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
s920243400
PaddleOCR
提交
0271adae
P
PaddleOCR
项目概览
s920243400
/
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
0271adae
编写于
11月 30, 2021
作者:
D
Double_V
提交者:
GitHub
11月 30, 2021
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #4799 from tink2123/del_fp16
del fp16 in rec_model
上级
a2b4de9f
64466574
变更
9
隐藏空白更改
内联
并排
Showing
9 changed file
with
9 addition
and
14 deletion
+9
-14
ppocr/modeling/transforms/tps_spatial_transformer.py
ppocr/modeling/transforms/tps_spatial_transformer.py
+1
-1
test_tipc/configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt
...c/configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt
+2
-2
test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/train_infer_python.txt
...nfigs/rec_mv3_none_bilstm_ctc_v2.0/train_infer_python.txt
+1
-1
test_tipc/configs/rec_mv3_none_none_ctc_v2.0/train_infer_python.txt
...configs/rec_mv3_none_none_ctc_v2.0/train_infer_python.txt
+1
-1
test_tipc/configs/rec_mv3_tps_bilstm_ctc_v2.0/train_infer_python.txt
...onfigs/rec_mv3_tps_bilstm_ctc_v2.0/train_infer_python.txt
+1
-1
test_tipc/configs/rec_r34_vd_none_bilstm_ctc_v2.0/train_infer_python.txt
...gs/rec_r34_vd_none_bilstm_ctc_v2.0/train_infer_python.txt
+1
-1
test_tipc/configs/rec_r34_vd_none_none_ctc_v2.0/train_infer_python.txt
...figs/rec_r34_vd_none_none_ctc_v2.0/train_infer_python.txt
+1
-1
test_tipc/configs/rec_r34_vd_tps_bilstm_ctc_v2.0/train_infer_python.txt
...igs/rec_r34_vd_tps_bilstm_ctc_v2.0/train_infer_python.txt
+1
-1
test_tipc/prepare.sh
test_tipc/prepare.sh
+0
-5
未找到文件。
ppocr/modeling/transforms/tps_spatial_transformer.py
浏览文件 @
0271adae
...
...
@@ -53,7 +53,7 @@ def compute_partial_repr(input_points, control_points):
1
]
repr_matrix
=
0.5
*
pairwise_dist
*
paddle
.
log
(
pairwise_dist
)
# fix numerical error for 0 * log(0), substitute all nan with 0
mask
=
repr_matrix
!=
repr_matrix
mask
=
np
.
array
(
repr_matrix
!=
repr_matrix
)
repr_matrix
[
mask
]
=
0
return
repr_matrix
...
...
test_tipc/configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt
浏览文件 @
0271adae
...
...
@@ -37,13 +37,13 @@ export2:null
infer_model:null
infer_export:tools/export_model.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec/rec_icdar15_train.yml -o
infer_quant:False
inference:tools/infer/predict_rec.py
--rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,100"
inference:tools/infer/predict_rec.py
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|
fp16|
int8
--precision:fp32|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
...
...
test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/train_infer_python.txt
浏览文件 @
0271adae
...
...
@@ -43,7 +43,7 @@ inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dic
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|
fp16|
int8
--precision:fp32|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
...
...
test_tipc/configs/rec_mv3_none_none_ctc_v2.0/train_infer_python.txt
浏览文件 @
0271adae
...
...
@@ -43,7 +43,7 @@ inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dic
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|
fp16|
int8
--precision:fp32|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
...
...
test_tipc/configs/rec_mv3_tps_bilstm_ctc_v2.0/train_infer_python.txt
浏览文件 @
0271adae
...
...
@@ -43,7 +43,7 @@ inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dic
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|
fp16|
int8
--precision:fp32|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
...
...
test_tipc/configs/rec_r34_vd_none_bilstm_ctc_v2.0/train_infer_python.txt
浏览文件 @
0271adae
...
...
@@ -43,7 +43,7 @@ inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dic
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|
fp16|
int8
--precision:fp32|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
...
...
test_tipc/configs/rec_r34_vd_none_none_ctc_v2.0/train_infer_python.txt
浏览文件 @
0271adae
...
...
@@ -43,7 +43,7 @@ inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dic
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|
fp16|
int8
--precision:fp32|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
...
...
test_tipc/configs/rec_r34_vd_tps_bilstm_ctc_v2.0/train_infer_python.txt
浏览文件 @
0271adae
...
...
@@ -43,7 +43,7 @@ inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dic
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|
fp16|
int8
--precision:fp32|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
...
...
test_tipc/prepare.sh
浏览文件 @
0271adae
...
...
@@ -141,11 +141,6 @@ elif [ ${MODE} = "whole_infer" ];then
wget
-nc
-P
./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar
--no-check-certificate
cd
./inference
&&
tar
xf
${
eval_model_name
}
.tar
&&
tar
xf ch_det_data_50.tar
&&
cd
../
fi
if
[
${
model_name
}
=
"ch_PPOCRv2_det"
]
;
then
wget
-nc
-P
./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
--no-check-certificate
wget
-nc
-P
./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/e2e_server_pgnetA_infer.tar
--no-check-certificate
cd
./inference
&&
tar
xf e2e_server_pgnetA_infer.tar
&&
tar
xf ch_det_data_50.tar
&&
cd
../
fi
if
[
${
model_name
}
==
"en_server_pgnetA"
]
;
then
wget
-nc
-P
./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/en_server_pgnetA.tar
--no-check-certificate
cd
./inference
&&
tar
xf en_server_pgnetA.tar
&&
cd
../
...
...
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