-
Notifications
You must be signed in to change notification settings - Fork 38
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
will change the deep learning framework from tensorflow to pytorch [The description is attatched below] #18
Comments
please assign me the task @Devanik21 |
if u have any suggestions u can surely let me know @Devanik21 |
Alright, try!🫡 |
Thanks a lot for giving me this opportunity @Devanik21 I will try my best! |
hello, are u working on it? @shravya312 |
I am working on it,its taking time I will submit pr as soon its done can u please add labels to pull request accepted the leader board is live the pr is not reflecting @Devanik21 |
I have updated the labels to official ones, now it will be counted. |
No not in the issue in the pr @Devanik21 |
in the right side labels is none yet |
Please wait |
haa sure 😇 |
Thanks a lot It is updated !!😇 |
By today it will be done @Devanik21 |
A dynamic computation graph is a key feature of PyTorch that allows the framework to create a map of calculations while the program is running.
Key Points:
Built While Running: The graph is formed as you run your code, not before. This means it can change every time you execute it.
Flexible and Adaptive: You can easily change how your model behaves based on the data you provide. For example, if the input data is different, the graph adjusts accordingly.
Easy to Debug: Since the graph is created as the code runs, you can use regular Python tools to check for errors right where they happen, making it easier to fix problems.
The text was updated successfully, but these errors were encountered: