LV.1

thanos123

30积分0赞

4 帖子 8 回复 0 收藏

TA的动态

TA的帖子

TA的回复

模型移植到MLU270 我的回复：#5yy999回复请问您部署成功了吗？自己训练的yolov5可以离线推理吗？可以 0

请问可以用270来训练yolov5模型吗？ 我的回复：能交流一下吗楼主 0

模型移植到MLU270 我的回复：跑手册中的minist.py代码时，出现下面的警告，查看了mlu_functions.yaml文件中对min 和max op是支持的，是什么原因导致没有在MLU上运行的呢？(pytorch) root@b22856f7374f:/home# python minst.py CNML: 7.10.2 ba20487CNRT: 4.10.1 a884a9aWARNING:root:You are using conv, but set mean and std. Mean and std are only usedfor first conv, which will not be used in the situation. Please do not set them![WARNING][/pytorch/catch/torch_mlu/csrc/aten/operators/op_methods.cpp][line:1437][min][thread:139825170163456][process:32]: min Op cannot run on MLU device, start running on CPU![WARNING][/pytorch/catch/torch_mlu/csrc/aten/operators/op_methods.cpp][line:1379][max][thread:139825170163456][process:32]: max Op cannot run on MLU device, start running on CPU![WARNING][/pytorch/catch/torch_mlu/csrc/aten/operators/op_methods.cpp][line:1437][min][thread:139825170163456][process:32]: min Op cannot run on MLU device, start running on CPU![WARNING][/pytorch/catch/torch_mlu/csrc/aten/operators/op_methods.cpp][line:1379][max][thread:139825170163456][process:32]: max Op cannot run on MLU device, start running on CPU![WARNING][/pytorch/catch/torch_mlu/csrc/aten/operators/op_methods.cpp][line:1437][min][thread:139825170163456][process:32]: min Op cannot run on MLU device, start running on CPU![WARNING][/pytorch/catch/torch_mlu/csrc/aten/operators/op_methods.cpp][line:1379][max][thread:139825170163456][process:32]: max Op cannot run on MLU device, start running on CPU![WARNING][/pytorch/catch/torch_mlu/csrc/aten/operators/op_methods.cpp][line:1437][min][thread:139825170163456][process:32]: min Op cannot run on MLU device, start running on CPU![WARNING][/pytorch/catch/torch_mlu/csrc/aten/operators/op_methods.cpp][line:1379][max][thread:139825170163456][process:32]: max Op cannot run on MLU device, start running on CPU!tensor([[-2.3016, -2.3202, -2.3819, -2.1831, -2.3390, -2.2291, -2.2857, -2.3253, -2.3701, -2.3062]]) 0

模型移植到MLU270 我的回复：执行手册的yolov5 案例报错：root@a356ed4f3d6e:/torch/src/catch/examples/online/yolov5# python test.py --mlu true --jit true --save_pt false --offline_mode false --batch_size 16 --core_number 16 --ann_dir $COCO_PATH_PYTORCH/COCO --image_number 4992 --half_input 0 --quantized_mode 2 --coco_path $COCO_PATH_PYTORCH --quantization false --input_channel_order 0Traceback (most recent call last): File "test.py", line 3, in <module> from utils.datasets import * File "/torch/src/catch/examples/online/yolov5/utils/datasets.py", line 107 yield from iter(self.sampler) ^SyntaxError: invalid syntaxroot@a356ed4f3d6e:/torch/src/catch/examples/online/yolov5# 0

模型移植到MLU270 我的回复：#1HelloAI回复https://developer.cambricon.com/index/document/down.html?ddd=9下载PyTorch的手册，熟悉量化和融合推理相关的操作。展开自己训练了一个yolov5s权重,在部署时，模型文件用你们提供的Demo中的yolo.py，我只需要把自己的权重量化后进行推理就可以了吗？学习你们的教程时https://developer.cambricon.com/index/curriculum/expdetails/id/13/classid/8.html其中的视频连接已经失效，请问有最新的视频地址吗？ 0