Skip to content

GitLab

Commit 22d81ceb authored by WenmuZhou's avatar WenmuZhou
Browse files

Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into fx_pse

parents d173bba3 da5d7ee3
Hide whitespace changes
Inline Side-by-side
Showing with 32 additions and 480 deletions
test1/utility.py → ppstructure/utility.py
View file @ 22d81ceb
...@@ -27,7 +27,7 @@ def init_args(): ...@@ -27,7 +27,7 @@ def init_args():
parser.add_argument("--table_model_dir", type=str) parser.add_argument("--table_model_dir", type=str)
parser.add_argument("--table_char_type", type=str, default='en') parser.add_argument("--table_char_type", type=str, default='en')
parser.add_argument("--table_char_dict_path", type=str, default="../ppocr/utils/dict/table_structure_dict.txt") parser.add_argument("--table_char_dict_path", type=str, default="../ppocr/utils/dict/table_structure_dict.txt")
parser.add_argument("--layout_path_model", type=str, default="lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config")
return parser return parser
...@@ -36,15 +36,13 @@ def parse_args(): ...@@ -36,15 +36,13 @@ def parse_args():
return parser.parse_args() return parser.parse_args()
def draw_result(image, result, font_path): def draw_structure_result(image, result, font_path):
if isinstance(image, np.ndarray): if isinstance(image, np.ndarray):
image = Image.fromarray(image) image = Image.fromarray(image)
boxes, txts, scores = [], [], [] boxes, txts, scores = [], [], []
for region in result: for region in result:
if region['type'] == 'Table': if region['type'] == 'Table':
pass pass
elif region['type'] == 'Figure':
pass
else: else:
for box, rec_res in zip(region['res'][0], region['res'][1]): for box, rec_res in zip(region['res'][0], region['res'][1]):
boxes.append(np.array(box).reshape(-1, 2)) boxes.append(np.array(box).reshape(-1, 2))
......
setup.py
View file @ 22d81ceb
...@@ -14,6 +14,7 @@ ...@@ -14,6 +14,7 @@
from setuptools import setup from setuptools import setup
from io import open from io import open
from paddleocr import VERSION
with open('requirements.txt', encoding="utf-8-sig") as f: with open('requirements.txt', encoding="utf-8-sig") as f:
requirements = f.readlines() requirements = f.readlines()
...@@ -32,7 +33,7 @@ setup( ...@@ -32,7 +33,7 @@ setup(
package_dir={'paddleocr': ''}, package_dir={'paddleocr': ''},
include_package_data=True, include_package_data=True,
entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]}, entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]},
version='2.0.6', version=VERSION,
install_requires=requirements, install_requires=requirements,
license='Apache License 2.0', license='Apache License 2.0',
description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices', description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',
......
test1/MANIFEST.in deleted 100644 → 0
View file @ d173bba3
include LICENSE
include README.md
recursive-include ppocr/utils *.txt utility.py logging.py network.py
recursive-include ppocr/data/ *.py
recursive-include ppocr/postprocess *.py
recursive-include tools/infer *.py
recursive-include test1 *.py
test1/api.md deleted 100644 → 0
View file @ d173bba3
# PaddleStructure
install layoutparser
```sh
wget https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
pip3 install layoutparser-0.0.0-py3-none-any.whl
```
## 1. Introduction to pipeline
PaddleStructure is a toolkit for complex layout text OCR, the process is as follows
![pipeline](../doc/table/pipeline.png)
In PaddleStructure, the image will be analyzed by layoutparser first. In the layout analysis, the area in the image will be classified, and the OCR process will be carried out according to the category.
Currently layoutparser will output five categories:
1. Text
2. Title
3. Figure
4. List
5. Table
Types 1-4 follow the traditional OCR process, and 5 follow the Table OCR process.
## 2. LayoutParser
## 3. Table OCR
[doc](table/README.md)
## 4. Predictive by inference engine
Use the following commands to complete the inference
```python
python3 table/predict_system.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --output ../output/table
```
After running, each image will have a directory with the same name under the directory specified in the output field. Each table in the picture will be stored as an excel, and the excel file name will be the coordinates of the table in the image.
