志解析结果是：
运行后将保存模型的训练日志和解析日志，使用 `test_tipc/configs/det_mv3_db_v2_0/train_benchmark.txt` 参数文件的训练日志解析结果是：
```
{"model_branch": "dygaph", "model_commit": "7c39a1996b19087737c05d883fd346d2f39dbcc0", "model_name": "det_mv3_db_v2_0_bs8_fp32_SingleP_DP", "batch_size": 8, "fp_item": "fp32", "run_process_type": "SingleP", "run_mode": "DP", "convergence_value": "5.413110", "convergence_key": "loss:", "ips": 19.333, "speed_unit": "images/s", "device_num": "N1C1", "model_run_time": "0", "frame_commit": "8cc09552473b842c651ead3b9848d41827a3dbab", "frame_version": "0.0.0"}
{"model_branch": "dygaph", "model_commit": "7c39a1996b19087737c05d883fd346d2f39dbcc0", "model_name": "det_mv3_db_v2_0_bs8_fp32_SingleP_DP", "batch_size": 8, "fp_item": "fp32", "run_process_type": "SingleP", "run_mode": "DP", "convergence_value": "5.413110", "convergence_key": "loss:", "ips": 19.333, "speed_unit": "samples/s", "device_num": "N1C1", "model_run_time": "0", "frame_commit": "8cc09552473b842c651ead3b9848d41827a3dbab", "frame_version": "0.0.0"}
```
训练日志和日志解析结果保存在benchmark_log目录下，文件组织格式如下：

2
tools/program.py
View File

@ -283,7 +283,7 @@ def train(config,
eta_sec_format = str(datetime.timedelta(seconds=int(eta_sec)))
strs = 'epoch: [{}/{}], global_step: {}, {}, avg_reader_cost: ' \
'{:.5f} s, avg_batch_cost: {:.5f} s, avg_samples: {}, ' \
'ips: {:.5f} , eta: {}'.format(
'ips: {:.5f} samples/s, eta: {}'.format(
epoch, epoch_num, global_step, logs,
train_reader_cost / print_batch_step,
train_batch_cost / print_batch_step,