modify: docs sail api
This commit is contained in:
@@ -0,0 +1,75 @@
|
||||
# sail 基础函数
|
||||
|
||||
## get_available_tpu_num
|
||||
|
||||
获取当前设备中可用的TPU数量
|
||||
|
||||
**接口形式:**
|
||||
```python
|
||||
def get_available_tpu_num() -> int
|
||||
```
|
||||
|
||||
**返回值说明**:
|
||||
|
||||
返回当前设备中可用 TPU的数量
|
||||
|
||||
## set_print_flag
|
||||
|
||||
设置是否打印程序的计算耗时信息
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def set_print_flag(print_flag: bool) -> None
|
||||
```
|
||||
|
||||
**参数说明**
|
||||
|
||||
- print_flag:bool
|
||||
|
||||
print_flag 为 True 时,打印程序的计算主要的耗时信息,否则不打印
|
||||
|
||||
## set_dump_io_flag
|
||||
|
||||
设置是否存储输入时间和输出时间。
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def set_dump_io_flag(dump_io_flag: bool) -> None
|
||||
```
|
||||
|
||||
**参数说明**
|
||||
|
||||
- dump_io_flag: bool
|
||||
|
||||
dump_io_flag为True时,存储输入数据和输出数据,否则不存储。
|
||||
|
||||
## set_decoder_env
|
||||
|
||||
设置Decoder的环境变量,必须在Decoder构造前设置,否则使用默认值。
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def set_decoder_env(env_name: str, env_value: str) -> None
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- env_name: str
|
||||
|
||||
选择设置Decoder的属性名称,可选的属性名称有:
|
||||
|
||||
- ‘refcounted_frames’ 设置为1时,解码出来的图像需要程序手动释放,为0时由Decoder自动释放。
|
||||
- ‘extra_frame_buffer_num’ 设置Decoder的最大缓存帧数
|
||||
- ‘rtsp_transport’ 设置RTSP采用的传输协议
|
||||
- ‘stimeout’ 设置阻塞超时时间
|
||||
- ‘rtsp_flags’ 设置RTSP是否自定义IO
|
||||
- ‘buffer_size’ 设置缓存大小
|
||||
- ‘max_delay’ 设置最大时延
|
||||
- ‘probesize’ 解析文件时读取的最大字节数
|
||||
- ‘analyzeduration’ 解析文件时读取的最大时长
|
||||
|
||||
- env_value: str
|
||||
|
||||
@@ -0,0 +1,21 @@
|
||||
# sail 数据类型
|
||||
|
||||
定义sophon环境中常用的数据类型
|
||||
|
||||
**接口形式**
|
||||
|
||||
```python
|
||||
sail.Dtype.BM_FLOAT32
|
||||
sail.Dtype.BM_INT8
|
||||
sail.Dtype.BM_UINT8
|
||||
sail.Dtype.BM_INT32
|
||||
sail.Dtype.BM_UINT32
|
||||
```
|
||||
|
||||
**参数说明**
|
||||
|
||||
- sail.Dtype.BM_FLOAT32 数据类型为float32
|
||||
- sail.Dtype.BM_INT8 数据类型为int8
|
||||
- sail.Dtype.BM_UINT8 数据类型为uint8
|
||||
- sail.Dtype.BM_INT32 数据类型为int32
|
||||
- sail.Dtype.BM_UINT32 数据类型为uint32
|
||||
@@ -0,0 +1,156 @@
|
||||
# 填充属性
|
||||
|
||||
PaddingAtrr中存储了数据padding的各项属性,可通过配置PaddingAtrr进行数据填充
|
||||
|
||||
## \_\_init\_\_
|
||||
|
||||
初始化 PaddingAtrr
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def __init__(self)
|
||||
def __init__(self, stx: int, sty: int, width: int, height: int, r: int, g: int, b: int)
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- stx: int
|
||||
|
||||
原图像相对于目标图像在x方向上的偏移量
|
||||
|
||||
- sty: int
|
||||
|
||||
原图像相对于目标图像在y方向上的偏移量
|
||||
|
||||
- width: int
|
||||
|
||||
在 padding 的同时可对原图像进行 resize,width 为原图像 resize 后的宽,若不进行 resize,则 width 为原图像的宽
|
||||
|
||||
- height: int
|
||||
|
||||
在 padding 的同时对原图像进行 resize,height 为原图像 resize 后的高,若不进行 resize,则 height 为原图像的高
|
||||
|
||||
- r: int
|
||||
|
||||
padding 时在 R 通道上填充的像素值
|
||||
|
||||
- g: int
|
||||
|
||||
padding 时在 G 通道上填充的像素值
|
||||
|
||||
- b: int
|
||||
|
||||
padding 时在B通道上填充的像素值
|
||||
|
||||
## set_stx
|
||||
|
||||
设置原图像相对于目标图像在 x 方向上的偏移量
|
||||
|
||||
**接口形式**
|
||||
|
||||
```python
|
||||
def set_stx(self, stx: int) -> None
|
||||
```
|
||||
|
||||
**参数说明**
|
||||
|
||||
- stx: int
|
||||
|
||||
原图像相对于目标图像在x方向上的偏移量
|
||||
|
||||
## set_sty
|
||||
|
||||
设置原图像相对于目标图像在y方向上的偏移量
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def set_sty(self, sty: int) -> None
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- sty: int
|
||||
|
||||
原图像相对于目标图像在y方向上的偏移量
|
||||
|
||||
## set_w
|
||||
|
||||
设置原图像resize后的width
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def set_w(self, width: int) -> None
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- width: int
|
||||
|
||||
在padding的同时可对原图像进行resize,width为原图像resize后的宽,若不进行resize,则width为原图像的宽
|
||||
|
||||
## set_h
|
||||
|
||||
设置原图像resize后的height
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def set_h(self, height: int) -> None
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- height: int
|
||||
|
||||
在padding的同时可对原图像进行resize,height为原图像resize后的高,若不进行resize,则height为原图像的高
|
||||
|
||||
## set_r
|
||||
|
||||
设置R通道上的padding值
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def set_r(self, r: int) -> None
|
||||
```
|
||||
|
||||
**参数说明**
|
||||
|
||||
- r: int
|
||||
|
||||
R通道上的padding值
|
||||
|
||||
## set_g
|
||||
|
||||
设置G通道上的padding值
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def set_g(self, g: int) -> None
|
||||
```
|
||||
|
||||
**参数说明**
|
||||
|
||||
- g: int
|
||||
|
||||
G通道上的padding值
|
||||
|
||||
## set_b
|
||||
|
||||
设置B通道上的padding值
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def set_b(self, b: int) -> None
|
||||
```
|
||||
|
||||
**参数说明**
|
||||
|
||||
- b: int
|
||||
|
||||
B通道上的padding值
|
||||
@@ -0,0 +1,51 @@
|
||||
# 设备句柄
|
||||
|
||||
Handle是设备句柄的包装类,在程序中用于设备的标识。
|
||||
|
||||
## \_\_init\_\_
|
||||
|
||||
初始化 Handle
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def __init__(self, tpu_id: int)
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- tpu_id: int
|
||||
|
||||
创建 Handle 使用的TPU的id号
|
||||
|
||||
## get_device_id
|
||||
|
||||
获取 Handle 中 TPU的id
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def get_device_id(self) -> int
|
||||
```
|
||||
|
||||
**返回值说明:**
|
||||
|
||||
- tpu_id: int
|
||||
|
||||
Handle 中的 TPU 的 id 号
|
||||
|
||||
## get_sn
|
||||
|
||||
获取 Handle 中标识设备的序列码
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def get_sn(self) -> str
|
||||
```
|
||||
|
||||
**返回值说明**
|
||||
|
||||
- serial_number: str
|
||||
|
||||
返回 Handle 中设备的序列码
|
||||
@@ -0,0 +1,17 @@
|
||||
# resize 插值策略(sail.bmcv_resize_algorithm)
|
||||
|
||||
定义图像resize中常见的插值策略
|
||||
|
||||
**接口形式**
|
||||
|
||||
```python
|
||||
sail.bmcv_resize_algorithm.BMCV_INTER_NEAREST
|
||||
sail.bmcv_resize_algorithm.BMCV_INTER_LINEAR
|
||||
sail.bmcv_resize_algorithm.BMCV_INTER_BICUBIC
|
||||
```
|
||||
|
||||
**参数说明**
|
||||
|
||||
- sail.bmcv_resize_algorithm.BMCV_INTER_NEAREST 最近邻插值算法
|
||||
- sail.bmcv_resize_algorithm.BMCV_INTER_LINEAR 双线性插值算法
|
||||