## 5. PaddleStructure whl package introduction
### 5.1 Use
5.1.1 Use by code
```python
import os
import cv2
from paddlestructure import PaddleStructure,draw_result,save_res
table_engine = PaddleStructure(show_log=True)
save_folder = './output/table'
img_path = '../doc/table/1.png'
img = cv2.imread(img_path)
result = table_engine(img)
save_res(result, save_folder,os.path.basename(img_path).split('.')[0])
for line in result:
print(line)
from PIL import Image
font_path = 'path/tp/PaddleOCR/doc/fonts/simfang.ttf'
image = Image.open(img_path).convert('RGB')
im_show = draw_result(image, result,font_path=font_path)
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
5.1.2 Use by command line
```bash
paddlestructure --image_dir=../doc/table/1.png
```
### Parameter Description
Most of the parameters are consistent with the paddleocr whl package, see [whl package documentation](../doc/doc_ch/whl.md)
| Parameter | Description | Default |
|------------------------|------------------------------------------------------|------------------|
| output | The path where excel and recognition results are saved | ./output/table |
| structure_max_len | When the table structure model predicts, the long side of the image is resized | 488 |
| structure_model_dir | Table structure inference model path | None |
| structure_char_type | Dictionary path used by table structure model | ../ppocr/utils/dict/table_structure_dict.tx |
test1/api_ch.md deleted 100644 → 0
View file @ d173bba3
# PaddleStructure
安装layoutparser
```sh
wget https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
pip3 install layoutparser-0.0.0-py3-none-any.whl
```
## 1. pipeline介绍
PaddleStructure 是一个用于复杂板式文字OCR的工具包，流程如下
![pipeline](../doc/table/pipeline.png)
在PaddleStructure中，图片会先经由layoutparser进行版面分析，在版面分析中，会对图片里的区域进行分类，根据根据类别进行对于的ocr流程。
目前layoutparser会输出五个类别:
1. Text
2. Title
3. Figure
4. List
5. Table
1-4类走传统的OCR流程，5走表格的OCR流程。
## 2. LayoutParser
[文档](layout/README.md)
## 3. Table OCR
[文档](table/README_ch.md)
## 4. 预测引擎推理
使用如下命令即可完成预测引擎的推理
```python
python3 table/predict_system.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --output ../output/table
```
运行完成后，每张图片会output字段指定的目录下有一个同名目录，图片里的每个表格会存储为一个excel，excel文件名为表格在图片里的坐标。
## 5. PaddleStructure whl包介绍
### 5.1 使用
5.1.1 代码使用
```python
import os
import cv2
from paddlestructure import PaddleStructure,draw_result,save_res
table_engine = PaddleStructure(show_log=True)
save_folder = './output/table'
img_path = '../doc/table/1.png'
img = cv2.imread(img_path)
result = table_engine(img)
save_res(result, save_folder,os.path.basename(img_path).split('.')[0])
for line in result:
print(line)
from PIL import Image
font_path = 'path/tp/PaddleOCR/doc/fonts/simfang.ttf'
image = Image.open(img_path).convert('RGB')
im_show = draw_result(image, result,font_path=font_path)
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
5.1.2 命令行使用
```bash
paddlestructure --image_dir=../doc/table/1.png
```
### 参数说明
大部分参数和paddleocr whl包保持一致，见 [whl包文档](../doc/doc_ch/whl.md)
| 字段 | 说明 | 默认值 |
|------------------------|------------------------------------------------------|------------------|
| output | excel和识别结果保存的地址 | ./output/table |
| table_max_len | 表格结构模型预测时，图像的长边resize尺度 | 488 |
| table_model_dir | 表格结构模型 inference 模型地址 | None |
| table_char_type | 表格结构模型所用字典地址 | ../ppocr/utils/dict/table_structure_dict.tx |
test1/paddlestructure.py deleted 100644 → 0
View file @ d173bba3
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import logging
import os
import sys
__dir__ = os.path.dirname(__file__)
sys.path.append(__dir__)
sys.path.append(os.path.join(__dir__, '..'))
import cv2
import numpy as np
from pathlib import Path
from ppocr.utils.logging import get_logger
from test1.predict_system import OCRSystem, save_res
from test1.table.predict_table import to_excel
from test1.utility import init_args, draw_result
logger = get_logger()
from ppocr.utils.utility import check_and_read_gif, get_image_file_list
from ppocr.utils.network import maybe_download, download_with_progressbar, confirm_model_dir_url, is_link
__all__ = ['PaddleStructure', 'draw_result', 'save_res']
VERSION = '2.1'
BASE_DIR = os.path.expanduser("~/.paddlestructure/")
model_urls = {
'det': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar',
'rec': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar',
'table': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar'
}
def parse_args(mMain=True):
import argparse
parser = init_args()
parser.add_help = mMain
for action in parser._actions:
if action.dest in ['rec_char_dict_path', 'table_char_dict_path']:
action.default = None
if mMain:
return parser.parse_args()
else:
inference_args_dict = {}
for action in parser._actions:
inference_args_dict[action.dest] = action.default
return argparse.Namespace(**inference_args_dict)
class PaddleStructure(OCRSystem):
def __init__(self, **kwargs):
params = parse_args(mMain=False)
params.__dict__.update(**kwargs)
if not params.show_log:
logger.setLevel(logging.INFO)
params.use_angle_cls = False
# init model dir
params.det_model_dir, det_url = confirm_model_dir_url(params.det_model_dir,
os.path.join(BASE_DIR, VERSION, 'det'),
model_urls['det'])
params.rec_model_dir, rec_url = confirm_model_dir_url(params.rec_model_dir,
os.path.join(BASE_DIR, VERSION, 'rec'),
model_urls['rec'])
params.table_model_dir, table_url = confirm_model_dir_url(params.table_model_dir,
os.path.join(BASE_DIR, VERSION, 'table'),
model_urls['table'])
# download model
maybe_download(params.det_model_dir, det_url)
maybe_download(params.rec_model_dir, rec_url)
maybe_download(params.table_model_dir, table_url)
if params.rec_char_dict_path is None:
params.rec_char_type = 'EN'
if os.path.exists(str(Path(__file__).parent / 'ppocr/utils/dict/table_dict.txt')):
params.rec_char_dict_path = str(Path(__file__).parent / 'ppocr/utils/dict/table_dict.txt')
else:
params.rec_char_dict_path = str(Path(__file__).parent.parent / 'ppocr/utils/dict/table_dict.txt')
if params.table_char_dict_path is None:
if os.path.exists(str(Path(__file__).parent / 'ppocr/utils/dict/table_structure_dict.txt')):
params.table_char_dict_path = str(
Path(__file__).parent / 'ppocr/utils/dict/table_structure_dict.txt')
else:
params.table_char_dict_path = str(
Path(__file__).parent.parent / 'ppocr/utils/dict/table_structure_dict.txt')
print(params)
super().__init__(params)
def __call__(self, img):
if isinstance(img, str):
# download net image
if img.startswith('http'):
download_with_progressbar(img, 'tmp.jpg')
img = 'tmp.jpg'
image_file = img
img, flag = check_and_read_gif(image_file)
if not flag:
with open(image_file, 'rb') as f:
np_arr = np.frombuffer(f.read(), dtype=np.uint8)
img = cv2.imdecode(np_arr, cv2.IMREAD_COLOR)
if img is None:
logger.error("error in loading image:{}".format(image_file))
return None
if isinstance(img, np.ndarray) and len(img.shape) == 2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
res = super().__call__(img)
return res
def main():
# for cmd
args = parse_args(mMain=True)
image_dir = args.image_dir
save_folder = args.output
if image_dir.startswith('http'):
download_with_progressbar(image_dir, 'tmp.jpg')
image_file_list = ['tmp.jpg']
else:
image_file_list = get_image_file_list(args.image_dir)
if len(image_file_list) == 0:
logger.error('no images find in {}'.format(args.image_dir))
return
structure_engine = PaddleStructure(**(args.__dict__))
for img_path in image_file_list:
img_name = os.path.basename(img_path).split('.')[0]
logger.info('{}{}{}'.format('*' * 10, img_path, '*' * 10))
result = structure_engine(img_path)
for item in result:
logger.info(item['res'])
save_res(result, save_folder, img_name)
logger.info('result save to {}'.format(os.path.join(save_folder, img_name)))
test1/setup.py deleted 100644 → 0
View file @ d173bba3
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
from setuptools import setup
from io import open
import shutil
with open('../requirements.txt', encoding="utf-8-sig") as f:
requirements = f.readlines()
requirements.append('tqdm')
def readme():
with open('api_ch.md', encoding="utf-8-sig") as f:
README = f.read()
return README
shutil.copytree('./table', './test1/table')
shutil.copyfile('./predict_system.py', './test1/predict_system.py')
shutil.copyfile('./utility.py', './test1/utility.py')
shutil.copytree('../ppocr', './ppocr')
shutil.copytree('../tools', './tools')
shutil.copyfile('../LICENSE', './LICENSE')
setup(
name='paddlestructure',
packages=['paddlestructure'],
package_dir={'paddlestructure': ''},
include_package_data=True,
entry_points={"console_scripts": ["paddlestructure= paddlestructure.paddlestructure:main"]},
version='1.0',
install_requires=requirements,
license='Apache License 2.0',
description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',
long_description=readme(),
long_description_content_type='text/markdown',
url='https://github.com/PaddlePaddle/PaddleOCR',
download_url='https://github.com/PaddlePaddle/PaddleOCR.git',
keywords=[
'ocr textdetection textrecognition paddleocr crnn east star-net rosetta ocrlite db chineseocr chinesetextdetection chinesetextrecognition'
],
classifiers=[
'Intended Audience :: Developers', 'Operating System :: OS Independent',
'Natural Language :: Chinese (Simplified)',
'Programming Language :: Python :: 3',
'Programming Language :: Python :: 3.2',
'Programming Language :: Python :: 3.3',
'Programming Language :: Python :: 3.4',
'Programming Language :: Python :: 3.5',
'Programming Language :: Python :: 3.6',
'Programming Language :: Python :: 3.7', 'Topic :: Utilities'
], )
shutil.rmtree('ppocr')
shutil.rmtree('tools')
shutil.rmtree('test1')
os.remove('LICENSE')
test1/table/README.md deleted 100644 → 0
View file @ d173bba3
# Table structure and content prediction
## 1. pipeline
The ocr of the table mainly contains three models
1. Single line text detection-DB
2. Single line text recognition-CRNN
3. Table structure and cell coordinate prediction-RARE
The table ocr flow chart is as follows
![tableocr_pipeline](../../doc/table/tableocr_pipeline.png)
1. The coordinates of single-line text is detected by DB model, and then sends it to the recognition model to get the recognition result.
2. The table structure and cell coordinates is predicted by RARE model.
3. The recognition result of the cell is combined by the coordinates, recognition result of the single line and the coordinates of the cell.
4. The cell recognition result and the table structure together construct the html string of the table.
## 2. How to use
### 2.1 Train
TBD
### 2.2 Eval
First cd to the PaddleOCR/ppstructure directory
The table uses TEDS (Tree-Edit-Distance-based Similarity) as the evaluation metric of the model. Before the model evaluation, the three models in the pipeline need to be exported as inference models (we have provided them), and the gt for evaluation needs to be prepared. Examples of gt are as follows:
```json
{"PMC4289340_004_00.png": [["<html>", "<body>", "<table>", "<thead>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>", "</thead>", "<tbody>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>", "</tbody>", "</table>", "</body>", "</html>"], [[1, 4, 29, 13], [137, 4, 161, 13], [215, 4, 236, 13], [1, 17, 30, 27], [137, 17, 147, 27], [215, 17, 225, 27]], [["<b>", "F", "e", "a", "t", "u", "r", "e", "</b>"], ["<b>", "G", "b", "3", " ", "+", "</b>"], ["<b>", "G", "b", "3", " ", "-", "</b>"], ["<b>", "P", "a", "t", "i", "e", "n", "t", "s", "</b>"], ["6", "2"], ["4", "5"]]]}
```
In gt json, the key is the image name, the value is the corresponding gt, and gt is a list composed of four items, and each item is
1. HTML string list of table structure
2. The coordinates of each cell (not including the empty text in the cell)
3. The text information in each cell (not including the empty text in the cell)
4. The text information in each cell (including the empty text in the cell)
Use the following command to evaluate. After the evaluation is completed, the teds indicator will be output.
