Open aldiak opened 4 years ago
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
?
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.
the current keras version on pip is 2.3.1, so if you run pip install keras
it should bump you up to that?
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