I have added the source code in the description. Since some issues have been reported by subscribers in the deployment, i have also added an alternative deployment code which does not need ngrok authentication code. Check it out and let me know in the comments which code worked for you.
Some of you might get different results if ur doing this on ur transfer learning models, this lil modified code will help u in getting the better and accurate results in prediction. change the import and predict code to this from skimage import transform size = (224,224) image = ImageOps.fit(image_data, size, Image.ANTIALIAS) image = np.asarray(image) np_image = transform.resize(image, (224, 224, 3)) np_image = np.expand_dims(np_image, axis=0) img = np_image
@@NachiketaHebbar sir I had a doubt that how can we do the same thing for YOLOv3 object detection. I mean can we deploy it as web app. Please reply early, if possible...it's urgent!!!
Hi! Thank you so much for the walkthrough. I am having trouble with the line: !nohup streamlit run app.py & I keep getting different errors. One is a syntax error and the other is "OSError: Background processes not supported. " I used python in Spyder to build my model and have been using Jupyter Notebooks for everything else. I am using a Windows machine. Any advice?
ERROR: google-colab 1.0.0 has requirement ipykernel~=4.10, but you'll have ipykernel 5.5.5 which is incompatible. /bin/bash: streamlit: command not found what to do?
hello there, it is stated that we can deply directly from google colab right? but whenever i run the code and open up the link the site cant be reached. how can i solve this?
THe deploy code still does not work. I really feel frustrated about this. I have spend about 4 hours with that but get message"This page isn’t working"
Hello! Thanks for the video! It helped me alot! BTW, With which video editor we can shoot the video like yours? Displaying screen + The presenter in the small frame?
I tried to run your code and keep getting this error. Can you help me understand what is wrong ? I did load a hdf5 model following your code. File "app.py", line 45, in st.write(prediction) NameError: name 'prediction' is not defined
Hello! First of all, thank you for your video and notebooks. When i running the notebook, i have an error. ModuleNotFoundError: No module named 'pyngrok'. How can i solve this problem?
Hey, great video and really helpful. I followed along and everything seems to be working but when i open the link it says "it is unreachable". Please give suggestion on the same
Hi, very nice video thank you but i am getting an error. When I select an image for guessing I get this error TypeError: 'Image' object is not subscriptable. Pls help me!
We can't call it IoT yet. If there was some sensor or camera capturing pictures of flowers , uploading it onto the cloud and If we then make a prediction on it, then we can classify it as deep learning using IoT.
Yes, the procedure will be mostly same. You will have to save the ml model as a pickle file and load it In the webapp. You can check my video on that in my deployment of ml model playlist.
I have added the source code in the description. Since some issues have been reported by subscribers in the deployment, i have also added an alternative deployment code which does not need ngrok authentication code. Check it out and let me know in the comments which code worked for you.
Pleaaase how can I instead of importing the image, display multiple images and select one to make the prediction?
you're rocking!!! cant express the amount of happiness i have right now
Really glad to hear that!
hii.. your video is very interesting, but I found a problem when i try it. my localhost wont connect, do you know how to fix it?
Thank you so much for your video. I am new to the programming language. Your course is understandable.
hii Nachiketa , the complete code has been executed successfully but at the end i am not able to open the website, can you please help me with that
Some of you might get different results if ur doing this on ur transfer learning models, this lil modified code will help u in getting the better and accurate results in prediction. change the import and predict code to this
from skimage import transform
size = (224,224)
image = ImageOps.fit(image_data, size, Image.ANTIALIAS)
image = np.asarray(image)
np_image = transform.resize(image, (224, 224, 3))
np_image = np.expand_dims(np_image, axis=0)
img = np_image
This was awesome!!
Thank you so much...it really helped a lot!!!
Your welcome, glad it helped!
@@NachiketaHebbar sir I had a doubt that how can we do the same thing for YOLOv3 object detection. I mean can we deploy it as web app. Please reply early, if possible...it's urgent!!!
@@anmoldubey3517 it's possible, you can check out this github repo for the same github.com/robmarkcole/deepstack-ui
I had to pip install pyngrok and then import ngrok from there before running the ngrok auth token
Hi Nachiketa, do you have any tutorial related to deploying a deep learning model which identifies the speaker.
Hi! Thank you so much for the walkthrough. I am having trouble with the line:
!nohup streamlit run app.py &
I keep getting different errors. One is a syntax error and the other is "OSError: Background processes not supported.
