NVIDIA
NVIDIA
TAO Pretrained DetectNet V2
Model
NVIDIA
NVIDIA
TAO Pretrained DetectNet V2

Pretrained weights to facilitate transfer learning using TAO Toolkit.

14 Versions
01/28/2022 3:38 PM UTC170.65 MBAccuracy: 77.0480 EpochsBatch Size: 1GPU: V100
08/24/2021 12:33 AM UTC229.15 MBAccuracy: 77.5280 EpochsBatch Size: 1GPU: V100
08/24/2021 12:32 AM UTC467.32 MBAccuracy: 76.4480 EpochsBatch Size: 1GPU: V100
squeezenetSelected
08/24/2021 12:32 AM UTC6.46 MBAccuracy: 65.6780 EpochsBatch Size: 1GPU: V100
08/24/2021 12:32 AM UTC47.74 MBAccuracy: 82.280 EpochsBatch Size: 1GPU: V100
08/24/2021 12:32 AM UTC5.1 MBAccuracy: 77.580 EpochsBatch Size: 1GPU: V100
08/24/2021 12:32 AM UTC13.37 MBAccuracy: 79.580 EpochsBatch Size: 1GPU: V100
08/24/2021 12:31 AM UTC153.77 MBAccuracy: 82.680 EpochsBatch Size: 1GPU: V100
08/24/2021 12:31 AM UTC113.2 MBAccuracy: 82.280 EpochsBatch Size: 1GPU: V100
08/24/2021 12:31 AM UTC294.53 MBAccuracy: 82.780 EpochsBatch Size: 1GPU: V100

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.