Видео

Can you give me your github?

it's not giving me any good result.

how can i train this swin with mu own data?

can we take another image on which we will apply the same. if yes tell me how

thanks for the tutorial, but i got wrong prediction, i think 5 epoch not enough.

I'm getting this error ValueError: Expected x_max for bbox (0.6930555555555555, 0.4097222222222222, 1.000522222222222, 0.7804180555555557, 2) to be in the range [0.0, 1.0], got 1.000522222222222. Pls help

how to generate image after training?

What if I only have Train and Test dataset?

Damn, just what i needed thanks brother😂

wow great work! you made my day! keep up the great work.

How can we make higher resolution output?

Hi could you please help ? it shows this message : n("FP16 is not supported on CPU; using FP32 instead

Thank you for your tutorial but I get some problem about *plt.imshow(bounding_boxes_img.permute(1, 2, 0))* command. My kernel is restarting with error: *The kernel appears to have died. It will restart automatically.* How can I fix it?

next video?

mt bom

is it a CNN modle

Has any of you guys had problems with overfitting? My dataset is 224 X 224 X 3, with 53 classes. There are 7624 training images, 265 test images and 265 validation images I did not perform augumentation before training, just normalizing and transforming to tensor, maybe it could be the case? In first epochs my val accuracy is like 0.01 but train acc is fine. What could possibly go wrong?

The !wget line doesn't work and results in 404 not found. Is it outdated? also in get_data_loaders function, the transform=transform causes an error.

it is error in step 11 NameError: name 'inp_batch' is not defined How fix it?

Can I use Swin IR for Superresolution and Later on Use this images For Skin disease classification Can It give more accurate results or not.

Only a few changes provided by chatgtp and Works perfect, realy thank you very much.

make another video where we can load our own model instead resnet 18

Hey, can we get link to the notebook !

Thanks for the turorial! I am curious about why does[ len(target) == 64] at 3:32 in the video

can you save the Faster RCNN trained model and used it later on on detection?

How to see the accuracy of this model

I am sorry but where is the part committed to the GPU implementation?

You should make a video on how to train it

Im getting this error when i used the same code and dataset from your video ValueError: Expected x_max for bbox (0.1953125, 0.128125, 1.0007171874999998, 0.9323515625000001, 6) to be in the range [0.0, 1.0], got 1.0007171874999998.

is it possible to use a custom dataset ?

no module named timm how to fix this?

where is the code for this

Would love to see part 2:)

What does the images and target should look like (in the line "images, target = next(iter(data_loader)")? I have tried to work with different input and there is an error at this line.

Thanks for the tutorial. I would like to have precision, recall and MAP.5 during the training

why did you create those specific layers on the head of the model?

Nice starting code, are you planning to post the other videos soon?

Man how can I contact you?

What's the name of the program you use in the video?

Sir, it threw me error _, _, h_old, w_old = img_lq.size() TypeError Traceback (most recent call last) <ipython-input-60-7d4efbfac0ee> in <module> 2 SCALE = 2 3 with torch.no_grad(): ----> 4 _, _, h_old, w_old = img_lq.size() 5 h_pad = (h_old // window_size + 1) * window_size - h_old 6 w_pad = (w_old // window_size + 1) * window_size - w_old TypeError: 'int' object is not callable

☀️ promo sm!!

Can anyone help me as how can I use validation set in this code ?

one thing to note is that what you programmed was actually image classification and not detection where it will be used in training so please change the name to classification otherwise your coding was spot on and would need some improvements and good vid.

how can i apply my dataset to this code ?

Thank you very much, you helped me a lot

Only 5% of my viewers are subscribed, if you aren't subscribed, please like and subscribe so that I can continue to make content.

How can I run inference on webcam using faster rcnn pytorch? Thank you in advance

𝓟Ř𝔬𝓂𝔬𝐒ϻ 🏃

plt.imshow(img) -------------------------------------------------------------------------- NameError Traceback (most recent call last) <ipython-input-14-23af6c37b3d0> in <module> ----> 1 plt.imshow(img) NameError: name 'img' is not defined

Hello. Thank you for the wonderful video. I would like to see the code for displaying the learning curve and validation curve, is it possible?