We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1
Assignment - 2
Due Date: Tuesday, Mar 5, 2024
Weightage: 10%
1. Create a constant tensor with value 7 in Tensorflow.
2. Assume two square tensors of shape [3,3]. Write a tensorflow operation that adds the two tensors. 3. Using the Keras API in tensorflow on the cats_vs_dogs dataset, construct a simple neural network model for binary classification. Compile it, and plot the validation loss for 10 epochs. (2) 4. Create a custom metric in Keras that calculates the F1 score for the previous cats_vs_dogs binary classification problem. (2) 5. Implement an image classification model using transfer learning with a pre-trained model (e.g., MobileNetV2) on the CIFAR-10 dataset. Fine-tune the model on a subset of the CIFAR-10 dataset. Save the model also. (2) 6. Explain the concept of TensorFlow Lite and the motivation behind converting models into the Lite version. 7. Convert the model trained on CIFAR-10 dataset into its tensorflow lite version.