refactor(actpred): 模型输入尺寸 image_size → image_width/image_height,默认 1920×1080

config/model/dataset/train/pretrain/predict/export 全链路适配非方形输入,
hailo_infer/onnx_infer 从模型元数据动态推导宽高;旧 224 checkpoint 配置键
不兼容(重训后替换)。Pi 5 CPU 冒烟验证 1080p 训练可行(~4.75s/步 batch=2)。
This commit is contained in:
qing committed 2026-08-13 02:19:30 +08:00
1 parent a240377ba1
commit 91b30040c7
11 files changed
+73 -56

No files matched your search

+12 -12
View File
@@ -5,8 +5,8 @@
HEF 由 actpred ONNX 经 Hailo DFC 编译生成(量化校准后)。本封装不硬编码
vstream 名称/形状/量化参数,全部从 HEF 的 input/output vstream info 动态推导:
图像输入: (1, F, 3, S, S) → NHWC uint8 (1, F, S, S, 3)
或 (1, S, S, F*3) → 帧沿通道拼接
图像输入: (1, F, 3, H, W) → NHWC uint8 (1, F, H, W, 3)
或 (1, H, W, F*3) → 帧沿通道拼接
动作输入: (1, H, D) float32,uint8 边缘时按 quant_info 量化
动作输出: (1, D),uint8 边缘时按 quant_info 反量化
@@ -111,15 +111,15 @@ class HailoPredictor:
def _derive_dims(self):
shape = tuple(self._image_info.shape)
if len(shape) == 5:
_, self.frame_len, c, self.image_size, _ = shape
_, self.frame_len, c, self.image_height, self.image_width = shape
if c != 3:
raise ValueError(f"图像输入通道维应为 3,实际形状 {shape}")
self._image_layout = "ncfhw"
else: # (1, S, S, F*3) NHWC 帧拼通道
_, self.image_size, s2, c = shape
if s2 != self.image_size or c % 3 != 0 or c == 3:
else: # (1, H, W, F*3) NHWC 帧拼通道
_, self.image_height, self.image_width, c = shape
if c % 3 != 0 or c == 3:
raise ValueError(
f"无法从 4 维图像输入推导帧数(期望 (1,S,S,F*3)),"
f"无法从 4 维图像输入推导帧数(期望 (1,H,W,F*3)),"
f"实际形状 {shape}")
self.frame_len = c // 3
self._image_layout = "nhwc_fused"
@@ -206,15 +206,15 @@ class HailoPredictor:
def _preprocess(self, image) -> np.ndarray:
img = Image.fromarray(image) if isinstance(image, np.ndarray) else image
img = img.convert("RGB").resize(
(self.image_size, self.image_size), Image.BILINEAR)
(self.image_width, self.image_height), Image.BILINEAR)
return np.asarray(img, dtype=np.uint8) # HWC uint8
def _image_buffer(self, frames: np.ndarray) -> np.ndarray:
"""(F, S, S, 3) → HEF 图像输入缓冲区(按编译后布局)"""
"""(F, H, W, 3) → HEF 图像输入缓冲区(按编译后布局)"""
if self._image_layout == "ncfhw":
return frames.transpose(0, 3, 1, 2)[np.newaxis] # (1,F,3,S,S)
# nhwc_fused: 帧沿通道拼接 (1, S, S, F*3)
return frames.reshape(1, self.image_size, self.image_size,
return frames.transpose(0, 3, 1, 2)[np.newaxis] # (1,F,3,H,W)
# nhwc_fused: 帧沿通道拼接 (1, H, W, F*3)
return frames.reshape(1, self.image_height, self.image_width,
self.frame_len * 3)