```python
python3 table/eval_table.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --gt_path=path/to/gt.json
```
### 2.3 Inference
First cd to the PaddleOCR/ppstructure directory
```python
python3 table/predict_table.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --output ../output/table
```
After running, the excel sheet of each picture will be saved in the directory specified by the output field
\ No newline at end of file
tools/infer/utility.py
View file @ 22d81ceb
...@@ -24,6 +24,7 @@ from paddle import inference ...@@ -24,6 +24,7 @@ from paddle import inference
import time import time
from ppocr.utils.logging import get_logger from ppocr.utils.logging import get_logger
def str2bool(v): def str2bool(v):
return v.lower() in ("true", "t", "1") return v.lower() in ("true", "t", "1")
...@@ -47,8 +48,8 @@ def init_args(): ...@@ -47,8 +48,8 @@ def init_args():
# DB parmas # DB parmas
parser.add_argument("--det_db_thresh", type=float, default=0.3) parser.add_argument("--det_db_thresh", type=float, default=0.3)
parser.add_argument("--det_db_box_thresh", type=float, default=0.5) parser.add_argument("--det_db_box_thresh", type=float, default=0.6)
parser.add_argument("--det_db_unclip_ratio", type=float, default=1.6) parser.add_argument("--det_db_unclip_ratio", type=float, default=1.5)
parser.add_argument("--max_batch_size", type=int, default=10) parser.add_argument("--max_batch_size", type=int, default=10)
parser.add_argument("--use_dilation", type=bool, default=False) parser.add_argument("--use_dilation", type=bool, default=False)
parser.add_argument("--det_db_score_mode", type=str, default="fast") parser.add_argument("--det_db_score_mode", type=str, default="fast")
...@@ -175,45 +176,45 @@ def create_predictor(args, mode, logger): ...@@ -175,45 +176,45 @@ def create_predictor(args, mode, logger):
if mode == "det": if mode == "det":
min_input_shape = { min_input_shape = {
"x": [1, 3, 50, 50], "x": [1, 3, 50, 50],
"conv2d_92.tmp_0": [1, 96, 20, 20], "conv2d_92.tmp_0": [1, 120, 20, 20],
"conv2d_91.tmp_0": [1, 96, 10, 10], "conv2d_91.tmp_0": [1, 24, 10, 10],
"conv2d_59.tmp_0": [1, 96, 20, 20], "conv2d_59.tmp_0": [1, 96, 20, 20],
"nearest_interp_v2_1.tmp_0": [1, 96, 10, 10], "nearest_interp_v2_1.tmp_0": [1, 256, 10, 10],
"nearest_interp_v2_2.tmp_0": [1, 96, 20, 20], "nearest_interp_v2_2.tmp_0": [1, 256, 20, 20],
"conv2d_124.tmp_0": [1, 96, 20, 20], "conv2d_124.tmp_0": [1, 256, 20, 20],
"nearest_interp_v2_3.tmp_0": [1, 24, 20, 20], "nearest_interp_v2_3.tmp_0": [1, 64, 20, 20],
"nearest_interp_v2_4.tmp_0": [1, 24, 20, 20], "nearest_interp_v2_4.tmp_0": [1, 64, 20, 20],
