machine-learning - 在具有不同数据集的 DIGITS 中使用预训练模型时出错。如何根据新数据集修改图层？

Question

我尝试对 DIGITS 使用预训练模型 (VGG 16)，但出现此错误。

ERROR: Check failed: error == cudaSuccess (2 vs. 0) out of memory

和

conv2_2 does not need backward computation.
relu2_1 does not need backward computation.
conv2_1 does not need backward computation.
pool1 does not need backward computation.
relu1_2 does not need backward computation.
conv1_2 does not need backward computation.
relu1_1 does not need backward computation.
conv1_1 does not need backward computation.
data does not need backward computation.
This network produces output label
This network produces output softmax
Network initialization done.
Solver scaffolding done.
Finetuning from /home/digits/digits/jobs/20161020-095911-9d01/model.caffemodel
Attempting to upgrade input file specified using deprecated V1LayerParameter: /home/digits/digits/jobs/20161020-095911-9d01/model.caffemodel
Successfully upgraded file specified using deprecated V1LayerParameter
Attempting to upgrade input file specified using deprecated input fields: /home/digits/digits/jobs/20161020-095911-9d01/model.caffemodel
Successfully upgraded file specified using deprecated input fields.
Note that future Caffe releases will only support input layers and not input fields.
Check failed: error == cudaSuccess (2 vs. 0)  out of memory

我将 deploy.prototxt 和 VGG_ILSVRC_16_layers.caffemodel 和 synset_words.txt 成功上传到 DIGITS 中，并使用我的数据集进行了测试，该数据集有两个类。

Answer 1

有时digits-server无法清除内存。如果您使用的是 ubuntu，请尝试使用此命令:

sudo restart nvidia-digits-server

如果这不起作用并且您再次面临相同的情况，则需要减少batch_size