def predict_ch3(model, t_i, n=6): # @save for X, y in t_i: break trues = d2l.get_fashion_mnist_labels(y) preds = d2l.get_fashion_mnist_labels(model(X).argmax(axis=1)) titles = [true + '\n' + pred for true, pred in zip(trues, preds)] d2l.show_images(X[0:n].reshape(n, 28, 28), 1, n, titles=titles[0:n]) plt.show()
def show_samples(): image, label = mnist_train[2] print(image.shape, label, type(image)) print(label, type(label), label.dtype) images, labels = mnist_train[0:4:1] print(images.shape, labels.shape) d2l.show_images(images, 2, 9) plt.show()
def train_model(images, labels): l_c = label_counts(labels) # label probabilities P_y = l_c / l_c.sum() for label, probability in enumerate(P_y): print('label {} : {}'.format(label, probability)) print('Samples', nd.size_array(images)) P_xy = label_pixel_probabilities(images, labels, l_c) # test the prediction image, label = mnist_test[1] predict_one(image, label, P_y, P_xy) X, y = mnist_test[:18] d2l.show_images(X, 2, 9, titles=predict(X, P_y, P_xy)) plt.show() ac = accuracy(P_y, P_xy) print('accuracy : {}'.format(ac))
import os import cv2 from mxnet import gluon, image, nd from mxnet.gluon import data as gdata, utils as gutils import d2l import numpy as np import tensorflow as tf import sklearn import mxnet voc_dir = "C:\\Users\\bhatt\\Desktop\\Jupyter Notebook\\VOCdevkit\\VOC2012" def read_voc_images(root=voc_dir, is_train=True): txt_fname = '%s/ImageSets/Segmentation/%s' % (root, 'train.txt' if is_train else 'val.txt') with open(txt_fname, 'r') as f: images = f.read().split() features, labels = [None] * len(images), [None] * len(images) for i, fname in enumerate(images): features[i] = image.imread('%s/JPEGImages/%s.jpg' % (root, fname)) labels[i] = image.imread('%s/SegmentationClass/%s.png' % (root, fname)) return features, labels train_features, train_labels = read_voc_images() n = 5 imgs = train_features[0:n] + train_labels[0:n] d2l.show_images(imgs, 2, n)