SSD-Tensorflow
SSD-Tensorflow copied to clipboard
Single Shot MultiBox Detector in TensorFlow
i choice a gpu to run the train.py, and the clone_to_cpu is false, why my cpu utility is 100% import os os.environ["CUDA_VISIBLE_DEVICE]='4' the gpu utility is 100%, use top command...
I use VOC2007 datasets to train SSD.The iteration has come to 10000, but the loss does not decrease. Who can help me?
Hello everyone! I'm training the net using PASCAL VOC 2012 dataset and find that the total loss is always higher than 40. Then I begin to observe the loss of...
INFO:tensorflow:global step 52620: loss = 45.7045 (0.686 sec/step) INFO:tensorflow:global step 52630: loss = 34.3893 (0.697 sec/step) INFO:tensorflow:global step 52640: loss = 18.0897 (0.762 sec/step) INFO:tensorflow:global step 52650: loss = 20.7888...
I have two questions about the evaluation, could anyone give me some hint and help, please? 1. AP_VOC07 v.s. AP_VOC12 When I ran the `eval_ssh_network.py`, I got two results, `AP_VOC07/mAP`...
How can use model inception_v3 instead of ssd_300_vgg? tf.app.flags.DEFINE_string('model_name', 'inception_v3', 'The name of the architecture to train.')
Traceback (most recent call last): File "D:\Python3.5\lib\site-packages\tensorflow\python\training\supervisor.py", line 994, in managed_session yield sess File "D:\Python3.5\lib\site-packages\tensorflow\contrib\slim\python\slim\learning.py", line 770, in train sess, train_op, global_step, train_step_kwargs) File "D:\Python3.5\lib\site-packages\tensorflow\contrib\slim\python\slim\learning.py", line 487, in train_step run_metadata=run_metadata)...
The following error occurred while executing the `jupyter notebook ssd_notebook.ipynb` in the docker container ``` Traceback (most recent call last): File "/usr/local/bin/jupyter-notebook", line 11, in sys.exit(main()) File "/usr/local/lib/python2.7/dist-packages/jupyter_core/applicat return super(JupyterApp,...