Skip to content

GitLab

Commit 4684103f authored by Leif's avatar Leif
Browse files

Merge remote-tracking branch 'PaddlePaddle/dygraph' into dygraph

parents 2bea3736 19204e8f
Hide whitespace changes
Inline Side-by-side
Showing with 23 additions and 21 deletions
doc/doc_en/models_list_en.md
View file @ 4684103f
...@@ -27,7 +27,7 @@ Relationship of the above models is as follows. ...@@ -27,7 +27,7 @@ Relationship of the above models is as follows.
|model name|description|config|model size|download| |model name|description|config|model size|download|
| --- | --- | --- | --- | --- | | --- | --- | --- | --- | --- |
|ch_ppocr_mobile_slim_v2.0_det|Slim pruned lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)| |inference model (coming soon) / slim model (coming soon)| |ch_ppocr_mobile_slim_v2.0_det|Slim pruned lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)| 2.6M |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_prune_infer.tar)|
|ch_ppocr_mobile_v2.0_det|Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)|3M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)| |ch_ppocr_mobile_v2.0_det|Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)|3M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|
|ch_ppocr_server_v2.0_det|General model, which is larger than the lightweight model, but achieved better performance|[ch_det_res18_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml)|47M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)| |ch_ppocr_server_v2.0_det|General model, which is larger than the lightweight model, but achieved better performance|[ch_det_res18_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml)|47M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)|
......
doc/doc_en/multi_languages_en.md
View file @ 4684103f
...@@ -83,32 +83,37 @@ Paddleocr currently supports 80 languages, which can be switched by modifying th ...@@ -83,32 +83,37 @@ Paddleocr currently supports 80 languages, which can be switched by modifying th
The specific supported [language] (#language_abbreviations) can be viewed in the table. The specific supported [language] (#language_abbreviations) can be viewed in the table.
``` bash ``` bash
paddleocr --image_dir doc/imgs_en/254.jpg --lang=en
paddleocr --image_dir doc/imgs/japan_2.jpg --lang=japan
``` ```
![](https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/imgs/japan_2.jpg) <div align="center">
<img src="../imgs_en/254.jpg" width="300" height="600">
<img src="../imgs_results/multi_lang/img_02.jpg" width="600" height="600">
</div>
The result is a list, each item contains a text box, text and recognition confidence The result is a list, each item contains a text box, text and recognition confidence
```text ```text
[[[671.0, 60.0], [847.0, 63.0], [847.0, 104.0], [671.0, 102.0]], ('もちもち', 0.9993342)] [('PHO CAPITAL', 0.95723116), [[66.0, 50.0], [327.0, 44.0], [327.0, 76.0], [67.0, 82.0]]]
[[[394.0, 82.0], [536.0, 77.0], [538.0, 127.0], [396.0, 132.0]], ('自然の', 0.9919842)] [('107 State Street', 0.96311164), [[72.0, 90.0], [451.0, 84.0], [452.0, 116.0], [73.0, 121.0]]]
[[[880.0, 89.0], [1014.0, 93.0], [1013.0, 127.0], [879.0, 124.0]], ('とろっと', 0.9976762)] [('Montpelier Vermont', 0.97389287), [[69.0, 132.0], [501.0, 126.0], [501.0, 158.0], [70.0, 164.0]]]
[[[1067.0, 101.0], [1294.0, 101.0], [1294.0, 138.0], [1067.0, 138.0]], ('后味のよい', 0.9988712)] [('8022256183', 0.99810505), [[71.0, 175.0], [363.0, 170.0], [364.0, 202.0], [72.0, 207.0]]]
[('REG 07-24-201706:59 PM', 0.93537045), [[73.0, 299.0], [653.0, 281.0], [654.0, 318.0], [74.0, 336.0]]]
[('045555', 0.99346405), [[509.0, 331.0], [651.0, 325.0], [652.0, 356.0], [511.0, 362.0]]]
[('CT1', 0.9988654), [[535.0, 367.0], [654.0, 367.0], [654.0, 406.0], [535.0, 406.0]]]
...... ......
``` ```
* Recognition * Recognition
```bash ```bash
paddleocr --image_dir doc/imgs_words/japan/1.jpg --det false --lang=japan paddleocr --image_dir doc/imgs_words_en/word_308.png --det false --lang=en
