-
Notifications
You must be signed in to change notification settings - Fork 2.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
add scene_text_recognition #329
Conversation
scene_text_recognition/README.md
Outdated
|
||
在现实生活中,包括路牌、菜单、大厦标语在内的很多场景均会有文字出现,这些场景的照片中的文字为图片场景的理解提供了更多信息,\[[1](#参考文献)\]使用深度学习模型自动识别路牌中的文字,帮助街景应用获取更加准确的地址信息。 | ||
|
||
本文将针对 **场景文字识别 (STR, Scene Text Recognition)** 任务,演示如何用 PaddlePaddle 实现 一个端对端 CTC 的模型 **CRNN(Convolutional Recurrent Neural Network)** |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
本例演示如何用 PaddlePaddle 完成场景文字识别任务。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
DONE
scene_text_recognition/README.md
Outdated
## 使用 PaddlePaddle 训练与预测 | ||
|
||
### 模型训练 | ||
训练脚本参照 [./train.py](./train.py),设置了如下命令行参数: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
- 什么叫:”训练脚本参照
train.py
,设置了如下命令行参数“ ?这句话并不通顺。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
DONE
scene_text_recognition/README.md
Outdated
- `test_file_list` 测试数据的列表文件,格式同上 | ||
|
||
### 预测 | ||
预测部分由infer.py完成,本示例对于ctc的预测使用的是最优路径解码算法(CTC greedy decoder),即在每个时间步选择一个概率最大的字符。在使用过程中,需要在infer.py中指定具体的模型目录、图片固定尺寸、batch_size和图片文件的列表文件。例如: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
预测使用的是最优路径解码算法,即:
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
DONE
|
||
import os | ||
from paddle.v2.image import load_image | ||
import cv2 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
- 请按照 Paddle repo的风格,统一docstring的风格。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
DONE
scene_text_recognition/model.py
Outdated
@with_bn: whether with batch normal | ||
''' | ||
assert num % 4 == 0 | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
- 用for循环来定义 17 ~ 56 行。
- 如果要用 Class 来封装模型的定义,不要混用。把这个函数移入 Model 类中。
scene_text_recognition/model.py
Outdated
act=paddle.activation.Softmax()) | ||
|
||
# warp CTC to calculate cost for a CTC task. | ||
if self.is_infer == False: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
请加上 ctc error evaluator。
scene_text_recognition/train.py
Outdated
@@ -0,0 +1,102 @@ | |||
import logging | |||
import argparse | |||
import paddle.v2 as paddle |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
请把python 本身的model 放在前面,空一行,然后是自定义的module。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
DONE
scene_text_recognition/train.py
Outdated
args.model_output_prefix, event.pass_id, event.batch_id, | ||
result.cost) | ||
with gzip.open(path, 'w') as f: | ||
params.to_tar(f) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
请为这个脚本写一个main 函数。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
DONE
scene_text_recognition/README.md
Outdated
在现实生活中,包括路牌、菜单、大厦标语在内的很多场景均会有文字出现,这些场景的照片中的文字为图片场景的理解提供了更多信息,\[[1](#参考文献)\]使用深度学习模型自动识别路牌中的文字,帮助街景应用获取更加准确的地址信息。 | ||
|
||
本文将针对 **场景文字识别 (STR, Scene Text Recognition)** 任务,演示如何用 PaddlePaddle 实现 一个端对端 CTC 的模型 **CRNN(Convolutional Recurrent Neural Network)** | ||
\[[2](#参考文献)\],具体的,本文使用如下图片进行训练,需要识别文字对应的文字 "keep"。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
- 请不要写本文使用如下图片进行训练,需要识别文字对应的文字 "keep"。
- 如果要使用这个例子,请简单以这个图作为一个实例,介绍STR需要作什么。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
DONE
scene_text_recognition/README.md
Outdated
其中最重要的几个参数包括: | ||
|
||
- `image_shape` 图片的尺寸 | ||
- `train_file_list` 训练数据的列表文件,每行一个路径加对应的text,格式类似: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
- 不要用 ”格式类似:“,格式是什么样子就是什么样子,不是 ”格式类似:“
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
DONE
