Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
weixin_41840029
PaddleOCR
提交
21d9f4bf
P
PaddleOCR
项目概览
weixin_41840029
/
PaddleOCR
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleOCR
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleOCR
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
未验证
提交
21d9f4bf
编写于
6月 07, 2022
作者:
A
andyjpaddle
提交者:
GitHub
6月 07, 2022
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #6501 from andyjpaddle/amp_tipc
[TIPC] add amp tipc
上级
fe1154e0
dfcdec49
变更
17
隐藏空白更改
内联
并排
Showing
17 changed file
with
142 addition
and
89 deletion
+142
-89
test_tipc/configs/ch_PP-OCRv2_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+6
-6
test_tipc/configs/ch_PP-OCRv2_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+6
-6
test_tipc/configs/ch_PP-OCRv2_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+6
-6
test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+7
-7
test_tipc/configs/ch_PP-OCRv3_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+6
-6
test_tipc/configs/ch_PP-OCRv3_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+6
-6
test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+6
-6
test_tipc/configs/ch_PP-OCRv3_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+7
-7
test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+5
-5
test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+5
-5
test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+5
-5
test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+5
-5
test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+5
-5
test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+5
-5
test_tipc/configs/ch_ppocr_server_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+5
-5
test_tipc/configs/ch_ppocr_server_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+4
-4
test_tipc/configs/en_table_structure/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+53
-0
未找到文件。
test_tipc/configs/ch_PP-OCRv2_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
===========================train_params===========================
===========================train_params===========================
model_name:ch_PPOCRv2_det
model_name:ch_PP
-
OCRv2_det
python:python3.7
python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
0
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
infer_quant:False
inference:tools/infer/predict_det.py
inference:tools/infer/predict_det.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1
--rec_batch_num:1
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|fp16|int8
--precision:fp32
--det_model_dir:
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
null:null
...
...
test_tipc/configs/ch_PP-OCRv2_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
===========================train_params===========================
===========================train_params===========================
model_name:ch_PPOCRv2_det_PACT
model_name:ch_PP
-
OCRv2_det_PACT
python:python3.7
python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
0
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
infer_quant:False
inference:tools/infer/predict_det.py
inference:tools/infer/predict_det.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1
--rec_batch_num:1
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|fp16|int8
--precision:fp32
--det_model_dir:
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
null:null
...
...
test_tipc/configs/ch_PP-OCRv2_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
===========================train_params===========================
===========================train_params===========================
model_name:
PPOCRv2_ocr
_rec
model_name:
ch_PP-OCRv2
_rec
python:python3.7
python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=
30
0
Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=
5
0
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
infer_quant:False
inference:tools/infer/predict_rec.py
inference:tools/infer/predict_rec.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1|6
--rec_batch_num:1|6
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|int8
--precision:fp32
--rec_model_dir:
--rec_model_dir:
--image_dir:./inference/rec_inference
--image_dir:./inference/rec_inference
null:null
null:null
...
...
test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
===========================train_params===========================
===========================train_params===========================
model_name:ch_PPOCRv2_rec_PACT
model_name:ch_PP
-
OCRv2_rec_PACT
python:python3.7
python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=
3|whole_train_whole_infer=30
0
Global.epoch_num:lite_train_lite_infer=
1|whole_train_whole_infer=5
0
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Global.pretrained_model:
null
Global.pretrained_model:
pretrain_models/ch_PP-OCRv2_rec_train/best_accuracy
train_model_name:latest
train_model_name:latest
train_infer_img_dir:./inference/rec_inference
train_infer_img_dir:./inference/rec_inference
null:null
null:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:True
infer_quant:True
inference:tools/infer/predict_rec.py
inference:tools/infer/predict_rec.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1|6
--rec_batch_num:1|6
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|int8
--precision:fp32
--rec_model_dir:
--rec_model_dir:
--image_dir:./inference/rec_inference
--image_dir:./inference/rec_inference
null:null
null:null
...
