-
Platform (like ubuntu 16.04/win10): Ubuntu 16.04
Python version: 3.5
Source framework with version (like Tensorflow 1.4.1 with GPU): Tensorflow 1.12 GPU
Destination framework with version (l…
-
Thank you for your code! I was able to exactly replicate the results of your approach (PPAL) on both COCO and Pascal VOC datasets, on Retinanet, without modifying any configuration files.
As the…
Ab-34 updated
5 months ago
-
-
您好，在根据您faster rnn例子做retinanet CAM，初学理解不到位，能否麻烦您简单指导下思路，不胜感激！18792567544@163.com
这是我阅读detectron2 retinanet总结的：
:
File "tools/test_net.py", lin…
-
I see no reason why we can't implement object detection into robosat for specific use-cases.
The pre-processing and post-processing needs to be slightly adapted to work with bounding boxes but othe…
-
My goal is as follows:
```
model = keras_cv.models.RetinaNet.from_preset(
"spinenet_imagenet_open_images",
bounding_box_format='xywh'
)
filepath = tf.keras.utils.get_file(origin="https…
-
Hi,
Following error is getting generated when trying to load the model.
ERROR:
TypeError Traceback (most recent call last)
in ()
8 detector.setModelTypeAsRetinaNet()
9 detector.setModelPat…
Aban8 updated
3 years ago
-
Probably if consecutive layers have same layer type stacked they are logged under same dictionary key in the results.
-
Hi,
My own dataset for used Resnet50 backbone model. But run train.py by implementation error:
File "/Users/servercalap/tf-retinanet-master/tf_retinanet/bin/../../tf_retinanet/utils/__init__.py"…