@lcy-seso update the commit |
scene_text_recognition/README.md
Outdated
1.从官方网站下载数据\[[2](#参考文献)\](Task 2.3: Word Recognition (2013 edition)),会有三个文件: Challenge2_Training_Task3_Images_GT.zip、Challenge2_Test_Task3_Images.zip和 Challenge2_Test_Task3_GT.txt。 | ||
分别对应训练集的图片和图片对应的单词,测试集的图片,测试数据对应的单词,然后执行以下命令,对数据解压并移动至目标文件夹: | ||
|
||
``` |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
```bash
以下还有几个地方须做同样修改
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/README.md
Outdated
|
||
在现实生活中,包括路牌、菜单、大厦标语在内的很多场景均会有文字出现,这些场景的照片中的文字为图片场景的理解提供了更多信息,\[[1](#参考文献)\]使用深度学习模型自动识别路牌中的文字,帮助街景应用获取更加准确的地址信息。 | ||
|
||
本例将演示如何用 PaddlePaddle 完成 **场景文字识别 (STR, Scene Text Recognition)** 任务。以下图为例,给定一个场景图片,STR需要从图片中识别出对应的文字"keep": |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
句末用句号
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
''' | ||
image = load_image(path) | ||
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) | ||
# resize all images to a fixed shape |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
注释前可空行,注释后不要空行
scene_text_recognition/infer.py
Outdated
|
||
|
||
if __name__ == "__main__": | ||
model_path = "model.ctc-pass-9-batch-150-test.tar.gz" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
预测用的具体参数通过命令行传入会比较方便
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
此处的多个参数都是如此
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/model.py
Outdated
:type input_image: LayerOutput | ||
:param num: number of CONV filters. | ||
:type num: int | ||
:param with_bn: whether with batch normal. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
batch normalization
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/train.py
Outdated
path = "{}-pass-{}-batch-{}-test.tar.gz".format( | ||
args.model_output_prefix, event.pass_id, event.batch_id) | ||
with gzip.open(path, 'w') as f: | ||
params.to_tar(f) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
trainer.save_parameter_to_tar(f)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/model.py
Outdated
class Model(object): | ||
def __init__(self, num_classes, shape, is_infer=False): | ||
''' | ||
:param num_classes: size of the character dict. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
参数解释的首字母大写,以下也需要修改
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
fixed_shape=None, | ||
is_infer=False): | ||
''' | ||
:param train_image_paths_generator: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
参数含义解释首字母大写,下同
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
|
||
def load_image(self, path): | ||
''' | ||
load image and transform to 1-dimention vector |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
函数解释首字母大写
|
||
def word2ids(self, sent): | ||
''' | ||
transform a word to a list of ids. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
函数解释首字母大写
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/model.py
Outdated
# CNN output image features, 128 float matrixes | ||
conv_features = self.conv_groups(self.image, 8, True) | ||
|
||
# cutting CNN output into a sequence of feature vectors, which are |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
cut ...
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/model.py
Outdated
gru_backward = simple_gru( | ||
input=sliced_feature, size=128, act=Relu(), reverse=True) | ||
|
||
# map each step of RNN to character distribution. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
map the output of RNNs to ...