- sail.bmcv_resize_algorithm.BMCV_INTER_BICUBIC 双三次插值算法
|
||||
@@ -0,0 +1,240 @@
|
||||
# Tensor 张量
|
||||
|
||||
Tensor 是模型推理的输入输出类型,包含了数据信息,实现内容管理
|
||||
|
||||
## \_\_init\_\_
|
||||
|
||||
初始化 Tensor,并为 Tensor 分配内存
|
||||
|
||||
**接口形式1**
|
||||
|
||||
```python
|
||||
def __init__(self, handle: Handle, data: np.arrat, own_sys_data=True)
|
||||
```
|
||||
|
||||
**参数说明1**
|
||||
|
||||
- handle: sail.Handle
|
||||
|
||||
设备标识 Handle
|
||||
|
||||
- array_data: numpy.array
|
||||
|
||||
利用 numpy.array 类型初始化 Tensor,其数据类型可以是 np.float32,np.int8,np.uint8
|
||||
|
||||
- own_sys_data:bool
|
||||
|
||||
指示该 Tensor 是否拥有 system memory,如果为 False,则直接将数据复制到 device memory
|
||||
|
||||
**接口形式2**
|
||||
|
||||
```python
|
||||
def __init__(self, handle: Handle, shape: tuple, dtype: Dtype, own_sys_data: bool, own_dev_data: bool)
|
||||
```
|
||||
|
||||
**参数说明2**
|
||||
|
||||
- handle: sail.Handle
|
||||
|
||||
设备标识 Handle
|
||||
|
||||
- shape: tuple
|
||||
|
||||
设置 Tensor 的 shape
|
||||
|
||||
- dtype: sail.Dtype
|
||||
|
||||
Tensor 的数据类型
|
||||
|
||||
- own_sys_data: bool
|
||||
|
||||
指示 Tensor 是否拥有 system memory
|
||||
|
||||
- own_dev_data: bool
|
||||
|
||||
指示 Tensor 是否拥有 device memory
|
||||
|
||||
## shape
|
||||
|
||||
获取 Tensor 的 shape
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def shape(self) -> list :
|
||||
```
|
||||
|
||||
**返回值说明:**
|
||||
|
||||
- tensor_shape : list
|
||||
|
||||
返回Tensor的shape的列表。
|
||||
|
||||
## asnumpy
|
||||
|
||||
获取Tensor中系统内存的数据,返回numpy.array类型。
|
||||
|
||||
**接口形式:**
|
||||
```python
|
||||
def asnumpy(self) -> numpy.array
|
||||
|
||||
def asnumpy(self, shape: tuple) -> numpy.array
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- shape: tuple
|
||||
|
||||
可对Tensor中的数据reshape,返回形状为shape的numpy.array
|
||||
|
||||
**返回值说明**
|
||||
|
||||
返回Tensor中系统内存的数据,返回类型为numpy.array。
|
||||
|
||||
## update_data
|
||||
|
||||
更新Tensor中系统内存的数据
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def update_data(self, data: numpy.array) -> None
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- data: numpy.array
|
||||
|
||||
更新的数据,数据size不能超过Tensor的size,Tensor的shape将保持不变。
|
||||
|
||||
## scale_from
|
||||
|
||||
先对data按比例缩放,再将数据更新到Tensor的系统内存。
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def scale_from(self, data: numpy.array, scale: float32)->None
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- data: numpy.array
|
||||
|
||||
对data进行scale,再将数据更新到Tensor的系统内存。
|
||||
|
||||
- scale: float32
|
||||
|
||||
等比例缩放时的尺度。
|
||||
|
||||
## scale_to
|
||||
|
||||
先对Tensor进行等比例缩放,再将数据返回到系统内存。
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def scale_to(self, scale: float32)->numpy.array
|
||||
|
||||
def scale_to(self, scale: float32, shape: tuple)->numpy.array
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- scale: float32
|
||||
|
||||
等比例缩放时的尺度。
|
||||
|
||||
- shape: tuple
|
||||
|
||||
数据返回前可进行reshape,返回shape形状的数据。
|
||||
|
||||
**返回值说明:**
|
||||
|
||||
- data: numpy.array
|
||||
|
||||
