train.py error

[aldiak]

Can someone help me?

(base) cyf@ubuntu:~/RetinanetTutorial/keras-retinanet$ keras_retinanet/bin/train.py --tensorboard-dir ~/RetinanetTutorial/TrainingOutput --snapshot-path ~/RetinanetTutorial/TrainingOutput/snapshots --random-transform --steps 100 pascal ~/RetinanetTutorial/PlumsVOC Using TensorFlow backend. /home/cyf/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) /home/cyf/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) /home/cyf/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) /home/cyf/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:529: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) /home/cyf/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:530: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) /home/cyf/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:535: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. np_resource = np.dtype([("resource", np.ubyte, 1)]) usage: train.py [-h] [--snapshot SNAPSHOT | --imagenet-weights | --weights WEIGHTS | --no-weights] [--backbone BACKBONE] [--batch-size BATCH_SIZE] [--gpu GPU] [--multi-gpu MULTI_GPU] [--multi-gpu-force] [--epochs EPOCHS] [--steps STEPS] [--snapshot-path SNAPSHOT_PATH] [--tensorboard-dir TENSORBOARD_DIR] [--no-snapshots] [--no-evaluation] [--freeze-backbone] {coco,pascal,kitti,oid,csv} ... train.py: error: unrecognized arguments: --random-transform

[jaspereb]

looks like you might be using a different version of train.py? did you pull the master branch from https://github.com/fizyr/keras-retinanet ?

does the random-transform arg appear when you run keras_retinanet/bin/train.py --help ?

[aldiak]

looks like you might be using a different version of train.py? did you pull the master branch from https://github.com/fizyr/keras-retinanet ?

does the random-transform arg appear when you run keras_retinanet/bin/train.py --help ?

I don't have that problem anymore but now It is showing another problem: You are using keras version 2.2.4. The minimum required version is 2.3.0.

even when I upgrade my keras version.

[jaspereb]

the current keras version on pip is 2.3.1, so if you run pip install keras it should bump you up to that?