他的首页
他的馆藏
他的动态
馆友反馈
关于他
| 共 223 篇文章 |
|
Dense(units, name="dense_1") self.dense_2 = keras.layers.variables: [''nested/dense_1/kernel:0'', ''nested/dense_1/bias:0'', ''nested/dense_2/kernel:0'', ''nested/dense_2/bias:0'']Changing trainable status of one of the nested layers...varia... 阅3 转0 评0 公众公开 24-04-02 20:57 |
tensorflow中 tf.reduce_mean函数。tf.reduce_mean 函数用于计算张量tensor沿着指定的数轴（tensor的某一维度）上的的平均值，主要用作降维或者计算tensor（图像）的平均值。import tensorflow as tfx = [[1,2,3],[1,2,3]]xx = tf.cast(x,tf.float32)mean_all = tf.reduce_mean(xx, keep_dims=False)mean_0 = tf.reduce_mean(xx, axis=0, keep_... 阅1 转0 评0 公众公开 24-03-25 15:22 |
本文将介绍一个简单技巧来在Keras中构建自定义loss函数，它可以接收除 y_true 和 y_pred 之外的参数。import keras.backend as Kdef mean_pred(y_true, y_pred):return K.mean(y_pred)model.compile(optimizer=''rmsprop'', loss=''binary_crossentropy'', metrics=[''accuracy'', mean_pre... 阅1 转0 评0 公众公开 24-03-19 15:59 |
# paddlepaddle codeself.p_conv = Conv2D(inc, 2*kernel_size*kernel_size, filter_size=3, padding=1, stride=stride)self.p_conv.weight = fluid.initializer.# paddlepaddle codeself.p_conv = Conv2D(inc, 2*kernel_size*kernel_size, filter_size=3, padding=1, stride=stride, param_attr=fluid.initializer. 阅21 转0 评0 公众公开 23-10-03 01:40 |
Pytorch-lightning入门实例Pytorch-lightning入门实例。import torchfrom torch.nn import functional as Ffrom torch import nnfrom pytorch_lightning.core.lightning import LightningModuleclass LitMNIST(LightningModule): def __init__(self):super().__init__()# mnist images are (1, 28, 28) (channels, width, height)self.layer_1... 阅107 转1 评0 公众公开 22-11-09 15:24 |
阅34 转0 评0 公众公开 22-10-05 15:12 |
tf weighted_cross_entropy_with_logitsweighted_cross_entropy_with_logits觉得有用的话,欢迎一起讨论相互学习~weighted_cross_entropy_with_logits(targets, logits, pos_weight, name=None): 阅4 转0 评0 公众公开 22-09-28 16:17 |
keras - binary_crossentropy和categorical_crossentropy的分析binary_crossentropy和categorical_crossentropy的分析。所以说多分类问题是要softmax激活函数配合分类交叉熵函数使用，而二分类问题要使用sigmoid激活函数配合二进制交叉熵函数适用，但是如果在多分类问题中使用了二进制交叉熵函数最后的模型分类效果会虚高，即比模型本身真实的... 阅17 转0 评0 公众公开 22-07-08 11:03 |
TensorFlow 深度学习损失函数tf.nn.softmax_cross_entropy_with_logits.Session() as sess:softmax=sess.run(y)c_e = sess.run(cross_entropy)c_e2 = sess.run(cross_entropy2)print("step1:softmax result=")print(softmax)print("step2:cross_entropy result=")print(c_e)print("Function(softmax_cross_entropy_wi... 阅36 转0 评0 公众公开 22-07-07 00:38 |
def addWeightByClassWeight():import numpy as npclass_weight = {0: 1.0,1: 1.0,2: 1.0,3: 1.0,4: 1.0,# Set weight "2" for class "5",# making this class 2x more important5: 2.0,6: 1.0,7: 1.0,8: 1.0,9: 1.0,}print("Fit with class weight")model = get_compiled_model()model.fit(x_train, y_train, c... 阅62 转0 评0 公众公开 22-06-30 07:19 |
