ibm-aur-nlp / publaynet Goto Github PK

fname = 'examples.tar.gz'
url = 'http://s3.us-south.cloud-object-storage.appdomain.cloud/dax-assets-dev/dax-publaynet/1.0.0/' + fname
r = requests.get(url)
open(fname , 'wb').write(r.content)

[04/08 20:23:44 detectron2]: Arguments: Namespace(config_file='../models/e2e_faster_rcnn_X-101-64x4d-FPN_1x.yaml', webcam=False, video_input=None, input=['../images/Page 0.png'], output=None, confidence_threshold=0.5, opts=['MODEL.WEIGHTS', '../models/Faster-RCNN.pkl'])
Traceback (most recent call last):
  File "../detectron2/demo/demo.py", line 80, in <module>
    cfg = setup_cfg(args)
  File "../Documents/detectron2/demo/demo.py", line 26, in setup_cfg
    cfg.merge_from_file(args.config_file)
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/detectron2/config/config.py", line 31, in merge_from_file
    loaded_cfg = self.load_yaml_with_base(cfg_filename, allow_unsafe=allow_unsafe)
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/fvcore/common/config.py", line 61, in load_yaml_with_base
    cfg = yaml.safe_load(f)
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/yaml/__init__.py", line 162, in safe_load
    return load(stream, SafeLoader)
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/yaml/__init__.py", line 114, in load
    return loader.get_single_data()
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/yaml/constructor.py", line 49, in get_single_data
    node = self.get_single_node()
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/yaml/composer.py", line 36, in get_single_node
    document = self.compose_document()
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/yaml/composer.py", line 58, in compose_document
    self.get_event()
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/yaml/parser.py", line 118, in get_event
    self.current_event = self.state()
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/yaml/parser.py", line 193, in parse_document_end
    token = self.peek_token()
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/yaml/scanner.py", line 129, in peek_token
    self.fetch_more_tokens()
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/yaml/scanner.py", line 223, in fetch_more_tokens
    return self.fetch_value()
  File "../anaconda3/envs/pytorch_env/lib/python3.9/site-packages/yaml/scanner.py", line 577, in fetch_value
    raise ScannerError(None, None,
yaml.scanner.ScannerError: mapping values are not allowed here

from detectron2.config import get_cfg

config_file = "/content/config/e2e_mask_rcnn_X-101-64x4d-FPN_1x.yaml" #(wget https://raw.githubusercontent.com/ibm-aur-nlp/PubLayNet/master/pre-trained-models/Mask-RCNN/e2e_mask_rcnn_X-101-64x4d-FPN_1x.yaml)
model_file = "/content/models/model_final.pkl" #(wget https://dax-cdn.cdn.appdomain.cloud/dax-publaynet/1.0.0/pre-trained-models/Mask-RCNN/model_final.pkl)
cfg = get_cfg()
cfg._open_cfg(config_file)
cfg.DATASETS.TRAIN = ("layout_train",)
cfg.DATASETS.TEST = ()
cfg.DATALOADER.NUM_WORKERS = 2
cfg.MODEL.WEIGHTS = model_file   # Let training initialize from model zoo
cfg.SOLVER.IMS_PER_BATCH = 2
cfg.SOLVER.BASE_LR = 0.00025  # pick a good LR
cfg.SOLVER.MAX_ITER = 3000    # 300 iterations seems good enough for this toy dataset; you will need to train longer for a practical dataset
cfg.SOLVER.STEPS = []        # do not decay learning rate
cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 128   # faster, and good enough for this toy dataset (default: 512)
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 4  # only has one class (ballon). (see https://detectron2.readthedocs.io/tutorials/datasets.html#update-the-config-for-new-datasets)
# NOTE: this config means the number of classes, but a few popular unofficial tutorials incorrect uses num_classes+1 here.

os.makedirs(cfg.OUTPUT_DIR, exist_ok=True)
trainer = DefaultTrainer(cfg) 
trainer.resume_or_load(resume=False)
trainer.train()

