Wow super wonderful! i instantly understood what is word embedding - tqsm!!
@DevelopersHuttКүн бұрын
Glad you liked it!
@VictorHugo-um1kr4 күн бұрын
Very nice!!
@DevelopersHuttКүн бұрын
Thank you! Cheers!
@geirebass6 күн бұрын
The ai.google.dev dosnt longer support Pro vision model.. so it cant read from images it seems ? do you have any updates oon that ?
@user-jm2cp3oq4r12 күн бұрын
This guy is the best
@user-jm2cp3oq4r12 күн бұрын
Man, thanks for this stuff bruh hehe
@DevelopersHuttКүн бұрын
Any time!
@user-jm2cp3oq4r12 күн бұрын
Man, this is gold
@DevelopersHuttКүн бұрын
Thank you so much 🙏
@tejkiran183614 күн бұрын
Hy I was implementing the code, but even at 10000 epoch there are just some pattern seems like all patterns are same for all the digits. Is this how it will be? are do i need to train for more epoch inorder to get exact digits. And my accuracy are 100% 2000 [D loss: 9.11535289560561e-06, accuracy: 100.00] [G loss: 0.005449621006846428] 3000 [D loss: 2.2335058815770026e-06, accuracy: 100.00] [G loss: 0.0015377863310277462] btw i am using cpu
@DevelopersHuttКүн бұрын
Can you try on Google colab with gpu and see
@nimendraamiththa117317 күн бұрын
Got the idea 💡... thanks ❤
@DevelopersHuttКүн бұрын
Most welcome 😊
@MemesBook.202421 күн бұрын
source code plsss
@justablank118422 күн бұрын
Best programming youtuber ever
@sujalmistry767723 күн бұрын
Git repo?
@kalidasy486724 күн бұрын
Excellent explanation... Wonderfu!
@user-bi2jm1cn1hАй бұрын
What will happen if instead of one-hot encoding hard-labels we have soft labels distribution?
@clusteringmiuАй бұрын
very clear. This explanation is so underrated... Thank you so much !!!
@ebadsayed4872 ай бұрын
When I am running the 49th line for training the model, it gives me an attribute error ValueError: Only input tensors may be passed as positional arguments. The following argument value should be passed as a keyword argument: True (of type <class 'bool'>) Can you resolve this please?
@algorithmo1342 ай бұрын
How do you define the loss function of discriminator and generator in the code? I am lost
@hifalog2 ай бұрын
How can ı change to answer of Ai to Turkish language
@DevelopersHutt2 ай бұрын
Trying adding instruction to prompt
@rajshekharrakshit90582 ай бұрын
What's the meaning of this video, u directly copied the whole code from tensorflow official website.
@DevelopersHutt2 ай бұрын
The goal was to walk you through each piece of code and what exactly that line is doing. Making you understand the concept is always my goal. Is there anything else you worry about?
@fazalbhai1232 ай бұрын
how to make Flutter app which does the same. Please help in this regard or make a video on this.
@DevelopersHutt2 ай бұрын
Thanks for reaching out. Can you please specify more about what kind of thing you want at [email protected]
@raffaulislam74232 ай бұрын
Is this project compatible with the wear os? I mean can this project be built for the wearable devices?
@DevelopersHutt2 ай бұрын
With right data. Yes
@karanshingde2 ай бұрын
Great Explanation! I have used DDP with accelerate in transformers. Along with Model it also loads whole data in respected GPUs.
@souhail_lh30133 ай бұрын
can you please send a link to your code?
@robokishan3 ай бұрын
amazingly explained
@DevelopersHutt3 ай бұрын
Glad you liked it
@MuhammadZubair-cu6cx3 ай бұрын
Hi there, Thank you! I need your help with translating from Urdu to English using T5 small. Could you please guide me? I'm willing to tip $50 for your assistance. I'm quite new to this. I also have a dataset ready. Thanks!
@flow29973 ай бұрын
do you have a pytorch alternative
@DevelopersHutt3 ай бұрын
Not yet
@DevelopersHutt3 ай бұрын
Not yet
@gfsoftwaredotcom3 ай бұрын
Finally a video using tensorflow. Thanks !
@piyukr3 ай бұрын
Good analogy brother. Thanks for making this informative video!
@Rapperabstar3 ай бұрын
Speechless 😶 Thanks man! You have got another subscriber ❤
@DevelopersHutt3 ай бұрын
Thank you so much 💓
@TianqiZhu-ud5kr3 ай бұрын
straight to the point
@tehreemqasim22043 ай бұрын
great video
@DevelopersHutt3 ай бұрын
Glad you enjoyed it
@binarify43643 ай бұрын
Awesome 2 min video mate ! Cheers !
@DevelopersHutt3 ай бұрын
🍻
@gunamrit3 ай бұрын
Good work!
@tehreemqasim22043 ай бұрын
excellent video
@pashamorozov82573 ай бұрын
this video is just a treasure. the simplest explanation. thanks!!