...
test_tipc/configs/ch_PP-OCRv3_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
===========================train_params===========================
===========================train_params===========================
model_name:ch_PPOCRv3_det
model_name:ch_PP
-
OCRv3_det
python:python3.7
python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
0
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
infer_quant:False
inference:tools/infer/predict_det.py
inference:tools/infer/predict_det.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1
--rec_batch_num:1
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|fp16|int8
--precision:fp32
--det_model_dir:
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
null:null
...
...
test_tipc/configs/ch_PP-OCRv3_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
===========================train_params===========================
===========================train_params===========================
model_name:ch_PPOCRv3_det_PACT
model_name:ch_PP
-
OCRv3_det_PACT
python:python3.7
python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
0
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
infer_quant:False
inference:tools/infer/predict_det.py
inference:tools/infer/predict_det.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1
--rec_batch_num:1
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|fp16|int8
--precision:fp32
--det_model_dir:
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
null:null
...
...
test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
===========================train_params===========================
===========================train_params===========================
model_name:
PPOCRv3_ocr
_rec
model_name:
ch_PP-OCRv3
_rec
python:python3.7
python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=
30
0
Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=
5
0
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
infer_quant:False
inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1|6
--rec_batch_num:1|6
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|int8
--precision:fp32
--rec_model_dir:
--rec_model_dir:
--image_dir:./inference/rec_inference
--image_dir:./inference/rec_inference
null:null
null:null
...
...
test_tipc/configs/ch_PP-OCRv3_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
===========================train_params===========================
===========================train_params===========================
model_name:ch_PPOCRv3_rec_PACT
model_name:ch_PP
-
OCRv3_rec_PACT
python:python3.7
python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=
3|whole_train_whole_infer=30
0
Global.epoch_num:lite_train_lite_infer=
1|whole_train_whole_infer=5
0
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Global.pretrained_model:
null
Global.pretrained_model:
pretrain_models/ch_PP-OCRv3_rec_train/best_accuracy
train_model_name:latest
train_model_name:latest
train_infer_img_dir:./inference/rec_inference
train_infer_img_dir:./inference/rec_inference
null:null
null:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:True
infer_quant:True
inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1|6
--rec_batch_num:1|6
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|int8
--precision:fp32
--rec_model_dir:
--rec_model_dir:
--image_dir:./inference/rec_inference
--image_dir:./inference/rec_inference
null:null
null:null
...
...
test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
...
@@ -4,7 +4,7 @@ python:python3.7
...
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=100|whole_train_whole_infer=
30
0
Global.epoch_num:lite_train_lite_infer=100|whole_train_whole_infer=
5
0
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2
...
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2
infer_quant:False
infer_quant:False
inference:tools/infer/predict_det.py
inference:tools/infer/predict_det.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1
--rec_batch_num:1
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|fp16|int8
--precision:fp32
--det_model_dir:
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
null:null
...
...
test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
...
@@ -4,7 +4,7 @@ python:python3.7
...
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=
30
0
Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=
5
0
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
infer_quant:False
inference:tools/infer/predict_det.py
inference:tools/infer/predict_det.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1
--rec_batch_num:1
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|fp16|int8
--precision:fp32
--det_model_dir:
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
null:null
...
...
test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
...
@@ -4,7 +4,7 @@ python:python3.7
...
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=2
0|whole_train_whole_infer=30
0
Global.epoch_num:lite_train_lite_infer=2
|whole_train_whole_infer=5
0
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
infer_quant:False
inference:tools/infer/predict_det.py
inference:tools/infer/predict_det.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1
--rec_batch_num:1
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|fp16|int8
--precision:fp32
--det_model_dir:
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
null:null
...
...
test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
...
@@ -4,7 +4,7 @@ python:python3.7
...
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=
30
0
Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=
5
0
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/rec/rec_icdar15_train.yml -o
...
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/rec/rec_icdar15_train.yml -o
infer_quant:False
infer_quant:False
inference:tools/infer/predict_rec.py
inference:tools/infer/predict_rec.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1|6
--rec_batch_num:1|6
--use_tensorrt:
True|
False
--use_tensorrt:False
--precision:fp32
|int8
--precision:fp32
--rec_model_dir:
--rec_model_dir:
--image_dir:./inference/rec_inference
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--save_log_path:./test/output/
...
