forked from PaddlePaddle/PaddleOCR
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge remote-tracking branch 'origin/dygraph' into dygraph
- Loading branch information
Showing
34 changed files
with
1,464 additions
and
51 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,102 @@ | ||
Global: | ||
use_gpu: True | ||
epoch_num: 21 | ||
log_smooth_window: 20 | ||
print_batch_step: 10 | ||
save_model_dir: ./output/rec/nrtr/ | ||
save_epoch_step: 1 | ||
# evaluation is run every 2000 iterations | ||
eval_batch_step: [0, 2000] | ||
cal_metric_during_train: True | ||
pretrained_model: | ||
checkpoints: | ||
save_inference_dir: | ||
use_visualdl: False | ||
infer_img: doc/imgs_words_en/word_10.png | ||
# for data or label process | ||
character_dict_path: | ||
character_type: EN_symbol | ||
max_text_length: 25 | ||
infer_mode: False | ||
use_space_char: True | ||
save_res_path: ./output/rec/predicts_nrtr.txt | ||
|
||
Optimizer: | ||
name: Adam | ||
beta1: 0.9 | ||
beta2: 0.99 | ||
clip_norm: 5.0 | ||
lr: | ||
name: Cosine | ||
learning_rate: 0.0005 | ||
warmup_epoch: 2 | ||
regularizer: | ||
name: 'L2' | ||
factor: 0. | ||
|
||
Architecture: | ||
model_type: rec | ||
algorithm: NRTR | ||
in_channels: 1 | ||
Transform: | ||
Backbone: | ||
name: MTB | ||
cnn_num: 2 | ||
Head: | ||
name: Transformer | ||
d_model: 512 | ||
num_encoder_layers: 6 | ||
beam_size: 10 # When Beam size is greater than 0, it means to use beam search when evaluation. | ||
|
||
|
||
Loss: | ||
name: NRTRLoss | ||
smoothing: True | ||
|
||
PostProcess: | ||
name: NRTRLabelDecode | ||
|
||
Metric: | ||
name: RecMetric | ||
main_indicator: acc | ||
|
||
Train: | ||
dataset: | ||
name: LMDBDataSet | ||
data_dir: ./train_data/data_lmdb_release/training/ | ||
transforms: | ||
- NRTRDecodeImage: # load image | ||
img_mode: BGR | ||
channel_first: False | ||
- NRTRLabelEncode: # Class handling label | ||
- NRTRRecResizeImg: | ||
image_shape: [100, 32] | ||
resize_type: PIL # PIL or OpenCV | ||
- KeepKeys: | ||
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order | ||
loader: | ||
shuffle: True | ||
batch_size_per_card: 512 | ||
drop_last: True | ||
num_workers: 8 | ||
|
||
Eval: | ||
dataset: | ||
name: LMDBDataSet | ||
data_dir: ./train_data/data_lmdb_release/evaluation/ | ||
transforms: | ||
- NRTRDecodeImage: # load image | ||
img_mode: BGR | ||
channel_first: False | ||
- NRTRLabelEncode: # Class handling label | ||
- NRTRRecResizeImg: | ||
image_shape: [100, 32] | ||
resize_type: PIL # PIL or OpenCV | ||
- KeepKeys: | ||
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order | ||
loader: | ||
shuffle: False | ||
drop_last: False | ||
batch_size_per_card: 256 | ||
num_workers: 1 | ||
use_shared_memory: False |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,30 @@ | ||
import paddle | ||
from paddle import nn | ||
import paddle.nn.functional as F | ||
|
||
|
||
class NRTRLoss(nn.Layer): | ||
def __init__(self, smoothing=True, **kwargs): | ||
super(NRTRLoss, self).__init__() | ||
self.loss_func = nn.CrossEntropyLoss(reduction='mean', ignore_index=0) | ||
self.smoothing = smoothing | ||
|
||
def forward(self, pred, batch): | ||
pred = pred.reshape([-1, pred.shape[2]]) | ||
max_len = batch[2].max() | ||
tgt = batch[1][:, 1:2 + max_len] | ||
tgt = tgt.reshape([-1]) | ||
if self.smoothing: | ||
eps = 0.1 | ||
n_class = pred.shape[1] | ||
one_hot = F.one_hot(tgt, pred.shape[1]) | ||
one_hot = one_hot * (1 - eps) + (1 - one_hot) * eps / (n_class - 1) | ||
log_prb = F.log_softmax(pred, axis=1) | ||
non_pad_mask = paddle.not_equal( | ||
tgt, paddle.zeros( | ||
tgt.shape, dtype='int64')) | ||
loss = -(one_hot * log_prb).sum(axis=1) | ||
loss = loss.masked_select(non_pad_mask).mean() | ||
else: | ||
loss = self.loss_func(pred, tgt) | ||
return {'loss': loss} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -57,3 +57,4 @@ def reset(self): | |
self.correct_num = 0 | ||
self.all_num = 0 | ||
self.norm_edit_dis = 0 | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.