Custom Dataset Training not starting

[VAIBHAVPATEL97]

Hello, I am trying to start the training for the custom dataset. But, I am getting the following ValueError. I am not able to figure out a way to solve it. Any leads to solve this. Thanks in advance.

(efficientdet) project@system :~/Desktop/EfficientDet$ python3 train.py --snapshot imagenet --phi 0 --gpu 0 --random-transform --compute-val-loss --freeze-backbone --batch-size 32 --steps 1000 coco datasets/coco

2021-09-09 11:48:25.120558: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2021-09-09 11:48:25.120578: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2.6.0
{'dataset_type': 'coco', 'detect_quadrangle': False, 'detect_text': False, 'snapshot': 'imagenet', 'freeze_backbone': True, 'freeze_bn': False, 'weighted_bifpn': False, 'batch_size': 32, 'phi': 0, 'gpu': '0', 'epochs': 50, 'steps': 1000, 'snapshot_path': 'checkpoints/2021-09-09', 'tensorboard_dir': 'logs/2021-09-09', 'snapshots': True, 'evaluation': True, 'random_transform': True, 'compute_val_loss': True, 'multiprocessing': False, 'workers': 1, 'max_queue_size': 10, 'coco_path': 'datasets/coco'}
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
Traceback (most recent call last):
  File "/home/project/Desktop/EfficientDet/train.py", line 381, in <module>
    main()
  File "/home/project/Desktop/EfficientDet/train.py", line 313, in main
    model, prediction_model = efficientdet(args.phi,
  File "/home/project/Desktop/EfficientDet/model.py", line 430, in efficientdet
    features = backbone_cls(input_tensor=image_input, freeze_bn=freeze_bn)
  File "/home/project/Desktop/EfficientDet/utils/__init__.py", line 58, in wrapper
    return func(*args, **kwargs)
  File "/home/project/Desktop/EfficientDet/efficientnet.py", line 461, in EfficientNetB0
    return EfficientNet(1.0, 1.0, 224, 0.2,
  File "/home/project/Desktop/EfficientDet/efficientnet.py", line 388, in EfficientNet
    if not is_keras_tensor(input_tensor):
  File "/home/project/anaconda3/envs/efficientdet/lib/python3.9/site-packages/tensorflow/python/keras/backend.py", line 1281, in is_keras_tensor
    raise ValueError('Unexpectedly found an instance of type `' + str(type(x)) +

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[Aryanjb]

Hello, I am trying to start the training for the custom dataset. But, I am getting the following ValueError. I am not able to figure out a way to solve it. Any leads to solve this. Thanks in advance.

(efficientdet) project@system :~/Desktop/EfficientDet$ python3 train.py --snapshot imagenet --phi 0 --gpu 0 --random-transform --compute-val-loss --freeze-backbone --batch-size 32 --steps 1000 coco datasets/coco

2021-09-09 11:48:25.120558: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2021-09-09 11:48:25.120578: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2.6.0
{'dataset_type': 'coco', 'detect_quadrangle': False, 'detect_text': False, 'snapshot': 'imagenet', 'freeze_backbone': True, 'freeze_bn': False, 'weighted_bifpn': False, 'batch_size': 32, 'phi': 0, 'gpu': '0', 'epochs': 50, 'steps': 1000, 'snapshot_path': 'checkpoints/2021-09-09', 'tensorboard_dir': 'logs/2021-09-09', 'snapshots': True, 'evaluation': True, 'random_transform': True, 'compute_val_loss': True, 'multiprocessing': False, 'workers': 1, 'max_queue_size': 10, 'coco_path': 'datasets/coco'}
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
Traceback (most recent call last):
  File "/home/project/Desktop/EfficientDet/train.py", line 381, in <module>
    main()
  File "/home/project/Desktop/EfficientDet/train.py", line 313, in main
    model, prediction_model = efficientdet(args.phi,
  File "/home/project/Desktop/EfficientDet/model.py", line 430, in efficientdet
    features = backbone_cls(input_tensor=image_input, freeze_bn=freeze_bn)
  File "/home/project/Desktop/EfficientDet/utils/__init__.py", line 58, in wrapper
    return func(*args, **kwargs)
  File "/home/project/Desktop/EfficientDet/efficientnet.py", line 461, in EfficientNetB0
    return EfficientNet(1.0, 1.0, 224, 0.2,
  File "/home/project/Desktop/EfficientDet/efficientnet.py", line 388, in EfficientNet
    if not is_keras_tensor(input_tensor):
  File "/home/project/anaconda3/envs/efficientdet/lib/python3.9/site-packages/tensorflow/python/keras/backend.py", line 1281, in is_keras_tensor
    raise ValueError('Unexpectedly found an instance of type `' + str(type(x)) +

Hi Vaibhav, did you manage to solve it? I'm also trying to train the model on a custom dataset but facing some issues. Could you please let me know how you proceeded. Thanks in advance