Commit 38f1ebe0 authored by Vighnesh Birodkar's avatar Vighnesh Birodkar Committed by TF Object Detection Team
Browse files

Change "fine_tune" -> "detection" in CenterNet configs.

PiperOrigin-RevId: 372579796
parent eaeea071
......@@ -115,7 +115,7 @@ train_config: {
fine_tune_checkpoint_version: V2
fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/ckpt-51"
fine_tune_checkpoint_type: "fine_tune"
fine_tune_checkpoint_type: "detection"
}
train_input_reader: {
......
......@@ -178,7 +178,7 @@ train_config: {
fine_tune_checkpoint_version: V2
fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/ckpt-51"
fine_tune_checkpoint_type: "fine_tune"
fine_tune_checkpoint_type: "detection"
}
train_input_reader: {
......
......@@ -138,7 +138,7 @@ train_config: {
fine_tune_checkpoint_version: V2
fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/ckpt-51"
fine_tune_checkpoint_type: "fine_tune"
fine_tune_checkpoint_type: "detection"
}
train_input_reader: {
......
......@@ -66,4 +66,5 @@ Model name
[Faster R-CNN Inception ResNet V2 640x640](http://download.tensorflow.org/models/object_detection/tf2/20200711/faster_rcnn_inception_resnet_v2_640x640_coco17_tpu-8.tar.gz) | 206 | 37.7 | Boxes
[Faster R-CNN Inception ResNet V2 1024x1024](http://download.tensorflow.org/models/object_detection/tf2/20200711/faster_rcnn_inception_resnet_v2_1024x1024_coco17_tpu-8.tar.gz) | 236 | 38.7 | Boxes
[Mask R-CNN Inception ResNet V2 1024x1024](http://download.tensorflow.org/models/object_detection/tf2/20200711/mask_rcnn_inception_resnet_v2_1024x1024_coco17_gpu-8.tar.gz) | 301 | 39.0/34.6 | Boxes/Masks
[ExtremeNet](http://download.tensorflow.org/models/object_detection/tf2/20200711/extremenet.tar.gz) | -- | -- | Boxes
[ExtremeNet (deprecated)](http://download.tensorflow.org/models/object_detection/tf2/20200711/extremenet.tar.gz) | -- | -- | Boxes
[ExtremeNet](http://download.tensorflow.org/models/object_detection/tf2/20210507/extremenet.tar.gz)| -- | -- | Boxes
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment