refactor(actpred): 默认图像分辨率改回 640×480
实机测速显示 1080p 采集的预处理缩放(约 45ms)主导端到端延迟 (测速报告 §6.1),640×480 下端到端 18.6ms,与 NPU/ORT 推理开销 更匹配。640×480 亦能被 16 整除,部署导出池化无损失。 已有 checkpoint 自带配置不受影响,仅改新训练默认值。
This commit is contained in:
1 parent
823e91a30e
commit
8af8dec1b0
6 files changed
+18
-18
No files matched your search
+4
-4
@@ -5,8 +5,8 @@ from typing import Optional
|
||||
|
||||
@dataclass
|
||||
class DataConfig:
|
||||
image_width: int = 1920
|
||||
image_height: int = 1080
|
||||
image_width: int = 640
|
||||
image_height: int = 480
|
||||
action_dim: int = 18
|
||||
history_len: int = 5
|
||||
frame_len: int = 3
|
||||
@@ -28,8 +28,8 @@ class ModelConfig:
|
||||
|
||||
@dataclass
|
||||
class TrainConfig:
|
||||
# 默认输入分辨率 1920×1080,batch=32 在 CPU/Pi 上内存不可行;
|
||||
# 高分辨率训练取小 batch,小分辨率可用 --batch-size 调大
|
||||
# 默认输入分辨率 640×480(1080p 采集的预处理缩放在实机测速中主导
|
||||
# 端到端延迟,见测速报告 §6.1);更高分辨率训练时需调小 batch
|
||||
batch_size: int = 4
|
||||
epochs: int = 100
|
||||
lr: float = 1e-3
|
||||
|
||||
Reference in new issue
Block a user