---
tags: handoverOK, Tensorflow,Keras on Smoking
---

# AI_Tensorflow using using a pre-trained model inception resenet v2

### 5204 Enviorment
> 目前相關資源都放在 5204上~這台配有1T 的資料碟與256G ssd系統碟 aewin@192.168.99.90:/home/aewin/work/work/work/
> 你可存取5204 ~透過ssh scp SAMBA
> SAMBA 和 SSH 帳密皆為aewin/aewin !
> 目前5204 IP為 192.168.99.90

ssh aewin@192.168.99.90:/home/aewin/work/work/work/
or 
scp aewin@192.168.99.90:/home/aewin/test_file ./your_pc

#### Tensorflow Code and Data

aewin@192.168.99.90:/home/aewin/work/work/work/tensorflow/code/V001

### TRANSFER LEARNING
https://medium.com/@yuhsienyeh/machine-learning-transfer-learning-%E9%81%B7%E7%A7%BB%E5%AD%B8%E7%BF%92-5095f8a14367

### TF-slim
https://zhuanlan.zhihu.com/p/41679504
### TFRecord files
https://blog.csdn.net/miaomiaoyuan/article/details/56865361
### Tensorflow convert .ckpt to .pb
https://cloud.tencent.com/developer/ask/188650
### why using Tensorflow Resnet V2
https://www.intel.ai/model-zoo-ia/#gs.l29s00

### Run Demo Code by using tensorflow to do AI

https://github.com/hsiaojung/tflearn_smo

ssh aewin@192.168.99.90 first~

sudo docker run --runtime=nvidia -it --rm  -p 8888:8888  tensorflow/tensorflow:latest-gpu-py3-jupyter bash
or
sudo docker run -it  --rm -p 8888:8888  -v /home/cyril/work/work/work:/tf/mnt   tensorflow/tensorflow:latest-gpu-py3-jupyter bash


docker run --runtime=nvidia -it -p 8888:8888 tensorflow/tensorflow:latest-gpu bash

sudo docker run --runtime=nvidia -v /home/aewin/work/:/mnt -it -p 8888:8888 tensorflow:gpu bash
 
cat /tf/command 
jupyter notebook --ip='*'  --allow-root