Commitad1570f

committed

Update memory requirements

1 parentcd4faa9 commitad1570fCopy full SHA for ad1570f

File tree

-1

lines changed

-1

lines changed

Lines changed: 2 additions & 1 deletion

Original file line number	Diff line number	Diff line change
`@@ -64,7 +64,8 @@ If you find Faster R-CNN useful in your research, please consider citing:`
`64`	`64`	`###Requirements: hardware`
`65`	`65`
`66`	`66`	`1. For training smaller networks (ZF, VGG_CNN_M_1024) a good GPU (e.g., Titan, K20, K40, ...) with at least 3G of memory suffices`
`67`		`-2. For training with VGG16, you'll need a K40 (~11G of memory)`
	`67`	`+2. For training Fast R-CNN with VGG16, you'll need a K40 (~11G of memory)`
	`68`	`+3. For training the end-to-end version of Faster R-CNN with VGG16, 3G of GPU memory is sufficient (using CUDNN)`
`68`	`69`
`69`	`70`	`###Installation (sufficient for the demo)`
`70`	`71`

Comments

(0)