|
@quocleix | |||||
|
EfficientDet: a new family of efficient object detectors. It is based on EfficientNet, and many times more efficient than state of art models.
Link: arxiv.org/abs/1911.09070
Code: coming soon pic.twitter.com/2KYabAnpLL
|
||||||
|
||||||
|
|
Quoc Le
@quocleix
|
22. stu |
|
Architecture of EfficientDet pic.twitter.com/8ZbS7JfEGZ
|
||
|
||
|
|
Quoc Le
@quocleix
|
22. stu |
|
And latency on CPU and GPU: pic.twitter.com/u0itlVZqP6
|
||
|
|
||
|
Nir Ben-Zvi
@nir_benz
|
22. stu |
|
Can we deduct frame-per-second figures from Table 2 in the paper? As is unfortunately often the case, GFLOPs don't correlate to GPU performance at all. The 'latency' table seems more relevant but the numbers are strangely different from real world figures I'm familiar with.
|
||
|
|
||
|
Olivier Grisel
@ogrisel
|
22. stu |
|
Maybe GFLOPs correlate with energy consumption? Although memory use and transfers are probably also very energy intensive.
|
||
|
|
||
|
Bibek Chaudhary
@imbibekk
|
22. stu |
|
chirstmas gift = code in tf 2.0
|
||
|
|
||
|
Alfredo Canziani
@alfcnz
|
22. stu |
|
Nah, it'd run faster in @PyTorch 😜
|
||
|
|
||
|
Sarim Zafar
@1Sarim
|
22. stu |
|
@pjreddie time to release the next YOLO-MON
|
||
|
|
||
|
Shivam Kotwalia 🔍
@ShivamKotwalia
|
22. stu |
|
@saumilshah95 Object Detection is never ending
|
||
|
|
||
|
Papa Ass
@assthiam19
|
29. stu |
|
Hello @quocleix . Is possible to deploy EfficientDet in mobile device ?
|
||
|
|
||
|
Mingxing Tan
@tanmingxing
|
29. stu |
|
Yes, you can. They are tflite compatible.
|
||
|
|
||