- 20 Jun, 2017 1 commit
-
-
derekjchow authored
-
- 19 Jun, 2017 3 commits
-
-
derekjchow authored
-
Kaz Sato authored
from Google internal link
-
黄璞 authored
* make slim_walkthrough ipython notebook python3 compatible * make slim_walkthrough ipython notebook python3 compatible
-
- 17 Jun, 2017 1 commit
-
-
Duc Nguyen authored
iteritems -> items
-
- 16 Jun, 2017 13 commits
-
-
vivek rathod authored
-
Jonathan Huang authored
-
derekjchow authored
Fixes #1585
-
Neal Wu authored
Fix broken link to mscoco.org
-
Neal Wu authored
URL returns 404
-
Dheera Venkatraman authored
Fix URL
-
Neal Wu authored
Remove the erroneous comment from resnet_v2.py again
-
Neal Wu authored
-
Matthias Winkelmann authored
Thanks for the good work!
-
Lukasz Kaiser authored
update sequence loss to contrib from legacy
-
derekjchow authored
-
Andrew Selle authored
Update cifar10_input.py
-
Andrew Selle authored
-
- 15 Jun, 2017 16 commits
-
-
Neal Wu authored
Add object_detection to the main README
-
Neal Wu authored
-
Neal Wu authored
Reduce batchsize from 32->24 for SSD configs.
-
Neal Wu authored
Reproduce reported virtual adversarial text results
-
Neal Wu authored
Fixing the initialization/loading bug.
-
Neal Wu authored
Implemented LRN for AlexNet tutorial
-
Neal Wu authored
-
Nick Johnston authored
Update username and add new line in READMEs.
-
Nick Johnston authored
-
Derek Chow authored
-
derekjchow authored
-
derekjchow authored
For details see our paper: "Speed/accuracy trade-offs for modern convolutional object detectors." Huang J, Rathod V, Sun C, Zhu M, Korattikara A, Fathi A, Fischer I, Wojna Z, Song Y, Guadarrama S, Murphy K, CVPR 2017 https://arxiv.org/abs/1611.10012
-
derekjchow authored
-
Ryan Sepassi authored
-
Neal Wu authored
-
Neal Wu authored
-
- 14 Jun, 2017 6 commits
-
-
Mohammad Babaeizadeh authored
The code currently loads the checkpoint and then initializes the variables resulting to random weights. Swapping the order fixes the loading checkpoint issue.
-
derekjchow authored
Fix slow down with only 1 GPU
-
g21589 authored
This patch assigns dequeue node to inputs_device. And nolonger shows "Ignoring device specification /device:GPU:X for node 'clone_X/fifo_queue_Dequeue'" message.
-
xiangjinwu authored
-
derekjchow authored
- Add inception_resnet_v2_base - Provide option to use SAME padding for all inception resnet v2 layers. This is to align feature maps sizes.
-
James Pruegsanusak authored
Use a relative link instead
-