small changes to front page #8
Conversation
| ``` | ||
| Caffe also provides **seamless switching between CPU and GPU**, which allows one to train models with fast GPUs and then deploy them on non-GPU clusters with one line of code: `Caffe::set_mode(Caffe::CPU)`. | ||
|
|
||
| Even in CPU mode, computing predictions on an image takes only 200 ms. |
There was a problem hiding this comment.
Could you remove this line? The CPU code is actually faster (something around 20ms with C++ and batch mode), but I haven't extensively benchmarked it. It would be safer to not mention it right now :)
There was a problem hiding this comment.
I think it's important to advertise the fact that this is totally useable
without a GPU though. 200 ms is accurate from unopened file to predictions,
right? We can say (on an image already loaded into memory, Caffe takes only
20 ms). We can always change the numbers as we get more accurate ones.
On Wed, Dec 4, 2013 at 12:38 PM, Yangqing Jia [email protected]:
In index.md:
-
-Caffe::set_mode(Caffe::CPU); -
+Caffe also provides seamless switching between CPU and GPU, which allows one to train models with fast GPUs and then deploy them on non-GPU clusters with one line of code:Caffe::set_mode(Caffe::CPU).
+
+Even in CPU mode, computing predictions on an image takes only 200 ms.Could you remove this line? The CPU code is actually faster (something
around 20ms with C++ and batch mode), but I haven't extensively benchmarked
it. It would be safer to not mention it right now :)—
Reply to this email directly or view it on GitHubhttps://github.com/Yangqing/caffe/pull/8/files#r8109227
.
weekly update
ghost
mentioned this pull request
Fix the instruction of installing lmdb in README
Revert "DEV-26710: Remove OHEM layer from Curalate Caffe"
ResNet-50 example using variable sized image data augmentation.
Merging minor edits / bug fixes for C++ interface
No description provided.