![](https://img-blog.csdnimg.cn/20201014180756928.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
tensorflow
卑微小鹿
这个作者很懒,什么都没留下…
展开
-
基于VGG的猫狗识别
1、首先进行图像处理:import csvimport globimport osimport randomos.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'import tensorflow as tffrom tensorflow import kerasfrom tensorflow.keras import layersimport numpy as npgpus = tf.config.experimental.list_physical_原创 2022-03-19 21:13:27 · 2607 阅读 · 0 评论 -
yolo 思维大突破
1.yolo与其他神经网络的不同之处:YOLO将物体检测作为回归问题求解。基于一个单独的end-to-end网络,完成从原始图像的输入到物体位置和类别的输出。从网络设计上,YOLO与rcnn、fast rcnn及faster rcnn的区别如下:[1] YOLO训练和检测均是在一个单独网络中进行。YOLO没有显示地求取region proposal(下采样)(翻译为区域提案)的过程。而rcnn/fast rcnn 采用分离的模块(独立于网络之外的selective search方法)求取候选框(可.原创 2022-03-18 21:02:13 · 1559 阅读 · 0 评论 -
tensorflow中title和square
title的用法:import tensorflow as tfa = tf.constant([[1, 2], [3, 4], [5, 6]], dtype=tf.float32)a1 = tf.tile(a, [2, 3])with tf.Session() as sess: print(sess.run(a)) print(sess.run(tf.shape(a))) print(sess.run(a1)) print(sess.run(tf.shape(原创 2022-03-02 19:23:17 · 259 阅读 · 0 评论 -
tensorflow中lstm_layers实战
import osos.environ['TF_CPP_MIN_LOG_LEVEL']='2'import tensorflow as tfimport numpy as npfrom tensorflow import kerasfrom tensorflow.keras import layerstf.random.set_seed(22)np.random.seed(22) assert tf.__version__.startswith('2.')bat.原创 2022-02-14 16:00:51 · 479 阅读 · 1 评论 -
tensorflow中lstms_cell实战
import osos.environ['TF_CPP_MIN_LOG_LEVEL']='2'import tensorflow as tfimport numpy as npfrom tensorflow import kerasfrom tensorflow.keras import layerstf.random.set_seed(22)np.random.seed(22) assert tf.__version__.startswith('2.')ba..原创 2022-02-14 15:54:17 · 216 阅读 · 0 评论 -
tensorflow中的sentiment_analysis_layer
import osos.environ['TF_CPP_MIN_LOG_LEVEL']='2'import tensorflow as tfimport numpy as npfrom tensorflow import kerasfrom tensorflow.keras import layerstf.random.set_seed(22)np.random.seed(22)assert tf.__version__.startswith('2.')batchsz =128#.原创 2022-02-12 20:56:24 · 79 阅读 · 0 评论 -
tensorflow中sentiment_analysis_cell
import osos.environ['TF_CPP_MIN_LOG_LEVEL']='2'import tensorflow as tfimport numpy as npfrom tensorflow import kerasfrom tensorflow.keras import layerstf.random.set_seed(22)np.random.seed(22)assert tf.__version__.startswith('2.')batchsz =128#.原创 2022-02-12 20:25:05 · 770 阅读 · 0 评论 -
tensorflow中resnet_train实战
import osos.environ['TF_CPP_MIN_LOG_LEVEL']='2'import tensorflow as tffrom tensorflow.keras import layers, optimizers, datasets, Sequentialfrom resnet import resnet18tf.random.set_seed(2345)def preprocess(x, y): # [-1~1] x = t.原创 2022-02-09 12:39:55 · 139 阅读 · 0 评论 -
tensorflow中resnet实战
import tensorflow as tffrom tensorflow import kerasfrom tensorflow.keras import layers, Sequentialclass BasicBlock(layers.Layer): def __init__(self, filter_num, stride=1): super(BasicBlock, self).__init__() self.conv1 = .原创 2022-02-08 22:44:00 · 169 阅读 · 0 评论 -
tensorlow:cifar100_train
cifar100_train原创 2022-02-06 00:01:43 · 1770 阅读 · 0 评论 -
tensorflow中keras实战CIFAR10
import osos.environ['TF_CPP_MIN_LOG_LEVEL']='2'import tensorflow as tffrom tensorflow.keras import datasets, layers, optimizers, Sequential, metricsfrom tensorflow import kerasdef preprocess(x, y): # [0~255] => [-1~1] x = 2 * tf..原创 2022-02-01 21:33:17 · 189 阅读 · 0 评论 -
fashion minst
fashion minstrel原创 2022-01-25 11:57:35 · 1687 阅读 · 1 评论