scene_text_recognition/model.py
Outdated
height=self.shape[0], | ||
width=self.shape[1]) | ||
|
||
# label input as a ID list |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
a -> an
cb3c400
to
f02f4c6
Compare
scene_text_recognition/utils.py
Outdated
|
||
def get_file_list(image_file_list): | ||
''' | ||
Generate the file list for train and test data. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
train -> training
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
f994b2f
to
4c70682
Compare
scene_text_recognition/README.md
Outdated
``` | ||
- `test_file_list` 测试数据的列表文件,格式同上。 | ||
- `label_dict_path` 训练数据中标记字典的存储路径,如果指定路径中字典文件不存在,程序会使用训练数据中的标记数据自动生成标记字典。 | ||
- `model_save_dir` 模型参数会的保存目录目录, 默认为当前目录下的`models`目录。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
请修改 "模型参数会的保存目录目录"
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
f1ef2e9
to
a3316a4
Compare
scene_text_recognition/README.md
Outdated
``` | ||
- `test_file_list` :测试数据的列表文件,格式同上。 | ||
- `label_dict_path` :训练数据中标记字典的存储路径,如果指定路径中字典文件不存在,程序会使用训练数据中的标记数据自动生成标记字典。 | ||
- `model_save_dir` :模型参数的保存目录,默认为当前路径下的`models`目录。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
默认为./models
。
scene_text_recognition/README.md
Outdated
|
||
### 指定训练配置参数 | ||
|
||
`config.py` 脚本中包含了模型配置的参数以及对应的详细解释,代码如下: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
模型配置和训练相关的参数
scene_text_recognition/README.md
Outdated
|
||
## STR任务简介 | ||
|
||
在现实生活中,许多图片中的文字为图片所处场景的理解提供了丰富的语义信息(例如:路牌、菜单、街道标语等)。同时,针对场景图片的文字识别技术的发展也促进了一些新型应用的产生,例如:\[[1](#参考文献)\]通过使用深度学习模型来自动识别路牌中的文字,帮助街景应用获取更加准确的地址信息。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
场景图片文字识别技术, 去掉“针对” 和 第一个 “的”
scene_text_recognition/README.md
Outdated
... | ||
``` | ||
|
||
通过修改 `config.py` 脚本可以实现对参数的调整。例如,通过修改 `use_gpu` 参数来指定是否使用 GPU 进行训练。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
去掉 第一个 “通过”
scene_text_recognition/README.md
Outdated
|
||
|
||
### 预测 | ||
预测部分由 `infer.py` 完成,使用的是最优路径解码算法,即:在每个时间步选择一个概率最大的字符。在使用过程中,需要在 `infer.py` 中指定具体的模型保存路径、图片固定尺寸、batch_size(默认设置为10)、标记词典路径和图片文件的列表文件。执行如下代码: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
默认值为10
scene_text_recognition/README.md
Outdated
|
||
- 由于模型依赖的 `warp CTC` 只有CUDA的实现,本模型只支持 GPU 运行。 | ||
- 本模型参数较多,占用显存比较大,实际执行时可以通过调节 `batch_size` 来控制显存占用。 | ||
- 本示例使用的数据集较小,如有需要,可以选用其他更大的数据集\[[3](#参考文献)\]来训练模型。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
保持前后一致 ,“本示例” -> “本例”
a3316a4
to
672e856
Compare
scene_text_recognition/README.md
Outdated
@@ -2,9 +2,9 @@ | |||
|
|||
## STR任务简介 | |||
|
|||
在现实生活中,包括路牌、菜单、大厦标语在内的很多场景均会有文字出现,这些场景的照片中的文字为图片场景的理解提供了更多信息,\[[1](#参考文献)\]使用深度学习模型自动识别路牌中的文字,帮助街景应用获取更加准确的地址信息。 | |||
在现实生活中,许多图片中的文字为图片所处场景的理解提供了丰富的语义信息(例如:路牌、菜单、街道标语等)。同时,场景图片文字识别技术的发展也促进了一些新型应用的产生,例如:\[[1](#参考文献)\]通过使用深度学习模型来自动识别路牌中的文字,帮助街景应用获取更加准确的地址信息。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/README.md
Outdated
@@ -21,7 +21,7 @@ pip install -r requirements.txt | |||
|
|||
### 指定训练配置参数 | |||
|
|||
通过 `config.py` 脚本修改训练和模型配置参数,脚本中有对可配置参数的详细解释,示例如下: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/README.md
Outdated
@@ -43,7 +43,8 @@ class ModelConfig(object): | |||
|
|||
... | |||
``` | |||
修改 `config.py` 对参数进行调整。例如,通过修改 `use_gpu` 参数来指定是否使用 GPU 进行训练。 | |||
|
|||
修改 `config.py` 脚本可以实现对参数的调整。例如,通过修改 `use_gpu` 参数来指定是否使用 GPU 进行训练。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/README.md
Outdated
``` | ||
4.训练过程中,模型参数会自动备份到指定目录,默认会保存在 `./models` 目录下。 | ||
|
||
|
||
