diff --git a/README.md b/README.md index 2b1e80ea66e3d1ca664ab7eaf8b5191d771d5fa9..997827360603b932c53e3614d47e43cf473cbbe9 100644 --- a/README.md +++ b/README.md @@ -9,14 +9,14 @@ PaddleHub是基于PaddlePaddle生态下的预训练模型管理和迁移学习 * 便捷地获取PaddlePaddle生态下的所有预训练模型，涵盖了图像分类、目标检测、词法分析、语义模型、情感分析、语言模型、视频分类、图像生成、图像分割等主流模型。 * 更多详情可查看官网：https://www.paddlepaddle.org.cn/hub * 通过PaddleHub Fine-tune API，结合少量代码即可完成**大规模预训练模型**的迁移学习，具体Demo可参考以下链接： - * [文本分类](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.1.0/demo/text-classification) - * [序列标注](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.1.0/demo/sequence-labeling) - * [多标签分类](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.1.0/demo/multi-label-classification) - * [图像分类](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.1.0/demo/image-classification) - * [检索式问答任务](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.1.0/demo/qa_classification) - * [回归任务](https://github.com/PaddlePaddle/PaddleHub/tree/develop/demo/sentence_similarity) - * [句子语义相似度计算](https://github.com/PaddlePaddle/PaddleHub/tree/develop/demo/sentence_similarity) - * [阅读理解任务](https://github.com/PaddlePaddle/PaddleHub/tree/develop/demo/reading-comprehension) + * [文本分类](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.2/demo/text-classification) + * [序列标注](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.2/demo/sequence-labeling) + * [多标签分类](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.2/demo/multi-label-classification) + * [图像分类](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.2/demo/image-classification) + * [检索式问答任务](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.2/demo/qa_classification) + * [回归任务](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.2/demo/sentence_similarity) + * [句子语义相似度计算](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.2/demo/sentence_similarity) + * [阅读理解任务](https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.2/demo/reading-comprehension) * PaddleHub引入『**模型即软件**』的设计理念，支持通过Python API或者命令行工具，一键完成预训练模型地预测，更方便的应用PaddlePaddle模型库。 * [PaddleHub命令行工具介绍](https://github.com/PaddlePaddle/PaddleHub/wiki/PaddleHub%E5%91%BD%E4%BB%A4%E8%A1%8C%E5%B7%A5%E5%85%B7) @@ -74,7 +74,7 @@ $ hub run ssd_mobilenet_v1_pascal --input_path test_object_detection.jpg $ hub run yolov3_coco2017 --input_path test_object_detection.jpg $ hub run faster_rcnn_coco2017 --input_path test_object_detection.jpg ``` -![SSD检测结果](https://raw.githubusercontent.com/PaddlePaddle/PaddleHub/release/v1.0.0/docs/imgs/object_detection_result.png) +![SSD检测结果](https://raw.githubusercontent.com/PaddlePaddle/PaddleHub/release/v1.2/docs/imgs/object_detection_result.png) 除了上述三类模型外，PaddleHub还发布了语言模型、语义模型、图像分类、生成模型、视频分类等业界主流模型，更多PaddleHub已经发布的模型，请前往 https://www.paddlepaddle.org.cn/hub 查看 @@ -103,11 +103,11 @@ PaddleHub如何完成迁移学习，详情参考[wiki教程](https://github.com/ PaddleHub如何自定义迁移任务，详情参考[wiki教程](https://github.com/PaddlePaddle/PaddleHub/wiki/PaddleHub:-%E8%87%AA%E5%AE%9A%E4%B9%89Task) -如何使用PaddleHub超参优化功能，详情参考[autofinetune使用教程](https://github.com/PaddlePaddle/PaddleHub/blob/develop/tutorial/autofinetune.md) +如何使用PaddleHub超参优化功能，详情参考[autofinetune使用教程](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.2/tutorial/autofinetune.md) -如何使用PaddleHub“端到端地”完成文本相似度计算，详情参考[word2vce使用教程](https://github.com/PaddlePaddle/PaddleHub/blob/develop/tutorial/sentence_sim.ipynb) +如何使用PaddleHub“端到端地”完成文本相似度计算，详情参考[word2vce使用教程](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.2/tutorial/sentence_sim.ipynb) -如何使用ULMFiT策略微调PaddleHub预训练模型，详情参考[PaddleHub 