- W Adjust min from [-5.106467] to [0.] for relu relu8_39
- W Adjust min from [-5.106467] to [0.] for relu relu13_67
- W Adjust min from [-5.106467] to [0.] for relu relu15_76
- W Adjust min from [-5.106467] to [0.] for relu relu17_85
- W Adjust min from [-4.101224] to [0.] for relu relu18_90
- W Adjust min from [-2.5565655] to [0.] for relu relu43_218
- W Adjust min from [-4.101224] to [0.] for relu relu23_118
- W Adjust min from [-4.101224] to [0.] for relu relu25_127
- W Adjust min from [-4.101224] to [0.] for relu relu27_136
- W Adjust min from [-3.4539304] to [0.] for relu relu28_141
- W Adjust min from [-24.208406] to [0.] for relu relu38_193
- W Adjust min from [-1.8253068] to [0.] for relu relu44_223
复制代码
请问我该怎样混合量化?jefferyzhang 发表于 2020-1-2 08:53
1. 确定是精度差还是压根就算错了,如果得出来结果和pytorch或者tf差距很大,或者符号位都不一样,那就是计 ...
LSC 发表于 2020-1-2 09:46
好的感谢提供思路,请问有没有办法查看每一层的参数?开对比一下量化前后参数差异。 ...
jefferyzhang 发表于 2020-1-2 08:53
1. 确定是精度差还是压根就算错了,如果得出来结果和pytorch或者tf差距很大,或者符号位都不一样,那就是计 ...
LSC 发表于 2020-1-2 10:48
我上传不了图片,所以我传到百度云里了,result1.jpg是不使用量化的结果,result3.jpg是u8量化的结果,re ...
jefferyzhang 发表于 2020-1-2 11:05
如果不是bug,那就只能试试二分法做混合量化
LSC 发表于 2020-1-2 11:07
明白,我传的是三张结果图,确认一下是不是只是精度问题。
jefferyzhang 发表于 2020-1-2 12:01
从图是看不出精度问题的,只能推断出很可能是精度问题。。。
检不捡的出还得看你NMS阈值设置多少 ...
jefferyzhang 发表于 2020-1-2 12:01
从图是看不出精度问题的,只能推断出很可能是精度问题。。。
检不捡的出还得看你NMS阈值设置多少 ...
- ...
- I Config File "/home/lsc/anaconda3/envs/RKNN/lib/python3.6/site-packages/rknn/base/RK1808_PID0X82" load/generated successfully
- I Initialzing network optimizer by /home/lsc/anaconda3/envs/RKNN/lib/python3.6/site-packages/rknn/base/RK1808_PID0X82 ...
- ...
复制代码
- Create RKNN model fail!
- E Catch exception when init runtime!
- E Traceback (most recent call last):
- E File "rknn/api/rknn_base.py", line 788, in rknn.api.rknn_base.RKNNBase.init_runtime
- E File "rknn/api/rknn_runtime.py", line 303, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
- E Exception: RKNN init failed. error code: RKNN_ERR_DEVICE_UNAVAILABLE
- W We need do some initial work, it will increase call time of inference for the first time.
- Create RKNN model fail!
- E Catch exception when init model!
- E Traceback (most recent call last):
- E File "rknn/api/rknn_base.py", line 901, in rknn.api.rknn_base.RKNNBase.inference
- E File "rknn/api/rknn_runtime.py", line 303, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
- E Exception: RKNN init failed. error code: RKNN_ERR_DEVICE_UNAVAILABLE
- Traceback (most recent call last):
- File "ctdet.py", line 10, in <module>
- det.run(img)
- File "/home/lsc/rknn-toolkit-v1.3.0/centernet/ctdet_rknn_v2/detector.py", line 93, in run
- output, dets = self.process(images)
- File "/home/lsc/rknn-toolkit-v1.3.0/centernet/ctdet_rknn_v2/detector.py", line 44, in process
- hm = output[3].reshape((1,80,128,128))
- TypeError: 'NoneType' object is not subscriptable
复制代码
欢迎光临 Toybrick (https://t.rock-chips.com/) | Powered by Discuz! X3.3 |