|
关于“推理经验-Inference Experience”类别
|
|
0
|
9
|
June 5, 2025
|
|
使用MindSpore Lite端侧模型转换工具将YOLOv8.onnx转为.ms报错Convert failed. Ret: Common error code.
|
|
1
|
39
|
October 31, 2025
|
|
使用mindsporelite推理，出现data size not equal 错误，tensor size 0
|
|
2
|
17
|
October 30, 2025
|
|
qwen1.5-0.5b推理报错Launch kernel failed, kernel full name: Default/ScatterNdUpdate-op0
|
|
0
|
7
|
October 21, 2025
|
|
Mindspore在自回归推理时的精度对齐设置
|
|
0
|
6
|
September 27, 2025
|
|
qwen1.5_1.8B推理出现回答混乱问题及解决
|
|
0
|
10
|
September 25, 2025
|
|
MindSpore大模型在线推理速度慢及解决方案
|
|
0
|
12
|
September 24, 2025
|
|
MindSpore与CANN的协同优化：实现极致性能的深度学习训练与推理
|
|
0
|
47
|
September 24, 2025
|
|
MindSpore Lite模型加载报错RuntimeError: build from file failed! Error is Common error code.
|
|
0
|
11
|
September 9, 2025
|
|
昇腾910上yolov5推理比较慢
|
|
1
|
12
|
September 6, 2025
|
|
昇思MindSpore开源社区上线智谱GLM-4.5与GLM-4.5-Air大模型
|
|
1
|
89
|
August 18, 2025
|
|
使用.om格式模型结合gradio框架进行推理出现模型执行错误
|
|
0
|
8
|
September 1, 2025
|
|
mindformers推理qwen2.5-72b报显存不足及解决
|
|
0
|
21
|
September 1, 2025
|
|
LLama2_7b推理报错ValueError: For BatchMatMul, inputs shape cannot be broadcast on CPU/GPU.和解决
|
|
0
|
9
|
August 18, 2025
|
|
MindSpore论坛报错活动第三十期-报错：使用MindSpore将.ckpt转.air再转.om出现AttributeError: 'AclLiteModel' object has no attribute '_is_destroye
|
|
0
|
15
|
August 15, 2025
|
|
训练过程中推理精度不变问题定位思路
|
|
0
|
10
|
August 1, 2025
|
|
MindSpore网络推理时使用Matmul矩阵乘法算子计算速度较慢
|
|
0
|
11
|
August 1, 2025
|
|
mindspore推理报错NameError:The name 'LTM' is not defined, or not supported in graph mode.及解决
|
|
0
|
9
|
August 1, 2025
|
|
MindSpore报错RuntimeError: Load op info form json config failed, version: Ascend310，及解决
|
|
0
|
10
|
August 1, 2025
|
|
使用converter_lite转换包含Dropout算子的模型至MindSpore模型失败
|
|
0
|
9
|
August 1, 2025
|
|
MindSpore Lite调用macBert模型报错
|
|
0
|
10
|
August 10, 2025
|
|
使用MindSpore Lite推理，报错RuntimeError: data size not equal! Numpy size: 6144000, Tensor size: 0
|
|
0
|
9
|
August 7, 2025
|
|
mindyolo在ckpt模型转为ONNX模型时报错
|
|
0
|
19
|
August 11, 2025
|