EdjeElectronics / TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10

How to train a TensorFlow Object Detection Classifier for multiple object detection on Windows
Apache License 2.0
2.92k stars 1.3k forks source link

SyntaxError: invalid syntax #540

Open yeonchae opened 3 years ago

yeonchae commented 3 years ago

Hello, guys. Thanks a lot for visiting this issue.

Actually, I've got some error on the procedure of running the legacy/train.py

Here's the full-text of given error. Actually, I had no idea with the python files in site-papckages.

Furthermore, "Returns a dropout op applied to the input" is not written in layers.py file.

(od) yeonchae@snucem:~/anaconda3/envs/od/models/research/object_detection$ python legacy/train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/ssd_mobilenet_v1_pets.config Traceback (most recent call last): File "legacy/train.py", line 51, in from object_detection.builders import dataset_builder File "/home/yeonchae/anaconda3/envs/od/models/research/object_detection/builders/dataset_builder.py", line 32, in from object_detection.builders import decoder_builder File "/home/yeonchae/anaconda3/envs/od/models/research/object_detection/builders/decoder_builder.py", line 25, in from object_detection.data_decoders import tf_example_decoder File "/home/yeonchae/anaconda3/envs/od/models/research/object_detection/data_decoders/tf_example_decoder.py", line 28, in from tf_slim import tfexample_decoder as slim_example_decoder File "/home/yeonchae/anaconda3/envs/od/lib/python3.6/site-packages/tf_slim-1.1.0-py3.6.egg/tf_slim/init.py", line 25, in from tf_slim.layers import File "/home/yeonchae/anaconda3/envs/od/lib/python3.6/site-packages/tf_slim-1.1.0-py3.6.egg/tf_slim/layers/init.py", line 25, in from tf_slim.layers.layers import File "/home/yeonchae/anaconda3/envs/od/lib/python3.6/site-packages/tf_slim-1.1.0-py3.6.egg/tf_slim/layers/layers.py", line 1528 """Returns a dropout op applied to the input. ^ SyntaxError: invalid syntax

Any comment would be greatly appreciated.

Thanks.