未验证 提交 a67a6fa3 编写于 作者: X xiaoting 提交者: GitHub

Merge pull request #5142 from tink2123/cherry-pick-fasttext

[cherrr-pick] mv fasttext for requirments
...@@ -235,7 +235,10 @@ PaddleOCR支持训练和评估交替进行, 可以在 `configs/rec/rec_icdar15_t ...@@ -235,7 +235,10 @@ PaddleOCR支持训练和评估交替进行, 可以在 `configs/rec/rec_icdar15_t
| rec_r31_sar.yml | SAR | ResNet31 | None | LSTM encoder | LSTM decoder | | rec_r31_sar.yml | SAR | ResNet31 | None | LSTM encoder | LSTM decoder |
| rec_resnet_stn_bilstm_att.yml | SEED | Aster_Resnet | STN | BiLSTM | att | | rec_resnet_stn_bilstm_att.yml | SEED | Aster_Resnet | STN | BiLSTM | att |
*其中SEED模型需要额外加载FastText训练好的[语言模型](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.en.300.bin.gz) *其中SEED模型需要额外加载FastText训练好的[语言模型](https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.en.300.bin.gz) ,并且安装 fasttext 依赖:
```
python3.7 -m pip install fasttext==0.9.1
```
训练中文数据,推荐使用[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml),如您希望尝试其他算法在中文数据集上的效果,请参考下列说明修改配置文件: 训练中文数据,推荐使用[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml),如您希望尝试其他算法在中文数据集上的效果,请参考下列说明修改配置文件:
......
...@@ -23,7 +23,6 @@ import sys ...@@ -23,7 +23,6 @@ import sys
import six import six
import cv2 import cv2
import numpy as np import numpy as np
import fasttext
class DecodeImage(object): class DecodeImage(object):
...@@ -136,6 +135,7 @@ class ToCHWImage(object): ...@@ -136,6 +135,7 @@ class ToCHWImage(object):
class Fasttext(object): class Fasttext(object):
def __init__(self, path="None", **kwargs): def __init__(self, path="None", **kwargs):
import fasttext
self.fast_model = fasttext.load_model(path) self.fast_model = fasttext.load_model(path)
def __call__(self, data): def __call__(self, data):
......
...@@ -12,5 +12,4 @@ cython ...@@ -12,5 +12,4 @@ cython
lxml lxml
premailer premailer
openpyxl openpyxl
fasttext==0.9.1
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册