mnist

I am currently training a CNN on MNIST, and the output probabilities (softmax) are giving [0.1,0.1,...,0.1] as training goes on. The initial values aren't uniform, so I can't figure out if I'm doing something stupid here? I'm only training for 15 steps, just to see how training progresses; even though that's a low number, I don't think that should result in uniform predictions? import numpy as np import tensorflow as tf import imageio from sklearn.datasets import fetch_mldata mnist = fetch_mldata('MNIST original') # Getting data from sklearn.model_selection import train_test_split def one_hot

I'm a bit new to the whole field and thus decided to work on the MNIST dataset. I pretty much adapted the whole code from https://github.com/pytorch/examples/blob/master/mnist/main.py , with only one significant change: Data Loading. I didn't want to use the pre-loaded dataset within Torchvision. So I used MNIST in CSV . I loaded the data from CSV file by inheriting from Dataset and making a new dataloader. Here's the relevant code: mean = 33.318421449829934 sd = 78.56749081851163 # mean = 0.1307 # sd = 0.3081 import numpy as np from torch.utils.data import Dataset, DataLoader class dataset

第一个CNN代码，暂时对于CNN的BP还不熟悉。但是通过这个代码对于tensorflow的运行机制有了初步的理解 1 ''' 2 softmax classifier for mnist 3 4 created on 2019.9.28 5 author: vince 6 ''' 7 import math 8 import logging 9 import numpy 10 import random 11 import matplotlib.pyplot as plt 12 import tensorflow as tf 13 from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets 14 from sklearn.metrics import accuracy_score 15 16 def weight_bais_variable(shape): 17 init = tf.random.truncated_normal(shape = shape, stddev = 0.01); 18 return tf.Variable(init); 19 20 def bais_variable(shape): 21 init = tf.constant(0.1, shape

from tensorboardX import SummaryWriter import torchvision writer=SummaryWriter(log_dir="embedding") mnist=torchvision.datasets.MNIST("mnist",download=True) writer.add_embedding( mat=mnist.train_data.reshape((-1,28*28))[:100,:], metadata=mnist.train_labelS[:100], label_img=mnist.train_data[:100,:,:].reshape((-1,1,28,28)).float()/255, global_step=0 ) 　　 add_embedding (mat , metadata = None , label_img = None , global_step = None , tag = 'default' , metadata_header = None ) mat (torch.Tensor or numpy.array): 一个矩阵，每行代表特征空间的一个数据点 metadata (list or torch.Tensor or numpy.array, optional): 一个一维列表，mat

import tensorflow as tf import matplotlib.pyplot as plt import numpy as np datapath = r'D:\data\ml\mnist.npz' (x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data(datapath) x_train = tf.keras.utils.normalize(x_train, axis=1) x_test = tf.keras.utils.normalize(x_test, axis=1) model = tf.keras.models.Sequential() model.add(tf.keras.layers.Flatten()) model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu)) model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu)) model.add(tf.keras.layers.Dense(10, activation=tf.nn.softmax)) model.compile(optimizer='adam', loss='sparse

主要内容： 一、TensorBoard应用进阶 1.1图像的显示 在构建模型的输入层时，定义了占位符x，placeholder就是接收训练样本的图像数据。为了把这些图像在TensorBoard中显示出来，需要把它加入summary中去。 通过tf.summary.image()函数，把带进来的图像信息加到summary中去。它的第一个参数是标识ID；第二个参数是图像的数据；第三个参数为10，表示最多显示10张图片。 image_shaped_input要求的形是一个四维的模式，后面三个参数分别表示图像的长、宽以及颜色的通道数（灰度图为1），第一个参数表示一次有多少行数据，-1表示暂时不确定，会根据带进来所有数据的总数来计算。 1.2张量的显示 在TensorBoard中以直方图的形式显示在计算中一些tensor的情况 可以通过tf.summary.histogram()函数。它的第一个参数也是标识ID，第二个参数是要显示的tensor值。 1.3标量的显示 当我们定义好loss_function以后，就可以通过tf.summary.scalar()函数，把loss值以标量的形式显示出来。 我们还可以把准确率也以标量的形式显示出来。 1.4训练模型的显示 在训练模型的过程中，需要把前面所有定义的summary操作合并。 这里定义了一个merged_summary_op，直接调用tf

首先进行数据预处理，需要生成.tsv、.jpg文件 import matplotlib.pyplot as plt import numpy as np import os from tensorflow.examples.tutorials.mnist import input_data LOG_DIR = 'log' SPRITE_FILE = 'mnist_sprite.jpg' META_FIEL = "mnist_meta.tsv" # 存储索引和标签 def create_sprite_image(images): if isinstance(images, list): images = np.array(images) img_h = images.shape[1] img_w = images.shape[2] n_plots = int(np.ceil(np.sqrt(images.shape[0]))) spriteimage = np.ones((img_h * n_plots, img_w * n_plots)) for i in range(n_plots): for j in range(n_plots): this_filter = i * n_plots + j if this_filter < images.shape[0]: # 个数 this

中文文档 TensorFlow 2 / 2.0 中文文档 知乎专栏 欢迎关注知乎专栏 https://zhuanlan.zhihu.com/geektutu 一、实战教程之强化学习 TensorFlow 2.0 (九) - 强化学习 70行代码实战 Policy Gradient TensorFlow 2.0 (八) - 强化学习 DQN 玩转 gym Mountain Car TensorFlow 2.0 (七) - 强化学习 Q-Learning 玩转 OpenAI gym TensorFlow 2.0 (六) - 监督学习玩转 OpenAI gym game 二、实战教程之图像识别 TensorFlow 2.0 (五) - mnist手写数字识别(CNN卷积神经网络) TensorFlow入门(四) - mnist手写数字识别(制作h5py训练集) TensorFlow入门(三) - mnist手写数字识别(可视化训练) TensorFlow入门(二) - mnist手写数字识别(模型保存加载) TensorFlow入门(一) - mnist手写数字识别(网络搭建) 三、Github 源码地址 Github - TensorFlow 2.0 Tutorial Github - TensorFlow 2 / 2.0 中文文档 中文文档 TensorFlow 2 / 2.0