"
I used python in Spyder to build my model and have been using Jupyter Notebooks for everything else. I am using a Windows machine. Any advice?
same errors...where u able to solve it??...pls help
nicely explained.. god bless you with more and more enthu and knowledge
Thanks a lot!
failed to complete tunnel connection what to do
Same did you find it ?
Same with me, can you fix it?
This is a nice video.!!
What if i want to use my images locally and not using from tensorflow. how you should do it? Thanks
ERROR: google-colab 1.0.0 has requirement ipykernel~=4.10, but you'll have ipykernel 5.5.5 which is incompatible.
/bin/bash: streamlit: command not found
what to do?
The code is not working.. I tried both codes... Please could you help with it?
So when I run my code it is showing an error like "file object has no attribute predict" how can I fix this?
hello there, it is stated that we can deply directly from google colab right? but whenever i run the code and open up the link the site cant be reached. how can i solve this?
I am getting an error like /bin/bash: ngrok: command not found while executing authentication cell
THe deploy code still does not work. I really feel frustrated about this. I have spend about 4 hours with that but get message"This page isn’t working"
do you solved the problem,please reply i am facing the same issue as this site can't be reached?
Hello! Thanks for the video! It helped me alot!
BTW, With which video editor we can shoot the video like yours?
Displaying screen + The presenter in the small frame?
I use this video editing software called Movavi.
not able to run !ngrok authtoken in colab. Please help!!
getting this message>> /bin/bash: grok: command not found.
Good Boy, but how about print accuracy...
Great video...did not know about ngrok...thanks.
Creating a video on using Docker in Heroku to deploy would be a great video...and helpful for us
Thanks, will try to make a video on it!
@@NachiketaHebbar your videos are really good, thanks for helping out
I tried to run your code and keep getting this error.
Can you help me understand what is wrong ?
I did load a hdf5 model following your code.
File "app.py", line 45, in
st.write(prediction)
NameError: name 'prediction' is not defined
I am facing the same issue , were u able to resolve it ?
Hello! First of all, thank you for your video and notebooks. When i running the notebook, i have an error.
ModuleNotFoundError: No module named 'pyngrok'.
How can i solve this problem?
Did you do pip install pyngrok ?
@@NachiketaHebbar sure, i did
@@BuseYaren same issue. Were you able to resolve this?
getting error in installing streamlit. pip install streamlit giving error
Use ' !pip install streamlit'
Can we add login and register page on this ?
Hey, great video and really helpful. I followed along and everything seems to be working but when i open the link it says "it is unreachable". Please give suggestion on the same
do you solved the problem,please reply i am facing the same issue as this site can't be reached?
how to fix port nbr i have port error problem
Hi,
very nice video thank you but i am getting an error.
When I select an image for guessing I get this error TypeError: 'Image' object is not subscriptable. Pls help me!
You have to convert the image into a Numpy array before trying to reshape it
can we say that its deep learning app using IoT
We can't call it IoT yet. If there was some sensor or camera capturing pictures of flowers , uploading it onto the cloud and If we then make a prediction on it, then we can classify it as deep learning using IoT.
@@NachiketaHebbar in real time scenario, is it worthy to make prediction on cloud
Can you do an example on GCloud.
Will try to make one on it soon
Whenever I am trying to run the authentication command it is showing command not found
You have to add ! mark before ngrok in the authentication command and you can remove the' ./'
first install pyngrok, import grok from pyngrok and then use ngrok authtoken command
see in website this show "not secure" 😁😁😁😁
Bro Can you please help me I am getting ngrok command not found error in google colab
i have added the code in the description. Try running that
Great video! Can you share the notebook?
added in the description
It will be great if you will share the colab notebook.
exactly , because the code gives errors
Getting error at line !nohup streamlit run app.py & as bsckground processes not supported... How to resolve this error... Btw nice video😊
I have also the same problem. How can I resolve this error?
Your code has errors
I need help Please
Can we try the same code In juypter?
Yes, you can
@@NachiketaHebbar thank you so much👍
can u give me the git link of your source code, please?
Added that in the description
Bro can we deploy an Ml model in googlecolab and stremlit
Yes, the procedure will be mostly same. You will have to save the ml model as a pickle file and load it In the webapp. You can check my video on that in my deployment of ml model playlist.
@@NachiketaHebbar tnx bro
Sir plz share google colab sheet plz plz plz sir
I have added it in the description
plz share the code would be useful ::
added that in the description
Bhai tu devmanus hai