Train your own dataset to report an error, run train_ssd_network to report an error

[liu978079474]

Hello, when I run training ssd network, something went wrong, here is the full log： D:\python3.6\python.exe D:/Project/MyLearning/SSD-Tensorflow-master/train_ssd_network.py

WARNING: The TensorFlow contrib module will not be included in TensorFlow 2.0. For more information, please see:

• https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
• https://github.com/tensorflow/addons If you depend on functionality not listed there, please file an issue.

WARNING:tensorflow:From D:/Project/MyLearning/SSD-Tensorflow-master/train_ssd_network.py:200: create_global_step (from tensorflow.contrib.framework.python.ops.variables) is deprecated and will be removed in a future version. Instructions for updating: Please switch to tf.train.create_global_step WARNING:tensorflow:From D:\python3.6\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version. Instructions for updating: Colocations handled automatically by placer. Traceback (most recent call last): File "D:/Project/MyLearning/SSD-Tensorflow-master/train_ssd_network.py", line 390, in tf.app.run() File "D:\python3.6\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run _sys.exit(main(argv)) File "D:/Project/MyLearning/SSD-Tensorflow-master/train_ssd_network.py", line 204, in main FLAGS.dataset_name, FLAGS.dataset_split_name, FLAGS.dataset_dir) File "D:\Project\MyLearning\SSD-Tensorflow-master\datasets\dataset_factory.py", line 55, in get_dataset reader) File "D:\Project\MyLearning\SSD-Tensorflow-master\datasets\imagenet.py", line 183, in get_split labels_to_names = create_readable_names_for_imagenet_labels() File "D:\Project\MyLearning\SSD-Tensorflow-master\datasets\imagenet.py", line 90, in create_readable_names_for_imagenet_labels filename, _ = urllib.request.urlretrieve(synset_url) File "D:\python3.6\lib\urllib\request.py", line 248, in urlretrieve with contextlib.closing(urlopen(url, data)) as fp: File "D:\python3.6\lib\urllib\request.py", line 223, in urlopen return opener.open(url, data, timeout) File "D:\python3.6\lib\urllib\request.py", line 532, in open response = meth(req, response) File "D:\python3.6\lib\urllib\request.py", line 642, in http_response 'http', request, response, code, msg, hdrs) File "D:\python3.6\lib\urllib\request.py", line 570, in error return self._call_chain(*args) File "D:\python3.6\lib\urllib\request.py", line 504, in _call_chain result = func(*args) File "D:\python3.6\lib\urllib\request.py", line 650, in http_error_default raise HTTPError(req.full_url, code, msg, hdrs, fp) urllib.error.HTTPError: HTTP Error 404: Not Found

Process finished with exit code 1

Thank you！

[chengyangkj]

I got the same problem,it's HTTP error ,train is need to download from the network?

[liu978079474]

Hello, you need to download network model vgg16, if you want to train from scratch, then you need to modify the configuration parameters of the training run.