1 introduction in this assignment you will build on your knowledge of
In this assignment you will build on your knowledge of classification
image classification problem using a convolutional neural network.
This assignment aims to guide you through the processes by following the four fundamental princi-
in particular you will solve an
• Data: Data import, preprocessing, and augmentation.
• Model: Designing a convolutional neural network model for classifying the images of the parts.
• Fitting: Training the model using stochastic gradient descent.
• Validation: Checking the model's accuracy on the reserved test data set and investigating
where the most improvement could be found. Additionally, looking into the uncertainty in the
This is not necessarily a lincar process, after you have fit and/or validated your model, you may need
to go back to carlier steps and adjust your processing of the data or your model structure. This may
need to be done several times to achieve a satisfactory result.
This assignment is worth 35% of your course grade and is graded from 0 35 marks. An additional
two bonus marks are available to the student who's model performs best on a previously unseen data
*The amount will be in form of wallet points that you can redeem to pay upto 10% of the price for any assignment. **Use of solution provided by us for unfair practice like cheating will result in action from our end which may include permanent termination of the defaulter’s account.Disclaimer:The website contains certain images which are not owned by the company/ website. Such images are used for indicative purposes only and is a third-party content. All credits go to its rightful owner including its copyright owner. It is also clarified that the use of any photograph on the website including the use of any photograph of any educational institute/ university is not intended to suggest any association, relationship, or sponsorship whatsoever between the company and the said educational institute/ university. Any such use is for representative purposes only and all intellectual property rights belong to the respective owners.