迁移学习与ULMFiT微调策略](https://github.com/PaddlePaddle/PaddleHub/blob/develop/tutorial/strategy_exp.md) +如何使用ULMFiT策略微调PaddleHub预训练模型，详情参考[PaddleHub 迁移学习与ULMFiT微调策略](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.2/tutorial/strategy_exp.md) ## FAQ @@ -155,4 +155,4 @@ print(res) ## 更新历史 -详情参考[更新历史](https://github.com/PaddlePaddle/PaddleHub/blob/develop/RELEASE.md) +详情参考[更新历史](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.2/RELEASE.md) diff --git a/demo/elmo/README.md b/demo/elmo/README.md index 713e91fd73ce2bca2237caa96327c45605666896..5c655f015f51f955af00fa48971965819ecc2e66 100644 --- a/demo/elmo/README.md +++ b/demo/elmo/README.md @@ -41,7 +41,7 @@ reader = hub.reader.LACClassifyReader( vocab_path=module.get_vocab_path()) ``` -其中数据集的准备代码可以参考 [chnsenticorp.py](https://github.com/PaddlePaddle/PaddleHub/blob/develop/paddlehub/dataset/chnsenticorp.py) +其中数据集的准备代码可以参考 [chnsenticorp.py](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.2/paddlehub/dataset/chnsenticorp.py) `hub.dataset.ChnSentiCorp()` 会自动从网络下载数据集并解压到用户目录下`$HOME/.paddlehub/dataset`目录 diff --git a/demo/image-classification/README.md b/demo/image-classification/README.md index 64d3e0c13a5f9effc06440f96b0c7845d8fceac4..9869b3fc5816390625675a90e34d7b1cd3e9884e 100644 --- a/demo/image-classification/README.md +++ b/demo/image-classification/README.md @@ -2,7 +2,7 @@ ## 关于 -本示例将展示如何使用PaddleHub Finetune API以及[图像分类](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/image_classification)预训练模型完成分类任务。 +本示例将展示如何使用PaddleHub Finetune API以及[图像分类](https://github.com/PaddlePaddle/models/tree/release/v1.2/PaddleCV/image_classification)预训练模型完成分类任务。 ## 准备工作 diff --git a/demo/multi-label-classification/README.md b/demo/multi-label-classification/README.md index 71bcd9af3d28df0f77ea022af819b8db3b1ac207..5612c58948bc18fab2de108c80f3463eba0ce8a7 100644 --- a/demo/multi-label-classification/README.md +++ b/demo/multi-label-classification/README.md @@ -42,7 +42,7 @@ reader = hub.reader.MultiLabelClassifyReader( max_seq_len=128) ``` -其中数据集的准备代码可以参考 [toxic.py](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.0.0/paddlehub/dataset/toxic.py) +其中数据集的准备代码可以参考 [toxic.py](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.2/paddlehub/dataset/toxic.py) `hub.dataset.Toxic()` 会自动从网络下载数据集并解压到用户目录下`$HOME/.paddlehub/dataset`目录 diff --git a/demo/qa_classification/README.md b/demo/qa_classification/README.md index aba130e9f78b5dc2f58b04a577f29c7bd06e6c89..9946d38d8f06f82878e362b7f3d86625c2515ca4 100644 --- a/demo/qa_classification/README.md +++ b/demo/qa_classification/README.md @@ -61,7 +61,7 @@ reader = hub.reader.ClassifyReader( max_seq_len=128) ``` -其中数据集的准备代码可以参考 [nlpcc_dbqa.py](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.0.0/paddlehub/dataset/nlpcc_dbqa.py) +其中数据集的准备代码可以参考 [nlpcc_dbqa.py](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.2/paddlehub/dataset/nlpcc_dbqa.py) `hub.dataset.NLPCC_DBQA())` 