``` ```
![](https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/imgs_words/japan/1.jpg) ![](https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.1/doc/imgs_words_en/word_308.png)
The result is a tuple, which returns the recognition result and recognition confidence The result is a tuple, which returns the recognition result and recognition confidence
```text ```text
('したがって', 0.99965394) (0.99879867, 'LITTLE')
``` ```
* Detection * Detection
......
ppocr/data/simple_dataset.py
View file @ 4684103f
...@@ -74,7 +74,7 @@ class SimpleDataSet(Dataset): ...@@ -74,7 +74,7 @@ class SimpleDataSet(Dataset):
data_line = self.data_lines[file_idx] data_line = self.data_lines[file_idx]
try: try:
data_line = data_line.decode('utf-8') data_line = data_line.decode('utf-8')
substr = data_line.strip("\n").split(self.delimiter) substr = data_line.strip("\n").strip("\r").split(self.delimiter)
file_name = substr[0] file_name = substr[0]
label = substr[1] label = substr[1]
img_path = os.path.join(self.data_dir, file_name) img_path = os.path.join(self.data_dir, file_name)
......
ppocr/modeling/heads/self_attention.py
View file @ 4684103f
...@@ -285,8 +285,7 @@ class PrePostProcessLayer(nn.Layer): ...@@ -285,8 +285,7 @@ class PrePostProcessLayer(nn.Layer):
elif cmd == "n": # add layer normalization elif cmd == "n": # add layer normalization
self.functors.append( self.functors.append(
self.add_sublayer( self.add_sublayer(
"layer_norm_%d" % len( "layer_norm_%d" % len(self.sublayers()),
self.sublayers(include_sublayers=False)),
paddle.nn.LayerNorm( paddle.nn.LayerNorm(
normalized_shape=d_model, normalized_shape=d_model,
weight_attr=fluid.ParamAttr( weight_attr=fluid.ParamAttr(
...@@ -320,9 +319,7 @@ class PrepareEncoder(nn.Layer): ...@@ -320,9 +319,7 @@ class PrepareEncoder(nn.Layer):
self.src_emb_dim = src_emb_dim self.src_emb_dim = src_emb_dim
self.src_max_len = src_max_len self.src_max_len = src_max_len
self.emb = paddle.nn.Embedding( self.emb = paddle.nn.Embedding(
num_embeddings=self.src_max_len, num_embeddings=self.src_max_len, embedding_dim=self.src_emb_dim)
embedding_dim=self.src_emb_dim,
sparse=True)
self.dropout_rate = dropout_rate self.dropout_rate = dropout_rate
def forward(self, src_word, src_pos): def forward(self, src_word, src_pos):
......
ppocr/utils/save_load.py
View file @ 4684103f
...@@ -80,9 +80,9 @@ def init_model(config, model, logger, optimizer=None, lr_scheduler=None): ...@@ -80,9 +80,9 @@ def init_model(config, model, logger, optimizer=None, lr_scheduler=None):
""" """
load model from checkpoint or pretrained_model load model from checkpoint or pretrained_model
""" """
gloabl_config = config['Global'] global_config = config['Global']
checkpoints = gloabl_config.get('checkpoints') checkpoints = global_config.get('checkpoints')
pretrained_model = gloabl_config.get('pretrained_model') pretrained_model = global_config.get('pretrained_model')
best_model_dict = {} best_model_dict = {}
if checkpoints: if checkpoints:
assert os.path.exists(checkpoints + ".pdparams"), \ assert os.path.exists(checkpoints + ".pdparams"), \
...@@ -105,7 +105,7 @@ def init_model(config, model, logger, optimizer=None, lr_scheduler=None): ...@@ -105,7 +105,7 @@ def init_model(config, model, logger, optimizer=None, lr_scheduler=None):
logger.info("resume from {}".format(checkpoints)) logger.info("resume from {}".format(checkpoints))
elif pretrained_model: elif pretrained_model:
load_static_weights = gloabl_config.get('load_static_weights', False) load_static_weights = global_config.get('load_static_weights', False)
if not isinstance(pretrained_model, list): if not isinstance(pretrained_model, list):
pretrained_model = [pretrained_model] pretrained_model = [pretrained_model]
if not isinstance(load_static_weights, list): if not isinstance(load_static_weights, list):
......
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