Home › Forums › Assignment NPTEL_ › Practical Machine learning with tensor flow › Practical Machine Learning with Tensorflow – Assignment 5
Tagged: Machine Learning, NPTEL, Practical Machine Learning with Tensorflow, Tensorflow, Unit 6  Week 5
 This topic has 0 replies, 1 voice, and was last updated 1 year, 2 months ago by Abhishek Tyagi.

AuthorPosts


April 19, 2020 at 10:10 am #375Abhishek TyagiKeymaster
1) Your first task is to perform image classification using convolutional neural networks on the CIFAR10 dataset. Please visit this notebook for answering the questions 1 to 5. You are advised to run the notebook with GPU as the hardware accelerator. You can change this setting in the Edit > Notebook settings. Build a convolutional neural network with the architecture mentioned in the notebook and train the model for 10 epochs. What is the range of test accuracy of the model?
Answer 6570
2) Remove the max pooling layers from the above architecture and retrain the model for 10 epochs. Does the test accuracy get better or worse?
Answer Worse
3) After removing the pooling layer in the architecture of the model, how did the number of parameters of the model change? Try and think of why this happened.
Answer None of the above (Reduced by 1128448 / 94496 or increased by 1127448 / 94496)
4) We have now trained a convolutional neural network. But let us check if we intuitively understand how filters work. What does the following filter do?
Filter = [[1/9, 1/9, 1/9], [1/9, 1/9, 1/9], [1/9, 1/9, 1/9]]Answer Blur the Image
5) Your second task is to perform flower classification using transfer learning taught this week. There are two parts: (1) pretrained base mode
(2) Finetuning the model. Please visit <b> this </b>notebook for answering the following questions. You need to understand the code and try to fill up the empty cells in the notebook.
What is the shape of one batch of image_data?Answer [30, 160, 160, 3]
6) What is the shape of a new block of features converted by the feature extractor for each image?
Answer [5, 5, 512]
7) What is the total number of trainable <i>TF</i> variables in the model (part1)?
Answer 2
8) What is the total number of trainable parameters in this model (part1)? Select the order of it:
Answer 1000
9) What is the total number trainable <i> TF</i> variables in the model (part2)?
Answer 4
10) What is the total number of trainable parameters in this mode (part2)? Select the order of it:
Answer 1000000
11) Let the validation accuracy in part1 be <i><b>x</b></i> and validation accuracy in part2 be y (both after training is done) . The value yx lies between?
Answer 0.0 to 0.1
 This topic was modified 1 year, 2 months ago by Abhishek Tyagi.
 This topic was modified 1 year, 2 months ago by Abhishek Tyagi.


AuthorPosts
 You must be logged in to reply to this topic.