From b328816ecf16c65ee43ba14c6edd2a6e8dcdacff Mon Sep 17 00:00:00 2001 From: Xingyi Zhou Date: Tue, 7 May 2019 11:54:35 -0500 Subject: [PATCH] add third-party implementation, fix data setup instruction, and fix typo in dlav0 --- README.md | 5 +++++ readme/DATA.md | 9 ++++++++- src/lib/models/networks/dlav0.py | 6 +++--- 3 files changed, 16 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index ade69a8..a138d77 100644 --- a/README.md +++ b/README.md @@ -119,6 +119,11 @@ We provide scripts for all the experiments in the [experiments](experiments) fol If you are interested in training CenterNet in a new dataset, use CenterNet in a new task, or use a new network architecture for CenterNet, please refer to [DEVELOP.md](readme/DEVELOP.md). Also feel free to send us emails for discussions or suggestions. +## Third-party implementation + +- Keras: [keras-centernet](https://github.com/see--/keras-centernet) from [see--](https://github.com/see--). + + ## License CenterNet itself is released under the MIT License (refer to the LICENSE file for details). diff --git a/readme/DATA.md b/readme/DATA.md index 5a57694..492cd15 100644 --- a/readme/DATA.md +++ b/readme/DATA.md @@ -91,6 +91,13 @@ If you want to reproduce the results in the paper for benchmark evaluation and t - Run `python convert_kitti_to_coco.py` in `tools` to convert the annotation into COCO format. You can set `DEBUG=True` in `line 5` to visualize the annotation. +- Link image folder + + ~~~ + cd ${CenterNet_ROOT}/data/kitti/ + mkdir images + ln -s training/image_2 images/trainval + ~~~ - The data structure should look like: @@ -106,4 +113,4 @@ If you want to reproduce the results in the paper for benchmark evaluation and t `-- images |-- trainval |-- test - ~~~ \ No newline at end of file + ~~~ diff --git a/src/lib/models/networks/dlav0.py b/src/lib/models/networks/dlav0.py index e7ca539..92fdbcf 100644 --- a/src/lib/models/networks/dlav0.py +++ b/src/lib/models/networks/dlav0.py @@ -639,9 +639,9 @@ def dla169up(classes, pretrained_base=None, **kwargs): return model ''' -def get_pose_net(heads, down_ratio=4, head_conv=256): - model = DLASeg('dla34', heads, +def get_pose_net(num_layers, heads, add_conv=256, down_ratio=4): + model = DLASeg('dla{}'.format(num_layers), heads, pretrained=True, down_ratio=down_ratio, head_conv=head_conv) - return model \ No newline at end of file + return model