:)

TensorFlowBasic Optimization with GradientTapeimport h5pyimport numpy as npimport tensorflow as tfimport matplotlib.pyplot as pltfrom tensorflow.python.framework.ops import EagerTensorfrom tensorflow.python.ops.resource_variable_ops import ResourceVariableimport timetrain_dataset = h5py.File('train데이터 경로', "r")test_dataset = h5py.File('test데이터 경로', "r")x_train = tf.data.Dataset.from_tensor_slice..

OptimizationGradient Descentimport numpy as npimport matplotlib.pyplot as pltimport scipy.ioimport mathimport sklearnimport sklearn.datasetsfrom opt_utils_v1a import load_params_and_grads, initialize_parameters, forward_propagation, backward_propagationfrom opt_utils_v1a import compute_cost, predict, predict_dec, plot_decision_boundary, load_datasetfrom copy import deepcopyfrom testCases import ..

Gradient CheckingPackagesimport numpy as npfrom testCases import *from public_tests import *from gc_utils import sigmoid, relu, dictionary_to_vector, vector_to_dictionary, gradients_to_vector%load_ext autoreload%autoreload 2  Dimensional Gradient Checkingforward propagationdef forward_propagation(x, theta): J = theta * x return Jx, theta = 2, 4J = forward_propagation(x, theta)print ("J..

RegularizationPackages# import packagesimport numpy as npimport matplotlib.pyplot as pltimport sklearnimport sklearn.datasetsimport scipy.iofrom reg_utils import sigmoid, relu, plot_decision_boundary, initialize_parameters, load_2D_dataset, predict_decfrom reg_utils import compute_cost, predict, forward_propagation, backward_propagation, update_parametersfrom testCases import *from public_tests ..

Initialization Packagesimport numpy as npimport matplotlib.pyplot as pltimport sklearnimport sklearn.datasetsfrom public_tests import *from init_utils import sigmoid, relu, compute_loss, forward_propagation, backward_propagationfrom init_utils import update_parameters, predict, load_dataset, plot_decision_boundary, predict_dec%matplotlib inlineplt.rcParams['figure.figsize'] = (7.0, 4.0) # set de..

Deep Neural Network for Image Classification: Applicationimport timeimport numpy as npimport h5pyimport matplotlib.pyplot as pltimport scipyfrom PIL import Imagefrom scipy import ndimagefrom dnn_app_utils_v3 import *from public_tests import *%matplotlib inlineplt.rcParams['figure.figsize'] = (5.0, 4.0) # set default size of plotsplt.rcParams['image.interpolation'] = 'nearest'plt.rcParams['image...

Building Deep Neural Network● Initialization○ 2-Layer Neural Networkdef initialize_parameters(n_x, n_h, n_y): np.random.seed(1) W1 = np.random.randn(n_h, n_x) * 0.01 b1 = np.zeros((n_h, 1)) W2 = np.random.randn(n_y, n_h) * 0.01 b2 = np.zeros((n_y, 1)) parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2} return..

Planar data classification with one hidden layerimport numpy as npimport copyimport matplotlib.pyplot as pltfrom testCases_v2 import *from public_tests import *import sklearnimport sklearn.datasetsimport sklearn.linear_modelfrom planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets%matplotlib inline%load_ext autoreload%autoreload 2# 데이터 불러오기X, Y = load_pla..

고양이를 인식하는 로지스틱 회귀 분류기import numpy as npimport copyimport matplotlib.pyplot as pltimport h5pyimport scipyfrom PIL import Imagefrom scipy import ndimagefrom lr_utils import load_datasetfrom public_tests import *%matplotlib inline%load_ext autoreload%autoreload 2 데이터 개요 및 전처리# Loading the data (cat/non-cat)train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset()# Example..