如何解决重塑数据集以正确大小
我正在尝试学习tensorflow,并尝试从sklearn导入手写数据集,但出现以下错误:
ValueError: Input 0 of layer conv2d is incompatible with the layer: : expected min_ndim=4,found ndim=3. Full shape received: [None,1797,64]
我的代码:
X,y = load_digits(return_X_y=True)
X = X/255.0
model = Sequential()
model.add(Conv2D(64,(3,3),input_shape=X.shape))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2,2)))
什么是正确的形状?
解决方法
Conv2D
层需要以下形状的输入:(num_examples,height,width,channels)
。您正在寻找Conv1D
图层,因为您输入的形状(根据错误)的形状为(num_examples,width)
。
load_digits
返回一个展平的数组,因此您需要将其重塑为8x8并取消挤压。
import tensorflow as tf
from sklearn import datasets
from tensorflow.keras.layers import *
X,y = datasets.load_digits(return_X_y=True)
X = X/255.0
X = X.reshape(-1,8,1)
model = tf.keras.Sequential()
model.add(Conv2D(64,(3,3),input_shape=X.shape[1:]))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2,2)))
model.build(input_shape=(8,1))
model(X)
<tf.Tensor: shape=(1797,3,64),dtype=float32,numpy=
array([[[[0.00000000e+00,0.00000000e+00,1.79972278e-03,...,3.92661383e-03,2.93043372e-03],[3.34757613e-03,4.03874973e-03,0.00000000e+00],[5.52046159e-03,1.12290974e-04,0.00000000e+00]]]]
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。