Using the beans dataset, Build a CNN network to perform image classification using TensorFlow. Does it overfit or underfit the data? Please justify your answer. To import the Beans dataset ; import tensorflow_datasets as tfds (bn_train, bn_validation, bn_test),bn_info = tfds.load( name = 'beans', split = ['train', 'validation', 'test'], as_supervised = True, with_info = True) print(bn_info)

For the code in the attached image: 1. Suppose sizeof(struct student) is 16 (decimal) and the start address of arr is 0xfff0b202.What is &arr[2][8]? Why?

I would like to represent the "residuals" part of the code (see below) as a surface (meshplot), in essence a 3D plot of 2D data # Import librariesimport matplotlib.pyplot as pltimport globfrom astropy.io import fitsfrom astropy.wcs import WCSimport numpy as npimport seaborn as sns # Initial plotfig, ax = plt.subplots(figsize=(7, 7)) # Data from the FITSdata_dir = glob.glob('/Users/petrderuyter/Desktop/harpn_sun_release_package_ccf_2018/2018-04-02/*.fits') #'/Users/xxxxxxxxxxxx/Desktop/harpn_sun_release_package_ccf_2018/2018-01-18/*.fits' # Empty lists for storagelams = []fluxs = [] # Read the FITS files and extract datafor file_path in data_dir:    hdul = fits.open(file_path)    data = hdul[1].data    h1 = hdul[1].header    flux = data[1]    w = WCS(h1, naxis=1, relax=False, fix=False)    lam = w.wcs_pix2world(np.arange(len(flux)), 0)[0]    lams.append(lam)    fluxs.append(flux)    ax.plot(lam, flux) # Calculate mean fluxmean_ccf = np.mean(fluxs, axis=0) # New figure for the mean…

Assign letter grades O solutions submitted (max: 1) In the attached spreadsheet, you are given homework grades of 25 students. Sheet 1 (hw1) stores the first homework grades, Sheet 2 (hw2) is the second homework grades and so on. Use either xlsread() or readmatrix() to import the given data into Matlab. Once you have the data in Matlab; 1- Create separate arrays for each homework, name them as hw1, hw2, hw3, hw4, hw5 2- Create an average grade array named hwAvg. Store the average homework grade in hwAvg using the below weights Homework 1, 2: each 15% Homework 3, 4 : 20% Homework 5: 30% 3- Create an array named letterGrade to store letter grades, this will be an array of strings. • 4- Preallocate the letterGrade array. Make sure it has the same length as hwAvg array. 5- Assign letter grades from hwAvg array using the grading policy shown below 100 - 90 : A <90 - 80 : B <80 - 70:C <70 - 60 : D <60 :F It is recommended that you download the file, see what it looks like, figure the steps…