### 预测 | ||
预测部分由 `infer.py` 完成,使用的是最优路径解码算法,即:在每个时间步选择一个概率最大的字符。在使用过程中,需要在 `infer.py` 中指定具体的模型目录、图片固定尺寸、batch_size(默认设置为10)和图片文件的列表文件。执行如下代码: | ||
预测部分由 `infer.py` 完成,使用的是最优路径解码算法,即:在每个时间步选择一个概率最大的字符。在使用过程中,需要在 `infer.py` 中指定具体的模型保存路径、图片固定尺寸、batch_size(默认为10)、标记词典路径和图片文件的列表文件。执行如下代码: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/README.md
Outdated
- `model_save_dir` 模型参数会的保存目录目录, 默认为当前目录下的`models`目录。 | ||
- `test_file_list` :测试数据的列表文件,格式同上。 | ||
- `label_dict_path` :训练数据中标记字典的存储路径,如果指定路径中字典文件不存在,程序会使用训练数据中的标记数据自动生成标记字典。 | ||
- `model_save_dir` :模型参数的保存目录,默认为`./models`。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/README.md
Outdated
- 本模型使用的数据集较小,可以选用其他更大的数据集\[[3](#参考文献)\]来训练需要的模型 | ||
- 由于模型依赖的 `warp CTC` 只有CUDA的实现,本模型只支持 GPU 运行。 | ||
- 本模型参数较多,占用显存比较大,实际执行时可以通过调节 `batch_size` 来控制显存占用。 | ||
- 本例使用的数据集较小,如有需要,可以选用其他更大的数据集\[[3](#参考文献)\]来训练模型。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/model.py
Outdated
@@ -45,12 +45,11 @@ def __build_nn__(self): | |||
''' | |||
Build the network topology. | |||
''' | |||
# CNN output image features. | |||
# Get the image features with CNN. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
scene_text_recognition/model.py
Outdated
@@ -68,7 +67,7 @@ def __build_nn__(self): | |||
act=Relu(), | |||
reverse=True) | |||
|
|||
# Map each step of RNN to character distribution. | |||
# Map the output of RNN to character distribution. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Almost LGTM.
else: | ||
num_channels = None | ||
|
||
tmp = img_conv_group( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
return img_conv_group
scene_text_recognition/README.md
Outdated
|
||
## STR任务简介 | ||
|
||
在现实生活中,许多图片中的文字为图片所处场景的理解提供了丰富的语义信息(例如:路牌、菜单、街道标语等)。同时,场景图片文字识别技术的发展也促进了一些新型应用的产生,例如:\[[1](#参考文献)\]通过使用深度学习模型来自动识别路牌中的文字,帮助街景应用获取更加准确的地址信息。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
- "许多图片中的文字为图片所处场景的理解提供了丰富的语义信息 " 这句话不通顺。
- 第二句话:同时,场景图片文字识别技术的发展也促进了一些新型应用的产生,请先给“场景图片文字识别”下定义。
scene_text_recognition/README.md
Outdated
|
||
在现实生活中,许多图片中的文字为图片所处场景的理解提供了丰富的语义信息(例如:路牌、菜单、街道标语等)。同时,场景图片文字识别技术的发展也促进了一些新型应用的产生,例如:\[[1](#参考文献)\]通过使用深度学习模型来自动识别路牌中的文字,帮助街景应用获取更加准确的地址信息。 | ||
|
||
本例将演示如何用 PaddlePaddle 完成 **场景文字识别 (STR, Scene Text Recognition)** 任务。如下图所示,给定一张场景图片,`STR` 需要从中识别出对应的文字"keep"。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
如下图所示, --> 任务如下图所示
scene_text_recognition/README.md
Outdated
|
||
<p align="center"> | ||
<img src="./images/503.jpg"/><br/> | ||
图 1. 数据示例 "keep" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
输入数据示例
scene_text_recognition/README.md
Outdated
pip install -r requirements.txt | ||
``` | ||
|
||
### 指定训练配置参数 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
修改配置参数
scene_text_recognition/README.md
Outdated
|
||
### 指定训练配置参数 | ||
|
||
`config.py` 脚本中包含了模型配置和训练相关的参数以及对应的详细解释,代码如下: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
代码片段如下。
... | ||
``` | ||
|
||
修改 `config.py` 脚本可以实现对参数的调整。例如,通过修改 `use_gpu` 参数来指定是否使用 GPU 进行训练。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
- 通过修改
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
加 ”通过” 就缺乏主语了 @lcy-seso
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
祈使句可以不需要主语~ 不过这里都可以。我觉得可以按照个人意愿酌情修改。
scene_text_recognition/README.md
Outdated
|
||
``` | ||
|
||
- `train_file_list` :训练数据的列表文件,每行由图片的存储路径和对应的标记文本组成,具体格式为: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
格式为:
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGMT.
resolve #328