[05/13 08:55:08 d2.engine.defaults]: Model:
GeneralizedRCNN(
  (backbone): ResNet(
    (stem): BasicStem(
      (conv1): Conv2d(
        3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False
        (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
      )
    )
    (res2): Sequential(
      (0): BottleneckBlock(
        (shortcut): Conv2d(
          64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv1): Conv2d(
          64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
        )
        (conv2): Conv2d(
          64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
        )
        (conv3): Conv2d(
          64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
      )
      (1): BottleneckBlock(
        (conv1): Conv2d(
          256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
        )
        (conv2): Conv2d(
          64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
        )
        (conv3): Conv2d(
          64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
      )
      (2): BottleneckBlock(
        (conv1): Conv2d(
          256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
        )
        (conv2): Conv2d(
          64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
        )
        (conv3): Conv2d(
          64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
      )
    )
    (res3): Sequential(
      (0): BottleneckBlock(
        (shortcut): Conv2d(
          256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
          (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
        )
        (conv1): Conv2d(
          256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False
          (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
        )
        (conv2): Conv2d(
          128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
        )
        (conv3): Conv2d(
          128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
        )
      )
      (1): BottleneckBlock(
        (conv1): Conv2d(
          512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
        )
        (conv2): Conv2d(
          128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
        )
        (conv3): Conv2d(
          128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
        )
      )
      (2): BottleneckBlock(
        (conv1): Conv2d(
          512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
        )
        (conv2): Conv2d(
          128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
        )
        (conv3): Conv2d(
          128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
        )
      )
      (3): BottleneckBlock(
        (conv1): Conv2d(
          512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
        )
        (conv2): Conv2d(
          128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
        )
        (conv3): Conv2d(
          128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
        )
      )
    )
    (res4): Sequential(
      (0): BottleneckBlock(
        (shortcut): Conv2d(
          512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False
          (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
        )
        (conv1): Conv2d(
          512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv2): Conv2d(
          256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv3): Conv2d(
          256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
        )
      )
      (1): BottleneckBlock(
        (conv1): Conv2d(
          1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv2): Conv2d(
          256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv3): Conv2d(
          256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
        )
      )
      (2): BottleneckBlock(
        (conv1): Conv2d(
          1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv2): Conv2d(
          256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv3): Conv2d(
          256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
        )
      )
      (3): BottleneckBlock(
        (conv1): Conv2d(
          1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv2): Conv2d(
          256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv3): Conv2d(
          256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
        )
      )
      (4): BottleneckBlock(
        (conv1): Conv2d(
          1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv2): Conv2d(
          256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv3): Conv2d(
          256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
        )
      )
      (5): BottleneckBlock(
        (conv1): Conv2d(
          1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv2): Conv2d(
          256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
        )
        (conv3): Conv2d(
          256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
        )
      )
    )
  )
  (proposal_generator): RPN(
    (rpn_head): StandardRPNHead(
      (conv): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (objectness_logits): Conv2d(1024, 15, kernel_size=(1, 1), stride=(1, 1))
      (anchor_deltas): Conv2d(1024, 60, kernel_size=(1, 1), stride=(1, 1))
    )
    (anchor_generator): DefaultAnchorGenerator(
      (cell_anchors): BufferList()
    )
  )
  (roi_heads): Res5ROIHeads(
    (pooler): ROIPooler(
      (level_poolers): ModuleList(
        (0): ROIAlign(output_size=(14, 14), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
      )
    )
    (res5): Sequential(
      (0): BottleneckBlock(
        (shortcut): Conv2d(
          1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False
          (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
        )
        (conv1): Conv2d(
          1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
          (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
        )
        (conv2): Conv2d(
          512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
        )
        (conv3): Conv2d(
          512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
        )
      )
      (1): BottleneckBlock(
        (conv1): Conv2d(
          2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
        )
        (conv2): Conv2d(
          512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
        )
        (conv3): Conv2d(
          512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
        )
      )
      (2): BottleneckBlock(
        (conv1): Conv2d(
          2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
        )
        (conv2): Conv2d(
          512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
        )
        (conv3): Conv2d(
          512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
          (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
        )
      )
    )
    (box_predictor): FastRCNNOutputLayers(
      (cls_score): Linear(in_features=2048, out_features=2, bias=True)
      (bbox_pred): Linear(in_features=2048, out_features=4, bias=True)
    )
  )
)
[05/13 08:55:26 d2.data.build]: Removed 0 images with no usable annotations. 1691 images left.
[05/13 08:55:26 d2.data.build]: Distribution of instances among all 4 categories:
|  category  | #instances   |  category  | #instances   |  category  | #instances   |
|:----------:|:-------------|:----------:|:-------------|:----------:|:-------------|
|    Text    | 43760        |    Math    | 2864         |   Table    | 78           |
|   Image    | 312          |            |              |            |              |
|   total    | 47014        |            |              |            |              |
[05/13 08:55:26 d2.data.dataset_mapper]: [DatasetMapper] Augmentations used in training: [ResizeShortestEdge(short_edge_length=(800,), max_size=1333, sample_style='choice'), RandomFlip()]
[05/13 08:55:26 d2.data.build]: Using training sampler TrainingSampler
[05/13 08:55:26 d2.data.common]: Serializing 1691 elements to byte tensors and concatenating them all ...
[05/13 08:55:26 d2.data.common]: Serialized dataset takes 5.30 MiB

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

<ipython-input-25-fc8bb5a8baf3> in <module>()
     21 os.makedirs(cfg.OUTPUT_DIR, exist_ok=True)
     22 trainer = DefaultTrainer(cfg)
---> 23 trainer.resume_or_load(resume=False)
     24 trainer.train()

4 frames

/usr/local/lib/python3.7/dist-packages/fvcore/common/checkpoint.py in _convert_ndarray_to_tensor(self, state_dict)
    357             if not isinstance(v, np.ndarray) and not isinstance(v, torch.Tensor):
    358                 raise ValueError(
--> 359                     "Unsupported type found in checkpoint! {}: {}".format(k, type(v))
    360                 )
    361             if not isinstance(v, torch.Tensor):

ValueError: Unsupported type found in checkpoint! weight_order: <class 'bytes'>

RuntimeError                              Traceback (most recent call last)

<ipython-input-26-857e01592fb9> in <module>()
----> 1 torch.load(model_file)

1 frames

/usr/local/lib/python3.7/dist-packages/torch/serialization.py in _legacy_load(f, map_location, pickle_module, **pickle_load_args)
    764     magic_number = pickle_module.load(f, **pickle_load_args)
    765     if magic_number != MAGIC_NUMBER:
--> 766         raise RuntimeError("Invalid magic number; corrupt file?")
    767     protocol_version = pickle_module.load(f, **pickle_load_args)
    768     if protocol_version != PROTOCOL_VERSION:

RuntimeError: Invalid magic number; corrupt file?