【TensorFlow】ValueError: Shape must be rank 1 but is rank 0 for ' ’ with input shapes: [].问题

基于TensorFlow训练mnist数据集出现如下错误：

检测代码，发现是偏置设置格式错误导致。

1、错误代码：

# 定义权重和偏置
n_input = 784
n_output = 10
weights = {'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64], stddev=0.1)),'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128], stddev=0.1)),'wd1': tf.Variable(tf.random_normal([7 * 7 * 128, 1024], stddev=0.1)),'wd2': tf.Variable(tf.random_normal([1024, n_output], stddev=0.1))
}
biases = {'bc1': tf.Variable(tf.random_normal(64), stddev=0.1),'bc2': tf.Variable(tf.random_normal(128), stddev=0.1),'bd1': tf.Variable(tf.random_normal(1024), stddev=0.1),'bd2': tf.Variable(tf.random_normal(n_output), stddev=0.1)
}

2、修改后的代码如下：

把biases的"()"改为"[]"

#定义权重和偏置
n_input = 784
n_output= 10
weights = {'wc1':tf.Variable(tf.random_normal([3,3,1,64], stddev=0.1)),'wc2':tf.Variable(tf.random_normal([3,3,64,128],stddev=0.1)),'wd1':tf.Variable(tf.random_normal([7*7*128,1024],stddev=0.1)),'wd2':tf.Variable(tf.random_normal([1024,n_output],stddev=0.1))
}
biases = {'bc1':tf.Variable(tf.random_normal([64], stddev=0.1)),'bc2':tf.Variable(tf.random_normal([128],stddev=0.1)),'bd1':tf.Variable(tf.random_normal([1024],stddev=0.1)),'bd2':tf.Variable(tf.random_normal([n_output],stddev=0.1))
}

【TensorFlow】ValueError: Shape must be rank 1 but is rank 0 for ' ’ with input shapes: [].问题相关推荐

人工智障与深度学渣之问题集锦：ValueError: Shape must be rank 4 but is rank 1 for 'Conv2D' with input shapes。。。
醉最近在写网络的时候,总会遇到一些坑,虽然大部分都能百度到,但还是有一些坑让我郁闷.比较好久没写网络了,以前的填坑经验也都忘了.比如这里的报错: ValueError: Shape must be r ...
keras报错 ValueError: Shape must be rank 1 but is rank 0 for 'bn_conv1/Reshape_4' (op: 'Reshape') 不用降级
问题:ValueError: Shape must be rank 1 but is rank 0 for 'bn_conv1/Reshape_4' (op: 'Reshape') with inpu ...
ValueError: Shape mismatch: The shape of labels (received (768,)) should equal the shape of logits e
问题运行tensorflow 的resnet网络,预测结果,出现报错 ValueError: Shape mismatch: The shape of labels (received (768,) ...
成功解决ValueError: Shape of passed values is (33, 1), indices imply (33, 2)
成功解决ValueError: Shape of passed values is (33, 1), indices imply (33, 2) 目录解决问题解决思路解决方法解决问题 Valu ...
成功解决ValueError: Cannot feed value of shape (80, 15, 1, 1) for Tensor 'Placeholder_1:0', which has sh
成功解决ValueError: Cannot feed value of shape (80, 15, 1, 1) for Tensor 'Placeholder_1:0', which has sh ...
成功解决ValueError: Shape of passed values is (1, 332), indices imply (1, 1)
成功解决ValueError: Shape of passed values is (1, 332), indices imply (1, 1) 目录解决问题解决思路解决方法解决问题 Valu ...
已解决ValueError: Shape of passed values is (1509, 1), indices imply (1509, 2)
已解决(pandas创建DataFrame对象失败)ValueError: Shape of passed values is (1509, 1), indices imply (1509, 2) 文 ...
已解决ValueError: Shape of passed values is (6, 3), indices imply (4, 3)
已解决(pd.concat连接错误)ValueError: Shape of passed values is (6, 3), indices imply (4, 3) 文章目录报错代码报错翻译 ...
解决ValueError: Shape of passed values is (1，5), indices imply (1，3)
报错部分代码: MetricsDataFrame = pd.DataFrame(Metrics,columns=np.tile(MetricNames, datasetNum),index=exper ...

【TensorFlow】ValueError: Shape must be rank 1 but is rank 0 for ' ’ with input shapes: [].问题

【TensorFlow】ValueError: Shape must be rank 1 but is rank 0 for ' ’ with input shapes: [].问题相关推荐

最新文章

热门文章