提交 6e89ec8d 编写于 作者: A andyjpaddle

fix sar export

上级 6460985d
...@@ -79,7 +79,7 @@ python3 tools/export_model.py -c configs/rec/rec_r31_sar.yml -o Global.pretraine ...@@ -79,7 +79,7 @@ python3 tools/export_model.py -c configs/rec/rec_r31_sar.yml -o Global.pretraine
SAR文本识别模型推理,可以执行如下命令: SAR文本识别模型推理,可以执行如下命令:
``` ```
python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_sar/" --rec_image_shape="3, 48, 48, 160" --rec_char_type="ch" --rec_algorithm="SAR" --rec_char_dict_path="ppocr/utils/dict90.txt" --max_text_length=30 --use_space_char=False python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_sar/" --rec_image_shape="3, 48, 48, 160" --rec_algorithm="SAR" --rec_char_dict_path="ppocr/utils/dict90.txt" --max_text_length=30 --use_space_char=False
``` ```
<a name="4-2"></a> <a name="4-2"></a>
......
...@@ -79,7 +79,7 @@ python3 tools/export_model.py -c configs/rec/rec_r31_sar.yml -o Global.pretraine ...@@ -79,7 +79,7 @@ python3 tools/export_model.py -c configs/rec/rec_r31_sar.yml -o Global.pretraine
For SAR text recognition model inference, the following commands can be executed: For SAR text recognition model inference, the following commands can be executed:
``` ```
python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_sar/" --rec_image_shape="3, 48, 48, 160" --rec_char_type="ch" --rec_algorithm="SAR" --rec_char_dict_path="ppocr/utils/dict90.txt" --max_text_length=30 --use_space_char=False python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./inference/rec_sar/" --rec_image_shape="3, 48, 48, 160" --rec_algorithm="SAR" --rec_char_dict_path="ppocr/utils/dict90.txt" --max_text_length=30 --use_space_char=False
``` ```
<a name="4-2"></a> <a name="4-2"></a>
......
...@@ -58,6 +58,8 @@ def export_single_model(model, ...@@ -58,6 +58,8 @@ def export_single_model(model,
other_shape = [ other_shape = [
paddle.static.InputSpec( paddle.static.InputSpec(
shape=[None, 3, 48, 160], dtype="float32"), shape=[None, 3, 48, 160], dtype="float32"),
[paddle.static.InputSpec(
shape=[None], dtype="float32")]
] ]
model = to_static(model, input_spec=other_shape) model = to_static(model, input_spec=other_shape)
elif arch_config["algorithm"] == "SVTR": elif arch_config["algorithm"] == "SVTR":
...@@ -232,4 +234,4 @@ def main(): ...@@ -232,4 +234,4 @@ def main():
if __name__ == "__main__": if __name__ == "__main__":
main() main()
\ No newline at end of file
...@@ -439,7 +439,8 @@ class TextRecognizer(object): ...@@ -439,7 +439,8 @@ class TextRecognizer(object):
valid_ratios = np.concatenate(valid_ratios) valid_ratios = np.concatenate(valid_ratios)
inputs = [ inputs = [
norm_img_batch, norm_img_batch,
valid_ratios, np.array(
[valid_ratios], dtype=np.float32),
] ]
if self.use_onnx: if self.use_onnx:
input_dict = {} input_dict = {}
......
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