"nearest_interp_v2_5.tmp_0": [1, 24, 20, 20], "nearest_interp_v2_5.tmp_0": [1, 64, 20, 20],
"elementwise_add_7": [1, 56, 2, 2], "elementwise_add_7": [1, 56, 2, 2],
"nearest_interp_v2_0.tmp_0": [1, 96, 2, 2] "nearest_interp_v2_0.tmp_0": [1, 256, 2, 2]
} }
max_input_shape = { max_input_shape = {
"x": [1, 3, 2000, 2000], "x": [1, 3, 2000, 2000],
"conv2d_92.tmp_0": [1, 96, 400, 400], "conv2d_92.tmp_0": [1, 120, 400, 400],
"conv2d_91.tmp_0": [1, 96, 200, 200], "conv2d_91.tmp_0": [1, 24, 200, 200],
"conv2d_59.tmp_0": [1, 96, 400, 400], "conv2d_59.tmp_0": [1, 96, 400, 400],
"nearest_interp_v2_1.tmp_0": [1, 96, 200, 200], "nearest_interp_v2_1.tmp_0": [1, 256, 200, 200],
"conv2d_124.tmp_0": [1, 256, 400, 400], "conv2d_124.tmp_0": [1, 256, 400, 400],
"nearest_interp_v2_2.tmp_0": [1, 96, 400, 400], "nearest_interp_v2_2.tmp_0": [1, 256, 400, 400],
"nearest_interp_v2_3.tmp_0": [1, 24, 400, 400], "nearest_interp_v2_3.tmp_0": [1, 64, 400, 400],
"nearest_interp_v2_4.tmp_0": [1, 24, 400, 400], "nearest_interp_v2_4.tmp_0": [1, 64, 400, 400],
"nearest_interp_v2_5.tmp_0": [1, 24, 400, 400], "nearest_interp_v2_5.tmp_0": [1, 64, 400, 400],
"elementwise_add_7": [1, 56, 400, 400], "elementwise_add_7": [1, 56, 400, 400],
"nearest_interp_v2_0.tmp_0": [1, 96, 400, 400] "nearest_interp_v2_0.tmp_0": [1, 256, 400, 400]
} }
opt_input_shape = { opt_input_shape = {
"x": [1, 3, 640, 640], "x": [1, 3, 640, 640],
"conv2d_92.tmp_0": [1, 96, 160, 160], "conv2d_92.tmp_0": [1, 120, 160, 160],
"conv2d_91.tmp_0": [1, 96, 80, 80], "conv2d_91.tmp_0": [1, 24, 80, 80],
"conv2d_59.tmp_0": [1, 96, 160, 160], "conv2d_59.tmp_0": [1, 96, 160, 160],
"nearest_interp_v2_1.tmp_0": [1, 96, 80, 80], "nearest_interp_v2_1.tmp_0": [1, 256, 80, 80],
"nearest_interp_v2_2.tmp_0": [1, 96, 160, 160], "nearest_interp_v2_2.tmp_0": [1, 256, 160, 160],
"conv2d_124.tmp_0": [1, 256, 160, 160], "conv2d_124.tmp_0": [1, 256, 160, 160],
"nearest_interp_v2_3.tmp_0": [1, 24, 160, 160], "nearest_interp_v2_3.tmp_0": [1, 64, 160, 160],
"nearest_interp_v2_4.tmp_0": [1, 24, 160, 160], "nearest_interp_v2_4.tmp_0": [1, 64, 160, 160],
"nearest_interp_v2_5.tmp_0": [1, 24, 160, 160], "nearest_interp_v2_5.tmp_0": [1, 64, 160, 160],
"elementwise_add_7": [1, 56, 40, 40], "elementwise_add_7": [1, 56, 40, 40],
"nearest_interp_v2_0.tmp_0": [1, 96, 40, 40] "nearest_interp_v2_0.tmp_0": [1, 256, 40, 40]
} }
elif mode == "rec": elif mode == "rec":
min_input_shape = {"x": [args.rec_batch_num, 3, 32, 10]} min_input_shape = {"x": [args.rec_batch_num, 3, 32, 10]}
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment