Intel® Edge Software Hub
Get answers from community peers to your questions about building Edge Software Hub solutions for edge compute node.
Announcements
Welcome to the Intel Community! If you like the answer to your question, please mark it as 'Accepted Solution' to help others.

The Edge Software Vision Package for Red Hat Enterprise Linux is now available here.

Learn more about developing on Intel® Hardware and Software here.
394 Discussions

No access "http://localhost:5000"

HuynhVanThuan
New Contributor I
6,616 Views

I have successfully run EII but for some reason I still can't access "http://localhost:5000" even though I followed the instructions. Can anyone help me? Here are all the files I followed your instructions

 

Labels (1)
0 Kudos
1 Solution
cindyl
Employee
6,499 Views

Hi Huynh, 

 

It seems like that there's an issue with the UDF. You can either create a new UDF or edit the current UDF for classification. If you are unsure about the code, you can refer to the file from "/Edge_Insights_for_Industrial_2.6.2/training-and-learning-suite/nnframework/tf/inferOpenvino/classificationInfer.py".

 

Regards,

Cindy



View solution in original post

8 Replies
Sahira_Intel
Moderator
6,565 Views

Hi,

It looks like the app was successfully launched but I would like to try to replicate this error. 

Can you please share more information about this error. Are you trying to run an EII demo? 

 

Sincerely,

Sahira

 


0 Kudos
HuynhVanThuan
New Contributor I
6,540 Views

Hi Sahira,

 

I want to give you a few more photos in this post. Hope it will give you a lot of useful information. If you need any information please let me know. Thank you so much

 

Best regards,

Mr. Huynh Van Thuan

 

0 Kudos
cindyl
Employee
6,551 Views

Hi Huynh,

 

Can you share the logs for ia_video_analytics and ia_video_ingestion? 

 $ docker logs -f ia_video_analytics

 $ docker logs -f ia_video_ingestion

 

Regards,

Cindy

0 Kudos
HuynhVanThuan
New Contributor I
6,545 Views

Hi Cindy,

 

The document you need to see is here. If you need any more information, please let me know. I am very happy about this. Thank you so much

 

Best Regards,

Mr. Huynh Van Thuan

 

 

0 Kudos
cindyl
Employee
6,533 Views

Hi Huynh,

 

Seems like there is an error with the custom UDF. May I know whether you are doing classification or object detection?

 

Regards,

Cindy

0 Kudos
HuynhVanThuan
New Contributor I
6,519 Views

Hi Cindy,

 

I'm doing object classification. If you need any more information let me know. Thanks

 

Regards,

Huynh

0 Kudos
cindyl
Employee
6,500 Views

Hi Huynh, 

 

It seems like that there's an issue with the UDF. You can either create a new UDF or edit the current UDF for classification. If you are unsure about the code, you can refer to the file from "/Edge_Insights_for_Industrial_2.6.2/training-and-learning-suite/nnframework/tf/inferOpenvino/classificationInfer.py".

 

Regards,

Cindy



HuynhVanThuan
New Contributor I
6,551 Views

Hi Sahira,

 

I want to make a demo application as mentioned from slide 35 -> 37 (AI4I Day 5 & 6.pdf) and I need to be able to access the "http://local:5000" link to be able to do this. 

 

Here is the sequence I did while running EII

 

1. copy ais to /home/ais/edge_insights_industrial/Edge_Insights_for_Industrial_2.6/IEdgeInsights/common/video/udfs/python
2. copy and replace .xml and bin files to /home/ais/edge_insights_industrial/Edge_Insights_for_Industrial_2.6/IEdgeInsights/common/video/udfs/python/ais/ref
3. Add label in labels.txt in /home/ais/edge_insights_industrial/Edge_Insights_for_Industrial_2.6/IEdgeInsights/common/video/udfs/python/ais/ref
4. go to /home/ais/edge_insights_industrial/Edge_Insights_for_Industrial_2.6/IEdgeInsights/build and run the builder script for video-streaming use case
```
python3 builder.py -f usecases/video-streaming.yml
```
5. Replace config files:
a. copy and replace classification/eii_config.json in /home/ais/edge_insights_industrial/Edge_Insights_for_Industrial_2.6/IEdgeInsights/build/provision/config if doing classification
b. copy and replace object detection/eii_config.json in /home/ais/edge_insights_industrial/Edge_Insights_for_Industrial_2.6/IEdgeInsights/build/provision/config if doing object detection


6. provision, build and run
```
cd provision && sudo -E ./provision.sh ../docker-compose.yml
cd .. && docker-compose -f docker-compose-build.yml build
docker-compose up -d
```
7. to clode EII visualizer, run the following command in the same terminal
```
docker-compose down
```

 

After I completed the above command sequence successfully, I continued to follow the command sequence in the file "AI41_node_red_command.txt" to be able to access the address "http://localhost:5000". Besides, I also refer to the document "AI4I Day 5 & 6.pdf" from slides 10 -> 12 and 16 -> 18 to execute the following sequence of commands

 

----------------------------------------------
1. Install Visual Studio code
----------------------------------------------

sudo snap install --classic code

----------------------------------------------
2. Preparing your MQTT Broker
----------------------------------------------

sudo nano /etc/mosquitto/mosquitto.conf

----------------------------------------------

bind_address 0.0.0.0
port 1884

-----------------------------------------------

sudo systemctl restart mosquitto.service

sudo systemctl status mosquitto.service

----------------------------------------------
3. Include MQTT in the docker for Video analytics
----------------------------------------------

numpy==1.18.0
paho-mqtt==1.4.0

----------------------------------------------
4. Include mqtt in the udf
----------------------------------------------

import paho.mqtt.client as mqtt
client = mqtt.Client()
client.connect("192.168.100.21", 1884, 60)

-----------------------------------------------

client.publish("/ais/",json.dumps({"Result":defects}))

----------------------------------------------
5. Modify UDF: Provision, build and run
----------------------------------------------

cd provision && sudo -E ./provision.sh ../docker-compose.yml
cd .. && docker-compose -f docker-compose-build.yml build
docker-compose up -d

--------------------------------------

 

After done come here. I started accessing "http://localhost:5000" and I still can't access it even though I don't know where I went wrong

 

0 Kudos
Reply