neural nework validation accuracy calculation

Joy
2018 2 14
1 个回答
更新时间：2019 2 19
5 次查看（30 天）

0 个投票

I am currently training a CNN to do modulation classification using NN toolbox. The validation accuracy reported by matlab through the training progress window is approximated 50% at the end of training. But when I tested the accuracy myself using the trained network with the validation data set, it's only about 20% to 25%. This is calculated as (num of correct classification / overall number of tests).
How does matlab calculate the validation accuracy? Where can I find more information? Thanks.

请先登录，再回答此问题。

回答（1 个）

Joy
Joy 2018-2-15

0 个投票

sure, here is the code
for snr = snr_str:2:snr_stop
ct_idx = ct_idx+1;
%loop through the data to find all signals with snr of current value
for k = 1:val_len
%check if the snr for this entry is correct
snr_str = string(squeeze(lbl(test_idx(k),2,:)).');
try
snr_i = str2num(snr_str);
catch
snr_i = str2num(char(snr_str));
end
if snr == snr_i
[YPre, scores] = classify(TO_net,valImages(:, :, 1, k));
if isequal(YPre, trainLabels(k))
%correct prediction
predictC_cnt = predictC_cnt+1;
else
predictW_cnt = predictW_cnt+1;
end
ct_idx_c = find(mods_str == string(YPre));
ct_idx_r = find(mods_str == string(trainLabels(k)));
confusionTbl(ct_idx, ct_idx_c, ct_idx_r) = confusionTbl(ct_idx, ct_idx_c, ct_idx_r)+1;
end
end
predictAcc_i = predictC_cnt/(predictC_cnt+predictW_cnt)*100;
predictAcc_t(ct_idx) = predictAcc_i;
%print overall accuracy for current snr
disp(['overall accuracy for snr = ', num2str(snr), ': ', num2str(predictAcc_i), ...
'% over ', num2str(predictC_cnt+predictW_cnt), ' tests']);
total_num_test = total_num_test + predictC_cnt+predictW_cnt;
predictC_cnt = 0;
predictW_cnt = 0;
end

3 个评论
显示 1更早的评论 隐藏 1更早的评论

Joy
Joy 2018-2-20
Just wondering why the CNN validation accuracy took a dive here on the last iteration? Please see the training progress plot attached.
I intentionally stopped the network from training early by giving a small number of MaxEpochs. This is because I suspected the network was overfitting. But I can't understand why the accuracy dropped so much on the last iteration.
Don Mathis
Don Mathis 2019-2-19
Could you post your network layers and training options?

请先登录，再进行评论。

类别

在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

提问:

Joy
Joy
2018-2-14

评论：

Jon Cherrie
Jon Cherrie
2019-2-19

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by