285 - Object detection using Mask RCNN (with XML annotated data)

Code generated in the video can be downloaded from here:
github.com/bns...
This video helps you get started with your first Mask RCNN project that uses existing annotated data. Annotated data used in this video can be downloaded from:
www.kaggle.com...
XML data in PascalVOC format
XML annotation file for each image
Please note that this video assumes you have installed Mask RCNN on your system. For installation instructions, please watch the previous video (Video numbered 284).
coco weights can be downloaded from: github.com/mat...

[@infosection]

First of all very thankful sir, your videos deserve more than millions of likes, sir, I'm working on segmentation, I have dataset images labeled with XML files, and my data set is about roads, I'm confused about using a U-NET model with this dataset. waiting for your kind response. Thanks

[@harastring]

Thanks for the video! Always exciting XD

[@weavers-construction-solutions]

Thank you for all your efforts

[@DigitalSreeni]

My pleasure!

[@jackharper6540]

I keep getting an error where it says
NotImplementedError: Exception encountered when calling Lambda.call().
We could not automatically infer the shape of the Lambda's output. Please specify the `output_shape` argument for this Lambda layer.
Do you know why I am getting this problem?

[@deepov]

Спасибо!

[@DigitalSreeni]

Thank you very much.

[@PiyushASupe]

Would like to request MaskRCNN like series for mobilenetSSD, with Raspi deployment.

[@MatheusHenrique-jz1dc]

Very good !!

[@noureddineelharyky1619]

thank you sir it works

[@junaidmalik7140]

Can u tell me what version used for tensirflow and keras , I'm having an error " No Module name Keras.engine"

[@technews16]

How to convert zip to egg folder

[@estebanmeza9645]

can you use annotations made with labelimg?

[@lennard4454]

How would I add custom transformations?
Like this with detecto:
custom_transforms = transforms.Compose([
transforms.ToPILImage(),
transforms.Resize(800),
transforms.ColorJitter(saturation=0.3),
transforms.ToTensor(),
utils.normalize_transform(),
])
dataset = core.Dataset('train_labels.csv', 'images/',
transform=custom_transforms)

[@ayxanxasmmmdov1438]

Hi, when i train model, it returns nan value. How do i solve this problem?

[@fredbaafi9013]

Thank you sir, your videos are really helpful, but my question is how do you assign the class when doing object detection on number plates, is it 2. That's 1 for car and 2 for number plate. Please i need help understanding it. Thank you

[@dantec.dagandanan3732]

Thanks sir

[@mayaltaee2963]

Thanks sir, I hope you can make videos of Faster R-CNN for objects detection.

[@DigitalSreeni]

I do not intend to make Faster R-CNN videos as it has been replaced by Mask R-CNN as the state of the art for object detection. Of course, it would be nice to learn about Faster R-CNN for educational purposes but I think the time is better utilized when spent on other techniques that are not obsolete.

[@mayaltaee2963]

@@DigitalSreeni Thank you for the quick answer. I am a doctoral student and my thesis on Faster R-CNN. I would like more information about the topic, especially since I watched different videos of you, and they were very clear and understandable.
regards,

[@abcreation8371]

1st view 1st comment 😎😎

[@yasirali8409]

Ooo

[@DigitalSreeni]

🎉

[@lennard4454]

Is it possible NOT to detect something? Usually we only train with images where there is at least on object it should detect... however I noticed that the network detects objects with high confidence in completely different testing images although it is not supposed to.

[@masamatovic5025]

Can we use Ipad for picture labeling in APEER.. Thanks for the answer.. :)

[@DigitalSreeni]

Yes, that’s what I do.

[@mujeebpa]

Can't find the code in GitHub Repo.

[@DigitalSreeni]

Will be uploaded soon, thanks for the patience.

[@MrBisht-yt1ou]

is your playlist is enough for ML and DL for beginner to intermediate level ?
what should I expect from this playlist ? Is the playlist still relevant today?

[@DigitalSreeni]

The playlist is highly relevant for beginners to intermediate level coders. My latter videos (recent ones) tend to focus heavily on image analysis so they will not be relevant for those seeking to learn non-image based analysis (e.g., financial analysis, NLP, audio processing, etc.)

[@yoyomcg]

do one on pytorch :)

[@Vu-Nguyen]

Hi, if i train 50 epoch first with coco weights , them can i replace coco weights with my last 50 epoch weights to train next 50 more epoch ? Or should i train straight 100 epoch? Or can i do to train with my last 50 epoch?

[@alibouhejba7336]

Hii , please do you have the solution for this problem?

[@sameerjasra]

Great explanation as usual. At your convenience can we have videos on Transformers. Thanks

[@Programlama101]

How can we see train/test results? I've found very useful to your videos but you are testing them with only single photo.

[@TruDeinoz]

21:40 I have the same issue. Weights were saved in a different location in a folder called logdir. How can I fix this?

[@CRTagadiya]

Is Object detection series in on way? just like Image segmentation

[@ashwiniyadav464]

Sir can you suggest any mask for selecting particular pixel in an image

[@JoseOliveira-lz1up]

your channel is really good!