Henry

my tf version is 0.12.1 it reports that "ImportError: cannot import name resnet_v1 from tensorflow.contrib.slim.python.slim.nets" when I load test_faster_rcnn.sh i add a new PYTHONPATH environment variable where there is resnet_v1.py,...

i find a solution under tf_0.12.1 do a little change tf-faster-rcnn/lib/nets/resnet_v1.py LINE 15 #from tensorflow.contrib.slim.python.slim.nets import resnet_v1 import resnet_v1 it works

well, i had the same problem after i had trained about 6000 steps. the problem did not occur at the beginning of loading the graph and weight of the model....

> > Use standard file utilities to get mtimes. > > ERROR:tensorflow:Model diverged with loss = NaN. > > E0513 16:02:25.483811 139845663950592 basic_session_run_hooks.py:760] Model diverged with loss = NaN. >...

How to train (to detect your custom objects): (to train old Yolo v2 yolov2-voc.cfg, yolov2-tiny-voc.cfg, yolo-voc.cfg, yolo-voc.2.0.cfg, ... click by the link) Training Yolo v3: Create file yolo-obj.cfg with the...

If your purpose is not changing the model, but modifying the number of object detection classes, there is no need in making some changes in other layers.

@SanoPan0411 If you compress the model, the performance may be influenced, even may not working. You can have a knowledge of convolutional neural network and full connection net layer. Maybe...