[英]Can caffe take in a batch of inputs with different resolutions at once? If so how?
I am thinking of building a larger network with more input layers which would consist of all the respective reshaped input resolutions from the batch. 我正在考虑建立一个具有更多输入层的更大的网络,其中将包含该批次中所有经过重新调整的输入分辨率。 Please let me know if this is possible and if it is what would be the most efficient way? 请让我知道这是否可行,这是最有效的方法吗?
For example: 3x160x160 + 3x48x48 + 3x128x128 | 例如:3x160x160 + 3x48x48 + 3x128x128 | | | | | Rest of the network | 网络其余部分| | | | | Outputs 产出
Caffe processes Blobs
: these are N
-dimensional arrays, therefore the dimensions of all elements in a single batch must be of the same shape (you can reshape
between batches). Caffe进程Blobs
:这些是N
维数组,因此,单个批次中所有元素的尺寸必须具有相同的形状(您可以在批次之间reshape
形状)。
However, if you are going to use the same multiple shapes for all inputs in the batch, ie, you'll have inputs like N
x3x160x160 + N
x3x48x48 + N
x3x128x128, then you can create three input layer (one for each shape) and feed the net with three types of blobs at each iteration. 但是,如果您要对批处理中的所有输入使用相同的多个形状,即您将拥有N
x3x160x160 + N
x3x48x48 + N
x3x128x128之类的输入,则可以创建三个输入层(每个形状一个)在每次迭代中用三种类型的Blob填充网络。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.