Create layers | Computer Vision with Keras p.1
Vložit
- čas přidán 13. 09. 2024
- You can Build Computer Vision software to DETECT and TRACK any Object.
→ 4-Step FREE Workshop pysource.com/b...
In this lesson, we will learn today how to prepare the image to be process by the neural networks, and how to build a very simple model creating layers.
If you've no idea what a neural network is, how the image is loaded, what layers are.. this is the best video for you to start learning it.
Blog: pysource.com/2...
➤ Courses:
Full Computer Vision course: pysource.com/o...
Training Mask R-CNN PRO (Notebook + Mini-Course): pysource.com/m...
Blueprint: pysource.com/b...
➤ Follow me on:
LinkedIn: / pysource
➤ For business inquiries:
pysource.com/c...
#keraslayers #computervision #tensorflow
good
I'm from Vietnam, I really like the way you describe the whole detail of the topic,. Thank you so much and I'm waiting for your wonderful lecture!
Thanks, new lessons will be coming soon
Really impressed with your awesome didatics. Thank you very much and looking forward for the next class. Regards from Brazil!
I'm glad to hear that :)
keep going dude ,quality content quality channel :)
Hello thank you for the videos.
Please could you give me some hints to resolve this problem:
I am trying to classify 3 classes of skins lesions with keras using transfer learning and ResNet50.
But my model only predicts one classe whatever change I do in the test dataset.
It could be for a lot of different reasons:
- Poor dataset (not many images, not enough augmentation, wrong model for that specific task)
- The code is not properly loading the images for the right class, and they get mixed up
- there is some error on the layer output (so it doesn't give the right result)
I recomment testing the code with other datasets, to see if it's a problem of the code or of the dataset, before proceeding
@@pysource-com Thank you for the reply.