@ZXTOWN3 ай бұрын
Sorry to say too many errors are coming on thus code.
@DevelopersHutt3 ай бұрын
Like?
@DevelopersHutt3 ай бұрын
Can you post it somewhere for visibility
@user-vm3iy9mb3g3 ай бұрын
tkns alot😇
@grapix11844 ай бұрын
just perfect, thanks!
@arimasters19804 ай бұрын
Hi thanks for the video but I believe in the last BLEU formula there is a typo, an exponential term is missing.
@DevelopersHutt4 ай бұрын
Thanks for identification. Will improve ❤️
@harshmalik34704 ай бұрын
Such a complex topic and now I know it, like it's nothing. Big thanks to this video.
@DevelopersHutt4 ай бұрын
I'm glad you liked it ❤️
@haulu1594 ай бұрын
with another dataset do like this or i need to cusstome the dataset
@DevelopersHutt4 ай бұрын
If you're using the same process as in video, then yes you'll need the data in the same format.
@user-oq7ju6vp7j4 ай бұрын
Thank you very much. Know, all people who make such videos to help other to understand new concepts are incredible. You make learning process much easier and more interesting. Keep going!!!
@efoanopa4 ай бұрын
I would like to know... Why is it that in the get_angles function, you floor-divided i by 2? That part np.power(10000, 2 * (i//2)/dmodel)
@DevelopersHutt4 ай бұрын
I'm glad you asked! That's for positional encoding. You can find the context here.kzbin.info/www/bejne/bGfWlnyKpMqaq6csi=mX83N2ETA1DFOVu- If you still struggle understanding it, drop me a line
@efoanopa4 ай бұрын
@@DevelopersHutt, you see in the formular, it was just 2*i But you made it 2*(i//2) and I am finding it difficult to understand why
@efoanopa4 ай бұрын
@@DevelopersHutt also, can you please send a link to your code?
@voyager434 ай бұрын
libraries are outdated, kindly update the code pls, nice project though
@DevelopersHutt4 ай бұрын
Thanks for the reminder. Will do 🙂
@voyager434 ай бұрын
@@DevelopersHutt yeah pls, coz I tried to solve the errors but still having issues
@Fleck20114 ай бұрын
Very nice, thanks!
@DevelopersHutt4 ай бұрын
I'm glad you liked it
@Daily_language4 ай бұрын
very good!
@DevelopersHutt4 ай бұрын
Thanks ❤️
@timiokusi4 ай бұрын
Hello brother, I am following your video but I am getting an error with the lstm layer which says no op kernel supports the op clipbyvalue in android studio. Would really appreciate if we can discuss and I can share this with you cos mine is for a fall detection. I am doing this for a uni project. Please help, thanks
@DevelopersHutt4 ай бұрын
Are you using the same tensorflow version as I did in android?
@GilbertoAlvarado-di5yc4 ай бұрын
Hi, In my PC it did not work ¿, I obtained this instead : 2024-04-01 17:44:59.714881: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1616] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 5464 MB memory: -> device: 0, name: NVIDIA GeForce RTX 4060 Laptop GPU, pci bus id: 0000:01:00.0, compute capability: 8.9 (224, 224, 3) (224, 224, 1) Traceback (most recent call last): File "C:\Users\galva\PycharmProjects\unet\main.py", line 46, in <module> c1 = Conv2D(32, (3,3) , activation = 'relu', kernel_inizializer = 'he_normal', padding = 'same')(inputs) File "C:\Users\galva\anaconda3\envs\py310\lib\site-packages\keras\dtensor\utils.py", line 96, in _wrap_function init_method(layer_instance, *args, **kwargs) File "C:\Users\galva\anaconda3\envs\py310\lib\site-packages\keras\layers\convolutional\conv2d.py", line 178, in __init__ super().__init__( File "C:\Users\galva\anaconda3\envs\py310\lib\site-packages\keras\layers\convolutional\base_conv.py", line 118, in __init__ super().__init__( File "C:\Users\galva\anaconda3\envs\py310\lib\site-packages\tensorflow\python\trackable\base.py", line 205, in _method_wrapper result = method(self, *args, **kwargs) File "C:\Users\galva\anaconda3\envs\py310\lib\site-packages\keras\engine\base_layer.py", line 335, in __init__ generic_utils.validate_kwargs(kwargs, allowed_kwargs) File "C:\Users\galva\anaconda3\envs\py310\lib\site-packages\keras\utils\generic_utils.py", line 1269, in validate_kwargs raise TypeError(error_message, kwarg) TypeError: ('Keyword argument not understood:', 'kernel_inizializer')
@user-xo1uk7uk6d4 ай бұрын
what if images are MNIST-back-image, how to denoise them ??
@DevelopersHutt4 ай бұрын
What do you mean by MNIST-back-image?
@user-dl1yn7tn5o4 ай бұрын
can you help me in finding another dataset of same project because this output mostly to jogging only
@DevelopersHutt4 ай бұрын
I got that dataset from kaggle. Not sure if there is an update one as well .