将处理后的数据返回至系统内存,返回numpy.array
|
||||
|
||||
## reshape
|
||||
|
||||
对Tensor进行reshape
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def reshape(self, shape: list)->None
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- shape: list
|
||||
|
||||
设置期望得到的新shape。
|
||||
|
||||
# own_sys_data
|
||||
|
||||
查询该Tensor是否拥有系统内存的数据指针。
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def own_sys_data(self)->bool
|
||||
```
|
||||
|
||||
**返回值说明:**
|
||||
|
||||
- judge_ret: bool
|
||||
|
||||
如果拥有系统内存的数据指针则返回True,否则False。
|
||||
|
||||
## own_dev_data
|
||||
|
||||
查询该Tensor是否拥有设备内存的数据
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def own_dev_data(self)->bool
|
||||
```
|
||||
|
||||
**返回值说明:**
|
||||
|
||||
- judge_ret : bool
|
||||
|
||||
如果拥有设备内存中的数据则返回True,否则False。
|
||||
|
||||
## sync_s2d
|
||||
|
||||
将Tensor中的数据从系统内存拷贝到设备内存。
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def sync_s2d(self)->None
|
||||
|
||||
def sync_s2d(self, size)->None
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- size: int
|
||||
|
||||
将特定size字节的数据从系统内存拷贝到设备内存。
|
||||
|
||||
## sync_d2s
|
||||
|
||||
将Tensor中的数据从设备内存拷贝到系统内存。
|
||||
|
||||
**接口形式:**
|
||||
|
||||
```python
|
||||
def sync_d2s(self)->None
|
||||
|
||||
def sync_d2s(self, size: int)->None
|
||||
```
|
||||
|
||||
**参数说明:**
|
||||
|
||||
- size: int
|
||||
|
||||
将特定size字节的数据从设备内存拷贝到系统内存。
|
||||
@@ -1,9 +1,6 @@
|
||||
from sophon_ai_project.yolov8_bmcv import main
|
||||
from sophon_ai_project.yolov8_bmcv import argsparser
|
||||
|
||||
# def main():
|
||||
# print("Hello from sophon-ai-project!")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
args = argsparser()
|
||||
|
||||
@@ -86,7 +86,7 @@ class pseudo_torch_nms:
|
||||
|
||||
ovr = inter / (areas[i] + areas[order[1:]] - inter)
|
||||
inds = np.where(ovr <= iou_thres)[0]
|
||||
order = order[inds + 1]
|
||||
order = order[inds + 1] # type: ignore
|
||||
keep = np.array(keep)
|
||||
return keep
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ logging.basicConfig(level=logging.INFO)
|
||||
class YOLOv8:
|
||||
def __init__(self, args):
|
||||
# load bmodel
|
||||
self.net = sail.Engine(args.bmodel, args.dev_id, sail.IOMode.SYSO)
|
||||
self.net = sail.Engine(args.bmodel, args.dev_id, sail.IOMode.SYSO) # type: ignore
|
||||
logging.debug("load {} success!".format(args.bmodel))
|
||||
self.handle = sail.Handle(args.dev_id)
|
||||
self.bmcv = sail.Bmcv(self.handle)
|
||||
@@ -42,7 +42,7 @@ class YOLOv8:
|
||||
output_shape = self.net.get_output_shape(self.graph_name, output_name)
|
||||
output_dtype = self.net.get_output_dtype(self.graph_name, output_name)
|
||||
output_scale = self.net.get_output_scale(self.graph_name, output_name)
|
||||
output = sail.Tensor(self.handle, output_shape, output_dtype, True, True)
|
||||
output = sail.Tensor(self.handle, output_shape, output_dtype, True, True) # type: ignore
|
||||
self.output_tensors[output_name] = output
|
||||
self.output_scales[output_name] = output_scale
|
||||
if(output_shape[1] < output_shape[2]):