...
test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
...
@@ -4,7 +4,7 @@ python:python3.7
...
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0
gpu_list:0
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=
30
0
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=
5
0
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
infer_quant:False
inference:tools/infer/predict_rec.py
inference:tools/infer/predict_rec.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1
--rec_batch_num:1
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|int8
--precision:fp32
--rec_model_dir:
--rec_model_dir:
--image_dir:./inference/rec_inference
--image_dir:./inference/rec_inference
null:null
null:null
...
...
test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
...
@@ -4,7 +4,7 @@ python:python3.7
...
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0
gpu_list:0
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=
30
0
Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=
5
0
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Global.checkpoints:null
Global.checkpoints:null
...
@@ -39,11 +39,11 @@ infer_export:null
...
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_image_shape="3,32,100"
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_image_shape="3,32,100"
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1|6
--rec_batch_num:1|6
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|int8
--precision:fp32
--rec_model_dir:
--rec_model_dir:
--image_dir:./inference/rec_inference
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--save_log_path:./test/output/
...
...
test_tipc/configs/ch_ppocr_server_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
...
@@ -4,7 +4,7 @@ python:python3.7
...
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
gpu_list:0|0,1
Global.use_gpu:True|True
Global.use_gpu:True|True
Global.auto_cast:amp
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=
30
0
Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=
5
0
Global.save_model_dir:./output/
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_lite_infer=4
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_lite_infer=4
Global.pretrained_model:null
Global.pretrained_model:null
...
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_res18_db_
...
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_res18_db_
infer_quant:False
infer_quant:False
inference:tools/infer/predict_det.py
inference:tools/infer/predict_det.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1
--rec_batch_num:1
--use_tensorrt:False
|True
--use_tensorrt:False
--precision:fp32
|fp16|int8
--precision:fp32
--det_model_dir:
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--image_dir:./inference/ch_det_data_50/all-sum-510/
--save_log_path:null
--save_log_path:null
...
...
test_tipc/configs/ch_ppocr_server_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
21d9f4bf
...
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec
...
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec
infer_quant:False
infer_quant:False
inference:tools/infer/predict_rec.py
inference:tools/infer/predict_rec.py
--use_gpu:True|False
--use_gpu:True|False
--enable_mkldnn:
True|
False
--enable_mkldnn:False
--cpu_threads:
1|
6
--cpu_threads:6
--rec_batch_num:1|6
--rec_batch_num:1|6
--use_tensorrt:
True|
False
--use_tensorrt:False
--precision:fp32
|int8
--precision:fp32
--rec_model_dir:
--rec_model_dir:
--image_dir:./inference/rec_inference
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--save_log_path:./test/output/
...
...
test_tipc/configs/en_table_structure/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
21d9f4bf
===========================train_params===========================
model_name:en_table_structure
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Global.pretrained_model:./inference/en_ppocr_mobile_v2.0_table_structure_train/best_accuracy
train_model_name:latest
train_infer_img_dir:./ppstructure/docs/table/table.jpg
null:null
##
trainer:norm_train
norm_train:tools/train.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
pact_train:null
fpgm_train:null
distill_train:null
null:null
null:null
##
===========================eval_params===========================
eval:null
null:null
##
===========================infer_params===========================
Global.save_inference_dir:./output/
Global.checkpoints:
norm_export:tools/export_model.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
quant_export:
fpgm_export:
distill_export:null
export1:null
export2:null
##
infer_model:./inference/en_ppocr_mobile_v2.0_table_structure_infer
infer_export:null
infer_quant:False
inference:ppstructure/table/predict_table.py --det_model_dir=./inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=./inference/en_ppocr_mobile_v2.0_table_rec_infer --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
--use_gpu:True|False
--enable_mkldnn:False
--cpu_threads:6
--rec_batch_num:1
--use_tensorrt:False
--precision:fp32
--table_model_dir:
--image_dir:./ppstructure/docs/table/table.jpg
null:null
--benchmark:False
null:null
===========================infer_benchmark_params==========================
random_infer_input:[{float32,[3,488,488]}]
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录