请问您部署成功了吗？自己训练的yolov5可以离线推理吗？
全部回复
-
-
-
LV.1 #4 thanos123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 ba20487
CNRT: 4.10.1 a884a9a
WARNING:root:
You are using conv, but set mean and std. Mean and std are only used
for 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]])
-
LV.1 #3 thanos123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 0
Traceback (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 syntax
root@a356ed4f3d6e:/torch/src/catch/examples/online/yolov5#
-
LV.1 #2 thanos123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？
-
LV.3 #1 HelloAI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。
请登录后评论