Видео

Just amazing 🤩

Hey I was curious where you are getting this loss function from. Especially the object loss term where the iou score is multiplied to target[..., 0]. I have seen this same scheme appear in all YOLOv3 implementations and each time it is stated that this is "what is done in the paper" but this is not mentioned in the paper.

I wonder why some methods have axEs and some have axIs

does anybody know what plugin or something he uses to get those code recommendations?

😃

thanku for all your lectures which are full of knowledge ,can u please make a video on einops if possible, thankyou in advance

Hi there, I was wondering how I get Kohya_GUI running?

Can you give us your plugins details please. Most needed !

Thank you! Very helpful video

Too good! so many concepts cleared

Much important to learn pytorch lightning?

Really helpful clear work. Thank you.

Great tutorial - I want to stress though that this model you trained is basically only memorizing the training data. If you created a validation set and looked at some of the results, it will perform very poorly. You simply did not have enough data. The original authors actually pretrained the backbone with ImageNet, so that is something to consider in your case here.

I got this issue, please help Value error, If 'border_mode' is set to 'BORDER_CONSTANT', 'value' must be provided. [type=value_error, input_value={'min_height': 499, 'min_...apply': False, 'p': 1.0}, input_type=dict]

well done

Thanks!

thank you for the vid :) great!

hi, it seems that torchtext got quite a bit of a changeover and this tutorial's contents are outdated, any chances you might wanna update it?

Thanks a lot man this is great help

In place of disc.zero_grad(), I think we should have opt_disc.zero_grad(), isn't it? I also confirmed it with ChatGpt. Can anyone else also confirm it?

What is your development environment

Hello, I am getting this error when trying to map the encoding function to the test dataset. Can anyone help me? Here is the function: # wrap the function with a `tf.py_function` # This allows TensorFlow to call the Python function within its data pipeline. def tf_my_encoding(text, label): encoded_text, label = tf.py_function( my_encoding, # python function to execute inp=[text, label], # expected inputs to the function Tout=(tf.int64, label.dtype) # expected output types ) print("Encoded Text Shape:", encoded_text.shape) print("Label Shape:", label.shape) encoded_text.set_shape([None]) label.set_shape(label, []) return encoded_text, label Application: encoded_ds_test = ds_test.map(tf_my_encoding) encoded_ds_test = ds_test.padded_batch(32, padded_shapes=([None], [])) Error: ValueError: The padded shape (None,) is not compatible with the shape () of the corresponding input component.

Why did you put 1 in unsqueeze targets ?

Nice!

THANK YOUUUUUUU

Thanks a lot!

amazing playlist for beginners, thank you for that !

Hi Aladdin, where can we find the code of this tutorial? I checked the link to the github you mentioned, but wasn't able to find it.

Did you do the hands on?

Thank you so much for your great content! I was wondering if the loader in the video is the train_loader? do you also apply oversampling on dev_train and test dataloader?

Hi Aladdin, im new to Yolo and it is until now that i found your channel. I wanna ask why nothing happened after I run the train file, it started then it finished but no picture showed up. Hope you can reply bro.

Why in games voltage has different than msi?

are you the son of notch (markus persson)?

you are very good thanks

why the recall value 1/4

not a single confusion in this video, thanks

How to tweak the model if we have more than 3 channels?

you are awesome. thank you for this immensely valuable resource!!

Great STUFF! Thanks Aladdin. However, when I try to replicate this tutorial, I get errors as follows: Traceback (most recent call last): File "C:\Users\USER\CODE\PycharmProjects\pythonProject2Conda\main.py", line 94, in <module> model.fit(train_dataset, epochs=5, verbose=2) File "C:\Users\USER\anaconda3\envs\tf_cpu\Lib\site-packages\keras\src\utils\traceback_utils.py", line 123, in error_handler raise e.with_traceback(filtered_tb) from None File "C:\Users\USER\anaconda3\envs\tf_cpu\Lib\site-packages\tensorflow\python\eager\execute.py", line 53, in quick_execute tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ tensorflow.python.framework.errors_impl.NotFoundError: Graph execution error: Detected at node ReadFile defined at (most recent call last): <stack traces unavailable> NewRandomAccessFile failed to Create/Open: C:\Users\USER\CODE\PycharmProjects\pythonProject2Conda/train_images/129_97.png : The system cannot find the file specified. ; No such file or directory [[{{node ReadFile}}]] [[IteratorGetNext]] [Op:__inference_one_step_on_iterator_2745] ANY HELP??

Let's build a recSys step by step.

can you show us how to inference with this model. you did not show the code

Perfect explanation. I was looking for a video just like this one. You're a lifesaver Aladdin

Can we use PEFT or LORA with Pytorch Lightning ?

Can we use PEFT or LORA with Pytorch Lightning ?

Can we use PEFT or LORA with Pytorch Lightning ?

What an amount of work! I don't often see people in the internet that are so dedicated to deep learning!

Looking forward to more videos about RecSys!

which IDE do u use?