|
||||
@@ -87,13 +87,13 @@ class YOLOv8:
|
||||
|
||||
def preprocess_bmcv(self, input_bmimg):
|
||||
rgb_planar_img = sail.BMImage(self.handle, input_bmimg.height(), input_bmimg.width(),
|
||||
sail.Format.FORMAT_RGB_PLANAR, sail.DATA_TYPE_EXT_1N_BYTE)
|
||||
self.bmcv.convert_format(input_bmimg, rgb_planar_img)
|
||||
sail.Format.FORMAT_RGB_PLANAR, sail.DATA_TYPE_EXT_1N_BYTE) # type: ignore
|
||||
self.bmcv.convert_format(input_bmimg, rgb_planar_img) # type: ignore
|
||||
resized_img_rgb, ratio, txy = self.resize_bmcv(rgb_planar_img)
|
||||
preprocessed_bmimg = sail.BMImage(self.handle, self.net_h, self.net_w, sail.Format.FORMAT_RGB_PLANAR, self.img_dtype)
|
||||
preprocessed_bmimg = sail.BMImage(self.handle, self.net_h, self.net_w, sail.Format.FORMAT_RGB_PLANAR, self.img_dtype) # type: ignore
|
||||
self.bmcv.convert_to(resized_img_rgb, preprocessed_bmimg, ((self.ab[0], self.ab[1]), \
|
||||
(self.ab[2], self.ab[3]), \
|
||||
(self.ab[4], self.ab[5])))
|
||||
(self.ab[4], self.ab[5]))) # type: ignore
|
||||
return preprocessed_bmimg, ratio, txy
|
||||
|
||||
def resize_bmcv(self, bmimg):
|
||||
@@ -117,7 +117,7 @@ class YOLOv8:
|
||||
|
||||
ratio = (r, r)
|
||||
txy = (tx1, ty1)
|
||||
attr = sail.PaddingAtrr()
|
||||
attr = sail.PaddingAtrr() # type: ignore
|
||||
attr.set_stx(int(round(tx1 - 0.1)))
|
||||
attr.set_sty(int(round(ty1 - 0.1)))
|
||||
attr.set_w(tw)
|
||||
@@ -127,7 +127,7 @@ class YOLOv8:
|
||||
attr.set_b(114)
|
||||
|
||||
preprocess_fn = self.bmcv.vpp_crop_and_resize_padding if self.use_vpp else self.bmcv.crop_and_resize_padding
|
||||
resized_img_rgb = preprocess_fn(bmimg, 0, 0, img_w, img_h, self.net_w, self.net_h, attr, sail.bmcv_resize_algorithm.BMCV_INTER_LINEAR)
|
||||
resized_img_rgb = preprocess_fn(bmimg, 0, 0, img_w, img_h, self.net_w, self.net_h, attr, sail.bmcv_resize_algorithm.BMCV_INTER_LINEAR) # type: ignore
|
||||
else:
|
||||
r_w = self.net_w / img_w
|
||||
r_h = self.net_h / img_h
|
||||
@@ -145,7 +145,7 @@ class YOLOv8:
|
||||
Returns:
|
||||
"""
|
||||
input_tensors = {self.input_name: input_tensor}
|
||||
self.net.process(self.graph_name, input_tensors, self.input_shapes, self.output_tensors)
|
||||
self.net.process(self.graph_name, input_tensors, self.input_shapes, self.output_tensors) # type: ignore
|
||||
outputs_dict = {}
|
||||
for name in self.output_names:
|
||||
# outputs_dict[name] = self.output_tensors[name].asnumpy()[:img_num] * self.output_scales[name]
|
||||
@@ -175,8 +175,8 @@ class YOLOv8:
|
||||
ratio_list.append(ratio)
|
||||
txy_list.append(txy)
|
||||
|
||||
input_tensor = sail.Tensor(self.handle, self.input_shape, self.input_dtype, False, False)
|
||||
self.bmcv.bm_image_to_tensor(preprocessed_bmimg, input_tensor)
|
||||
input_tensor = sail.Tensor(self.handle, self.input_shape, self.input_dtype, False, False) # type: ignore
|
||||
self.bmcv.bm_image_to_tensor(preprocessed_bmimg, input_tensor) # type: ignore
|
||||
|
||||
else:
|
||||
BMImageArray = eval('sail.BMImageArray{}D'.format(self.batch_size))
|
||||
@@ -190,8 +190,8 @@ class YOLOv8:
|
||||
ratio_list.append(ratio)
|
||||
txy_list.append(txy)
|
||||
bmimgs[i] = preprocessed_bmimg.data()
|
||||
input_tensor = sail.Tensor(self.handle, self.input_shape, self.input_dtype, False, False)
|
||||
self.bmcv.bm_image_to_tensor(bmimgs, input_tensor)
|
||||
input_tensor = sail.Tensor(self.handle, self.input_shape, self.input_dtype, False, False) # type: ignore
|
||||
self.bmcv.bm_image_to_tensor(bmimgs, input_tensor) # type: ignore
|
||||
|
||||
start_time = time.time()
|
||||
outputs = self.predict(input_tensor, img_num)
|
||||
@@ -216,13 +216,13 @@ def draw_bmcv(dev_id, image, boxes, output_img_dir, file_name, cn, masks=None, c
|
||||
if (x2 - x1) <= thickness * 2 or (y2 - y1) <= thickness * 2:
|
||||
logging.info("width or height too small, this rect will not be drawed: (x1={},y1={},w={},h={})".format(x1, y1, x2-x1, y2-y1))
|
||||
else:
|
||||
bmcv.rectangle(img_bgr_planar, x1, y1, (x2 - x1), (y2 - y1), color, thickness)
|
||||
bmcv.rectangle(img_bgr_planar, x1, y1, (x2 - x1), (y2 - y1), color, thickness) # type: ignore
|
||||
# bmcv.putText(image, COCO_CLASSES[int(classes_ids[idx] + 1)], x1, y1, tuple(color),1.0,1)
|
||||
logging.debug("class id={}, score={}, (x1={},y1={},w={},h={})".format(int(classes_ids[idx]), conf_scores[idx], x1, y1, x2-x1, y2-y1))
|
||||
logging.debug("class id={}, score={}, (x1={},y1={},w={},h={})".format(int(classes_ids[idx]), conf_scores[idx], x1, y1, x2-x1, y2-y1)) # type: ignore
|
||||
if isvideo:
|
||||
return img_bgr_planar
|
||||
else:
|
||||
bmcv.imwrite(os.path.join(output_img_dir, file_name), img_bgr_planar)
|
||||
bmcv.imwrite(os.path.join(output_img_dir, file_name), img_bgr_planar) # type: ignore
|
||||
|
||||
def main(args):
|
||||
# check params
|
||||
@@ -266,8 +266,8 @@ def main(args):
|
||||
# decode
|
||||
start_time = time.time()
|
||||
decoder = sail.Decoder(img_file, True, args.dev_id)
|
||||
bmimg = sail.BMImage()
|
||||
ret = decoder.read(yolov8_handle, bmimg)
|
||||
bmimg = sail.BMImage() # type: ignore
|
||||
ret = decoder.read(yolov8_handle, bmimg) # type: ignore
|
||||
if ret != 0:
|
||||
logging.error("{} decode failure.".format(img_file))
|
||||
continue
|
||||
@@ -331,9 +331,9 @@ def main(args):
|
||||
yolov8_handle = sail.Handle(args.dev_id)
|
||||
end_flag = False
|
||||
while not end_flag:
|
||||
frame = sail.BMImage()
|
||||
frame = sail.BMImage() # type: ignore
|
||||
start_time = time.time()
|
||||
ret = decoder.read(yolov8_handle, frame)
|
||||
ret = decoder.read(yolov8_handle, frame) # type: ignore
|
||||
decode_time += time.time() - start_time
|
||||
if ret: #differ from cv.
|
||||
end_flag = True
|
||||
@@ -356,7 +356,7 @@ def main(args):
|
||||
classes_ids=det_draw[:, -1],
|
||||
conf_scores=det_draw[:, -2],
|
||||
isvideo=True)
|
||||
encoder.video_write(drawed_bmimg)
|
||||
encoder.video_write(drawed_bmimg) # type: ignore
|
||||
frame_list.clear()
|
||||
decoder.release()
|
||||
encoder.release()
|
||||
|
||||
Reference in New Issue
Block a user