fully connected layer in a CNN
3 ビュー (過去 30 日間)
古いコメントを表示
Jyoti Nautiyal
2020 年 9 月 27 日
コメント済み: Jyoti Nautiyal
2020 年 10 月 2 日
I trained a CNN for MNIST dataset with one fully connected layer. The input to fully connected layer is 9 channels of size 20 x 20, and ouput is 10 classes. How can i calculate the total number of multiplications and additions in this layer.
0 件のコメント
採用された回答
Srivardhan Gadila
2020 年 10 月 1 日
You can use the analyzeNetwork to view the network architecture, shape of layerwise Activations & Learnables etc.
Based on the above information and under the assumption that your fullyConnectedLayer is having bias as Learnables then the layer has an input vector of size 4000 (i.e., 20x20x10 flattened) and the size of Weights & Bias are 10x4000, 10x1 respectively.
The general operation of fullyConnectedLayer is Z = W*X + b => 10*4000 = 40,000 multiplications and 39,990 + 10 = 40,000 additions.
その他の回答 (0 件)
参考
カテゴリ
Help Center および File Exchange で Image Data Workflows についてさらに検索
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!