-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Measure accuracy on ResNet50 #7
Comments
To compare with BVLC Caffe with cuDNN:
NB: Due to out of memory, the batch size of 64 could not be used on the NVIDIA GTX1080 (8.0 GB RAM). At the same time, during the Intel Caffe evaluation on ResNet with the batch size of 32, the memory usage was only 2.3 GB. NB-2: After investigating a bit further, the maximum viable batch size was 24 for the
|
When the calibration tool is supported (#8), we will measure accuracy with quantised weights. |
The measured accuracy as actually higher than the authors reported in the submission. This may be due to them using the default
|
In fact, the special
|
So, we need to fix two things for ResNet50:
|
Here is the results for ResNet50 with 224px input and float32
int8
|
So we have validated a minor (0.22-0.24%) loss of accuracy (110-120 images) with |
Here is the results for ResNet50 with 320px input and 320px mean generated over 500 images: float32
int8
|
The mean was generated over 500 images? Was the evaluation also over 500 images or 50,000 images? |
Full 50,000 lmdb. It just was not prepared yet when I've generated this mean. |
So it looks the higher the input resolution, the higher is the accuracy? float32
int8
320' values measured with 320px input and using the mean file from Intel |
I've added results of evaluation using 320px mean file from Intel into the previous tables. |
I also see the Intriguingly, I see only 10 threads being used in both cases, which is equivalent to the number of cores but is only half of the number of available hyperthreads. Can you confirm please? |
Here's the experimental data obtained when following the README and using:
|
The text was updated successfully, but these errors were encountered: