[86022.030544] usb 4-2: new SuperSpeed USB device number 2 using xhci_hcd [86032.041106] usb 4-2: New USB device strings: Mfr=2, Product=3, SerialNumber=1
[86032.041110] usb 4-2: Product
Jul 9 09:09:56 me kernel: [ 2740.896079] usb 4-2: new full-speed USB device number 4 using uhci_hcdJul 9 09:09:57 me kernel: [ 2741.080112] usb 4-2: New USB device found, idVendor=046d, idProduct=c52fJul 9 09:09:57 me kernel: [ 2741.080118] usb 4-2: New USB device strin
.[147333.530241] usb 4-2: new SuperSpeed] usb 4-2: Product: VLI Product String
[147333.554422] usb 4-2: Manufacturer: VLI manufacture String[147333.554426] usb 4-2: SerialNumber: 00000000
USB3.0 -蓝色/5 SW/SWBus 004 Device 005: ID 054c:09c2 Sony Corp.[ 241.322233] usb 4-2: new SuperSpeed USB device number 4 using xhci_hcd[ 241.435830] usb 4-2: New US
我对知识蒸馏了解不多。我有一个问题。 有一个模型显示了99%的性能(10class图像分类)。但我不能使用更大的模型,因为我必须保持推理时间。如果我使用另一个大模型训练知识蒸馏,是否会产生整体效应? -option-或者让我知道是否有比这更好的方法来提高性能。 enter image description here
驱动器设置为从模式.[ 1672.540299] usb 4-2: new SuperSpeed USB device number 7 using xhci_hcd[ 1672.562871] usb 4-2: New USB devicestrings: Mfr=4, Product=5, SerialNumber=6
[ 1672.562873] usb <em