deep learning
guangjinzheng
这个作者很懒,什么都没留下…
展开
-
coco json to txt
import jsonfrom collections import defaultdictname_box_id = defaultdict(list)id_name = dict()f = open("D:/deeplearning/datasets/coco/annotations/instances_train2017.json", encoding='utf-8')data = json.load(f)annotations = data['annotations']for a.原创 2020-10-02 17:22:56 · 368 阅读 · 0 评论 -
image classification fashion mnist
import tensorflow as tfimport matplotlib.pyplot as pltfrom matplotlib.pyplot import MultipleLocator# tensorflow==2.1.0# 载入并准备好 MNIST 数据集。将样本从整数转换为浮点数:(x_train, y_train), (x_test, y_test) = tf.keras.datasets.fashion_mnist.load_data()x_train, x_test .原创 2020-09-27 20:25:35 · 224 阅读 · 0 评论 -
image classification dogs and cats cnn
import tensorflow as tffrom keras.preprocessing.image import ImageDataGeneratorimport matplotlib.pyplot as pltfrom matplotlib.pyplot import MultipleLocatorpath = 'D:/deeplearning/datasets/dogsandcats/'batchsizes = 32epochs = 15# read datatrain_d.原创 2020-09-26 20:52:17 · 230 阅读 · 0 评论 -
image classification cifar10 CNN
import tensorflow as tffrom tensorflow.keras import datasets, layers, modelsimport matplotlib.pyplot as plt(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()# Normalize pixel values to be between 0 and 1train_ima.原创 2020-09-26 17:18:52 · 222 阅读 · 0 评论 -
tensorflow hello world mnist
from __future__ import absolute_import, division, print_function, unicode_literals import tensorflow as tfmnist = tf.keras.datasets.mnist(x_train, y_train), (x_test, y_test) = mnist.load_data()x_train, x_test = x_train / 255.0, x_test / 255.0model.原创 2020-09-26 16:58:36 · 187 阅读 · 1 评论 -
test tensorflow GPU
import tensorflow as tfprint('GPU', tf.test.is_gpu_available())a = tf.constant(2.)b = tf.constant(4.)print(a * b)# 2020-07-07 guangjinzheng # test GPU GPU True原创 2020-09-26 16:56:15 · 163 阅读 · 0 评论 -
computer configuration
本文实验在 64 位 Windows10 操作系统环境下进行,软件方面采用基于 tensorflow 和 Anaconda 以及 python 的开发环境 pycharm,硬件基于Intel(R) Core(TM) i7-10700K CPU @ 3.8GHz CPU,16GB RAM,NVIDIA GeForce RTX 2080 SUPER GPU ,CUDA10.0下进行。OS: window 10 professionCPU:Intel(R) Core(TM) i7-10700K...原创 2020-09-26 11:19:32 · 636 阅读 · 0 评论 -
image classification inception v3 CNN
本文实验在 64 位 Windows10 操作系统环境下进行,软件方面采用基于 tensorflow 和 Anaconda 以及 python 的开发环境 pycharm,硬件基于Intel(R) Core(TM) i7-10700K CPU @ 3.8GHz CPU,16GB RAM,NVIDIA GeForce RTX 2080 SUPER GPU ,CUDA10.0下进行。tensorflow==2.1.0tensorflow-gpu==2.1.0opencv-pythonm...原创 2020-09-26 11:07:12 · 257 阅读 · 0 评论 -
image classification three layers CNN
tensorflow==2.1.0tensorflow-gpu==2.1.0opencv-pythonmatplotlib# 导入模块import globimport osimport cv2import tensorflow as tffrom tensorflow.keras import layers, optimizers, datasets, Sequentialimport numpy as npimport matplotlib.pyplot as pl.原创 2020-09-26 10:55:49 · 138 阅读 · 0 评论 -
show training history data
import matplotlib.pyplot as pltfrom matplotlib.pyplot import MultipleLocatorimport csv# 图可视化def pltshow(loss,val_loss,accuracy,val_accuracy): epochs = len(loss) epochs_range = range(epochs) plt.figure(figsize=(8,8)) plt.subplot(1,2,1.原创 2020-09-25 17:20:34 · 233 阅读 · 0 评论 -
read pictures cv2
import osimport globimport cv2import numpy as npfrom sklearn.model_selection import train_test_splitpath = 'D:/deeplearning/datasets/flower_photos/'w, h, d = 100, 100, 3classtotal = 0classnum = []def read_img(path): pathones = [] for i .原创 2020-09-25 17:16:20 · 250 阅读 · 0 评论