会自动从网络下载数据集并解压到用户目录下`$HOME/.paddlehub/dataset`目录 diff --git a/demo/reading-comprehension/README.md b/demo/reading-comprehension/README.md index 0e5986e9675f5205b3d58aba8def8f70a9fac325..1017d95cec31f821dfe00735d10e0f9644740f36 100644 --- a/demo/reading-comprehension/README.md +++ b/demo/reading-comprehension/README.md @@ -48,7 +48,7 @@ reader = hub.reader.ReadingComprehensionReader( max_query_length=64) ``` -其中数据集的准备代码可以参考 [squad.py](https://github.com/PaddlePaddle/PaddleHub/blob/develop/paddlehub/dataset/squad.py) +其中数据集的准备代码可以参考 [squad.py](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.2/paddlehub/dataset/squad.py) `hub.dataset.SQUAD()` 会自动从网络下载数据集并解压到用户目录下`$HOME/.paddlehub/dataset`目录 diff --git a/demo/regression/README.md b/demo/regression/README.md index 7ac6fe446de18d6647bfca79fa10c94239d54541..781a64d606ccee2e33ac2ccde1b7371c0820d525 100644 --- a/demo/regression/README.md +++ b/demo/regression/README.md @@ -45,7 +45,7 @@ reader = hub.reader.RegressionReader( max_seq_len=args.max_seq_len) ``` -其中数据集的准备代码可以参考 [glue.py](https://github.com/PaddlePaddle/PaddleHub/blob/develop/paddlehub/dataset/glue.py) +其中数据集的准备代码可以参考 [glue.py](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.2/paddlehub/dataset/glue.py) `hub.dataset.GLUE("STS-B")` 会自动从网络下载数据集并解压到用户目录下`$HOME/.paddlehub/dataset`目录 diff --git a/demo/sequence-labeling/README.md b/demo/sequence-labeling/README.md index ed0caf786dc9a6b7b9e59cf31f47f31aa09818a7..de163f9bf6940beab01661364409c23be418b69c 100644 --- a/demo/sequence-labeling/README.md +++ b/demo/sequence-labeling/README.md @@ -57,7 +57,7 @@ reader = hub.reader.SequenceLabelReader( max_seq_len=128) ``` -其中数据集的准备代码可以参考 [msra_ner.py](https://github.com/PaddlePaddle/PaddleHub/blob/develop/paddlehub/dataset/msra_ner.py) +其中数据集的准备代码可以参考 [msra_ner.py](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.2/paddlehub/dataset/msra_ner.py) `hub.dataset.MSRA_NER()` 会自动从网络下载数据集并解压到用户目录下`$HOME/.paddlehub/dataset`目录 diff --git a/demo/ssd/README.md b/demo/ssd/README.md index 14504b7c005dae17d0c96a2cba48ce3c4f250bbf..f78cc0c8aff9e5c421f814e68abb8080da35d244 100644 --- a/demo/ssd/README.md +++ b/demo/ssd/README.md @@ -4,7 +4,7 @@ 本示例展示如何使用SSD Module进行预测。 -SSD是一个目标检测模型，可以检测出图片中的实物的类别和位置，PaddleHub发布的SSD模型通过pascalvoc数据集训练，支持20个数据类别的检测，关于模型的训练细节，请查看[SSD](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/object_detection) +SSD是一个目标检测模型，可以检测出图片中的实物的类别和位置，PaddleHub发布的SSD模型通过pascalvoc数据集训练，支持20个数据类别的检测，关于模型的训练细节，请查看[SSD](https://github.com/PaddlePaddle/models/tree/release/v1.2/PaddleCV/object_detection) ## 准备工作 diff --git a/demo/text-classification/README.md b/demo/text-classification/README.md index 17567da0931b311ee52e50bc4abb25855175274c..710eb21d56fe98e5ffa2ea62c0138ea449d606de 100644 --- a/demo/text-classification/README.md +++ b/demo/text-classification/README.md @@ -86,7 +86,7 @@ reader = hub.reader.ClassifyReader( metrics_choices = ["acc"] ``` -其中数据集的准备代码可以参考 [chnsenticorp.py](https://github.com/PaddlePaddle/PaddleHub/blob/develop/paddlehub/dataset/chnsenticorp.py) +其中数据集的准备代码可以参考 [chnsenticorp.py](https://github.com/PaddlePaddle/PaddleHub/blob/release/v1.2/paddlehub/dataset/chnsenticorp.py) `hub.dataset.ChnSentiCorp()` 会自动从网络下载数据集并解压到用户目录下`$HOME/.paddlehub/dataset`目录