File:Krizhevsky et al 2012 CNN Fig2.png
Original file (951 × 301 pixels, file size: 80 KB, MIME type: image/png)
Figure 2: An illustration of the architecture of our CNN, explicitly showing the delineation of responsibilities between the two GPUs. One GPU runs the layer-parts at the top of the figure while the other runs the layer-parts at the bottom. The GPUs communicate only at certain layers. The network’s input is 150,528-dimensional, and the number of neurons in the network’s remaining layers is given by 253,440–186,624–64,896–64,896–43,264– 4096–4096–1000. In: Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet Classification with Deep Convolutional Neural Networks." (PDF) In: Advances in Neural Information Processing Systems (NIPS 2012).
File history
Click on a date/time to view the file as it appeared at that time.
Date/Time | Thumbnail | Dimensions | User | Comment | |
---|---|---|---|---|---|
current | 01:28, 22 July 2018 | 951 × 301 (80 KB) | Omoreira (talk | contribs) | Figure 2: An illustration of the architecture of our CNN, explicitly showing the delineation of responsibilities between the two GPUs. One GPU runs the layer-parts at the top of the figure while the other runs the layer-parts at the bottom.... |
You cannot overwrite this file.
File usage
The following page uses this file: