[Other] Add detection, segmentation and OCR examples for Ascend deploy. (#983)

* Add Huawei Ascend NPU deploy through PaddleLite CANN

* Add NNAdapter interface for paddlelite

* Modify Huawei Ascend Cmake

* Update way for compiling Huawei Ascend NPU deployment

* remove UseLiteBackend in UseCANN

* Support compile python whlee

* Change names of nnadapter API

* Add nnadapter pybind and remove useless API

* Support Python deployment on Huawei Ascend NPU

* Add models suppor for ascend

* Add PPOCR rec reszie for ascend

* fix conflict for ascend

* Rename CANN to Ascend

* Rename CANN to Ascend

* Improve ascend

* fix ascend bug

* improve ascend docs

* improve ascend docs

* improve ascend docs

* Improve Ascend

* Improve Ascend

* Move ascend python demo

* Imporve ascend

* Improve ascend

* Improve ascend

* Improve ascend

* Improve ascend

* Imporve ascend

* Imporve ascend

* Improve ascend

* acc eval script

* acc eval

* remove acc_eval from branch huawei

* Add detection and segmentation examples for Ascend deployment

* Add detection and segmentation examples for Ascend deployment

* Add PPOCR example for ascend deploy

* Imporve paddle lite compiliation

* Add FlyCV doc

* Add FlyCV doc

* Add FlyCV doc

* Imporve Ascend docs

* Imporve Ascend docs

examples/vision/ocr/PP-OCRv3/python/README.md

@@ -35,6 +35,8 @@ python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2
 python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu --backend trt
 # 昆仑芯XPU推理
 python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device kunlunxin
+# 华为昇腾推理
+python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device ascend
 ```
 
 运行完成可视化结果如下图所示

examples/vision/ocr/PP-OCRv3/python/infer.py

@@ -72,6 +72,10 @@ def build_option(args):
         option.use_kunlunxin()
         return option
 
+    if args.device.lower() == "ascend":
+        option.use_ascend()
+        return option
+
     if args.backend.lower() == "trt":
         assert args.device.lower(
         ) == "gpu", "TensorRT backend require inference on device GPU."
@@ -112,6 +116,8 @@ runtime_option = build_option(args)
 
 # PPOCR的cls和rec模型现在已经支持推理一个Batch的数据
 # 定义下面两个变量后, 可用于设置trt输入shape, 并在PPOCR模型初始化后, 完成Batch推理设置
+# 当用户要把PP-OCR部署在对动态shape推理支持有限的设备上时,(例如华为昇腾)
+# 需要把cls_batch_size和rec_batch_size都设置为1.
 cls_batch_size = 1
 rec_batch_size = 6
 
@@ -144,6 +150,10 @@ rec_option.set_trt_input_shape("x", [1, 3, 48, 10],
 rec_model = fd.vision.ocr.Recognizer(
     rec_model_file, rec_params_file, rec_label_file, runtime_option=rec_option)
 
+# 当用户要把PP-OCR部署在对动态shape推理支持有限的设备上时,(例如华为昇腾)
+# 需要使用下行代码, 来启用rec模型的静态shape推理.
+# rec_model.preprocessor.static_shape_infer = True
+
 # 创建PP-OCR，串联3个模型，其中cls_model可选，如无需求，可设置为None
 ppocr_v3 = fd.vision.ocr.PPOCRv3(
     det_model=det_model, cls_model=cls_model, rec_model=rec_model)