/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1568: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
/tmp/ipykernel_30/1120537138.py:28: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
  trainer = Trainer(
/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:494: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
max_steps is given, it will override any value given in num_train_epochs
/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1568: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
/tmp/ipykernel_30/1120537138.py:28: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
  trainer = Trainer(
/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:494: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
max_steps is given, it will override any value given in num_train_epochs
/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1568: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
/tmp/ipykernel_30/1120537138.py:28: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
  trainer = Trainer(
/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:494: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
max_steps is given, it will override any value given in num_train_epochs
/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1568: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
/tmp/ipykernel_30/1120537138.py:28: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
  trainer = Trainer(
/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:494: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
max_steps is given, it will override any value given in num_train_epochs
/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1568: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
/tmp/ipykernel_30/1120537138.py:28: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
  trainer = Trainer(
/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:494: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
max_steps is given, it will override any value given in num_train_epochs
/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1568: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
/tmp/ipykernel_30/1120537138.py:28: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
  trainer = Trainer(
/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:494: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
max_steps is given, it will override any value given in num_train_epochs
No files have been modified since last commit. Skipping to prevent empty commit.
/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1568: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
/tmp/ipykernel_30/1818982133.py:28: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
  trainer = Trainer(
/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:494: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1568: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
/tmp/ipykernel_30/2368586458.py:28: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
  trainer = Trainer(
/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:494: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
max_steps is given, it will override any value given in num_train_epochs
{'area': [613362, 407907, 255150, 157685, 139682, 142128, 161721], 'bbox': [[748, 195, 1425, 1101], [1037, 56, 1586, 799], [1279, 469, 1684, 1099], [1599, 498, 1904, 1015], [397, 468, 728, 890], [490, 797, 819, 1229], [211, 930, 568, 1383]], 'bbox_id': [0, 1, 2, 3, 4, 5, 6], 'category': [1, 1, 1, 1, 1, 1, 1]}
{'area': [65339, 2400, 2880, 63732, 6160, 3276, 3245, 2491, 11289], 'bbox': [[615, 69, 838, 362], [574, 311, 634, 351], [517, 357, 562, 421], [528, 329, 754, 611], [126, 419, 203, 499], [21, 541, 73, 604], [1963, 459, 2018, 518], [1917, 465, 1964, 518], [743, 1, 902, 72]], 'bbox_id': [0, 1, 2, 3, 4, 5, 6, 7, 8], 'category': [1, 1, 1, 1, 1, 1, 1, 1, 1]}
{'area': [60342], 'bbox': [[983, 533, 1209, 800]], 'bbox_id': [0], 'category': [1]}
{'area': [246697], 'bbox': [[994, 619, 1445, 1166]], 'bbox_id': [0], 'category': [1]}
{'area': [22400], 'bbox': [[276, 420, 416, 580]], 'bbox_id': [0], 'category': [1]}
{'area': [54990, 46330, 61479], 'bbox': [[144, 10, 379, 244], [362, 0, 567, 226], [671, 1, 914, 254]], 'bbox_id': [0, 1, 2], 'category': [1, 1, 1]}
{'area': [78732, 31150, 75551], 'bbox': [[376, 257, 619, 581], [432, 483, 607, 661], [182, 435, 483, 686]], 'bbox_id': [0, 1, 2], 'category': [1, 1, 1]}
{'area': [8900, 10282, 3185, 9858, 3190, 10395, 6072, 6095, 24112, 9212, 11770], 'bbox': [[108, 340, 197, 440], [56, 368, 153, 474], [18, 386, 67, 451], [0, 444, 106, 537], [42, 517, 100, 572], [84, 474, 183, 579], [302, 322, 371, 410], [370, 255, 423, 370], [416, 525, 592, 662], [366, 630, 460, 728], [340, 668, 447, 778]], 'bbox_id': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10], 'category': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}
{'area': [930852], 'bbox': [[19, 145, 1033, 1063]], 'bbox_id': [0], 'category': [1]}
Some weights of the model checkpoint at facebook/detr-resnet-50-dc5 were not used when initializing DetrForObjectDetection: ['model.backbone.conv_encoder.model.layer1.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer2.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer3.0.downsample.1.num_batches_tracked', 'model.backbone.conv_encoder.model.layer4.0.downsample.1.num_batches_tracked']
- This IS expected if you are initializing DetrForObjectDetection from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing DetrForObjectDetection from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Some weights of DetrForObjectDetection were not initialized from the model checkpoint at facebook/detr-resnet-50-dc5 and are newly initialized because the shapes did not match:
- class_labels_classifier.bias: found shape torch.Size([92]) in the checkpoint and torch.Size([2]) in the model instantiated
- class_labels_classifier.weight: found shape torch.Size([92, 256]) in the checkpoint and torch.Size([2, 256]) in the model instantiated
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.