Home

Awesome

A realtime remote service to get the keras callbacks to the telegram including the details of metrics .

<p align="center"> <a href="https://pypi.org/project/tensorgram/"> <img src="https://raw.githubusercontent.com/ksdkamesh99/TensorGram/main/Images/tensorgram.gif" alt="Logo"> </a> </p> <p align="center">

Downloads License Stargazers Issues Contributors Top Language Pull Request Forks

</p>

Features:-

  1. It helps by getting the updates of your model including metrics and loss function graphs which help user the view and get to a statistical conclusion about the model remotely.
  2. It is a biggest advantage for the users who need not spend hours and hours infront of system for watching the updates of the model.
  3. Updates you get are from a telegram bot.

Installation:-

You can easily install this telegram using following command.

pip install tensorgram

Dependencies/Requirements:-

  1. Keras
  2. Tensorflow
  3. Requests
  4. Matplotlib

Works on python>=3.7

How to use:-

import tensorflow
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation
import numpy as np 
from tensorflow.keras.optimizers import SGD

X = np.array([[0,0],[0,1],[1,0],[1,1]])
y = np.array([[0],[1],[1],[0]])

model = Sequential()
model.add(Dense(8, input_dim=2))
model.add(Activation('tanh'))
model.add(Dense(1))
model.add(Activation('sigmoid'))

sgd = SGD(learning_rate=0.1)
model.compile(loss='binary_crossentropy', optimizer=sgd,metrics=['accuracy'])



<p align="center"> <a href="https://pypi.org/project/tensorgram/"> <img src="https://raw.githubusercontent.com/ksdkamesh99/TensorGram/main/Images/start.jpeg" width=200px> </a> </p> * This application send you the data based on the unique chat id for every user in telegram. So to get your chat id you need to go to search and type @chatid_echo_bot and click on start to get your unique chat id. <p align="center"> <a href="https://pypi.org/project/tensorgram/"> <img src="https://raw.githubusercontent.com/ksdkamesh99/TensorGram/main/Images/chatid.jpeg" width=200px> </a> </p>
from tensorgram import TensorGram
tf=TensorGram("model-name","123456789")
model.fit(X, y, batch_size=1, epochs=10,callbacks=[tf],verbose=1)
<p align="center"> <a href="https://pypi.org/project/tensorgram/"> <img src="https://raw.githubusercontent.com/ksdkamesh99/TensorGram/main/Images/merged.png" width=500px float="left"> </a> </p>

Bug / Feature Request:-

If you find a bug (gave undesired results), kindly open an issue here by including your search query and the expected result.

If you'd like to request a new function, feel free to do so by opening an issue here. Please include sample queries and their corresponding results.

💥 How to Contribute ?

❤️ Thanks to our awesome contributors ✨✨

<table> <tr> <td> <a href="https://github.com/ksdkamesh99/TensorGram/graphs/contributors"> <img src="https://contrib.rocks/image?repo=ksdkamesh99/TensorGram" /> </a> </td> </tr> </table>

CONTRIBUTORS.md

Code of Conduct

You can find our Code of Conduct here.

Open-source Programs

Winter of Code is an open-source program envisioned by DevScript that helps understand the paradigm of Open Source contribution. It aims to bring students into the world of open source development and see the power of unified problem solving in real time.

<img src="https://devscript.tech/woc/img/WOC-logo.png" width="40%"> ## License

This project follows the MIT License.

Contact:-

For any kind of suggesstions/ help in code Please mail me at ksdkamesh99@gmail.com.