tiny-training

tiny-training copied to clipboard

how to train the quantized model on custom dataset

2

Hello I 'm an engineer from NXP. I'm very interested in your incredible work. I'd read your paper "On-Device Training Under 256KB Memory", we want to reproduce your works on...

tonyzhangnxp

Hello everyone, I try to reproduce the example but the compilation failed with the following error: 127 /* ty=int32 */ 127 127 () 1 127 ['fwd@output', 'v15_bias', 'v15_weight', 'v14_conv_2_bias', 'v14_conv_1_bias',...

mashemat

I follow the setup in the algorithm, and I fail to replicate the procedure in scripts by encountering the following error: ``` File "path/tiny-training/algorithm/train_cls.py", line 11, in from core.model import...

Django-Jiang

another idea : deep learning on web browser.

1

SeekPoint

From training to IR translation

4

Hi @songhan @zhijian-liu @Lyken17 @tonylins @synxlin . To my understanding (correct me if I'm wrong), the first step is to train models and get model weights saved in .pth files,...

kgorgor

Doubt in Algorithm Part : how you have prepared three models in int8 format: mbv2-w0.35, mcunet-5fps, proxyless-w0.3

1

Hi, In Algorithm part , you have used the pkl file for building the model (For eg mcunet-5fps.pkl in assets/mcu_models). Could you please let me know how you have create...

chinmaykhattar

https://user-images.githubusercontent.com/7783214/204312118-061344b4-7d21-4790-8e9a-1e9ad95c974f.mp4

Lyken17