search

clovaai / deep-text-recognition-benchmark

Text recognition (optical character recognition) with deep learning methods, ICCV 2019
Apache License 2.0
3.72k stars 1.09k forks source link

custom dataset Calculated padded input size per channel: (1 x 22). Kernel size: (2 x 2) #410

Open PavloMyrotiuk opened 11 months ago

PavloMyrotiuk commented 11 months ago

generated 3 datasets(train, valid, eval) placed them into data/train, data/valid, data/eval folders Running in Google Colab:

!python train.py \
--exp_name 'test-train' \
--imgH 23 --imgW 80 --character '0123456789b' \
--train_data data/train --valid_data data/valid --select_data train --batch_ratio 1 \
--Transformation TPS \
--FeatureExtraction ResNet \
--SequenceModeling BiLSTM \
--Prediction Attn \
--workers 2

Getting an error:

Traceback (most recent call last):
  File "/content/drive/MyDrive/Workspace/deep-text-recognition-benchmark/train.py", line 317, in <module>
    train(opt)
  File "/content/drive/MyDrive/Workspace/deep-text-recognition-benchmark/train.py", line 163, in train
    preds = model(image, text[:, :-1])  # align with Attention.forward
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/parallel/data_parallel.py", line 183, in forward
    return self.module(*inputs[0], **module_kwargs[0])
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/content/drive/MyDrive/Workspace/deep-text-recognition-benchmark/model.py", line 76, in forward
    visual_feature = self.FeatureExtraction(input)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/content/drive/MyDrive/Workspace/deep-text-recognition-benchmark/modules/feature_extraction.py", line 62, in forward
    return self.ConvNet(input)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/content/drive/MyDrive/Workspace/deep-text-recognition-benchmark/modules/feature_extraction.py", line 242, in forward
    x = self.conv4_2(x)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py", line 460, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py", line 456, in _conv_forward
    return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Calculated padded input size per channel: (1 x 22). Kernel size: (2 x 2). Kernel size can't be greater than actual input size

Output before an error: 

Filtering the images containing characters which are not in opt.character
Filtering the images whose label is longer than opt.batch_max_length
--------------------------------------------------------------------------------
dataset_root: data/train
opt.select_data: ['train']
opt.batch_ratio: ['1']
--------------------------------------------------------------------------------
dataset_root:    data/train  dataset: train
sub-directory:  /.   num samples: 20103
num total samples of train: 20103 x 1.0 (total_data_usage_ratio) = 20103
num samples of train per batch: 192 x 1.0 (batch_ratio) = 192
--------------------------------------------------------------------------------
Total_batch_size: 192 = 192
--------------------------------------------------------------------------------
dataset_root:    data/valid  dataset: /
sub-directory:  /.   num samples: 5847
--------------------------------------------------------------------------------
model input parameters 23 80 20 1 512 256 13 25 TPS ResNet BiLSTM Attn
Skip Transformation.LocalizationNetwork.localization_fc2.weight as it is already initialized
Skip Transformation.LocalizationNetwork.localization_fc2.bias as it is already initialized
Model:
DataParallel(
  (module): Model(
    (Transformation): TPS_SpatialTransformerNetwork(
      (LocalizationNetwork): LocalizationNetwork(
        (conv): Sequential(
          (0): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
          (4): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (5): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (6): ReLU(inplace=True)
          (7): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
          (8): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (9): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (10): ReLU(inplace=True)
          (11): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
          (12): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (13): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (14): ReLU(inplace=True)
          (15): AdaptiveAvgPool2d(output_size=1)
        )
        (localization_fc1): Sequential(
          (0): Linear(in_features=512, out_features=256, bias=True)
          (1): ReLU(inplace=True)
        )
        (localization_fc2): Linear(in_features=256, out_features=40, bias=True)
      )
      (GridGenerator): GridGenerator()
    )
    (FeatureExtraction): ResNet_FeatureExtractor(
      (ConvNet): ResNet(
        (conv0_1): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn0_1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv0_2): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn0_2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (maxpool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
        (layer1): Sequential(
          (0): BasicBlock(
            (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
            (downsample): Sequential(
              (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
              (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
        (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (maxpool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
        (layer2): Sequential(
          (0): BasicBlock(
            (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
            (downsample): Sequential(
              (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
              (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
          (1): BasicBlock(
            (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
          )
        )
        (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (maxpool3): MaxPool2d(kernel_size=2, stride=(2, 1), padding=(0, 1), dilation=1, ceil_mode=False)
        (layer3): Sequential(
          (0): BasicBlock(
            (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
            (downsample): Sequential(
              (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
              (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
          (1): BasicBlock(
            (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
          )
          (2): BasicBlock(
            (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
          )
          (3): BasicBlock(
            (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
          )
          (4): BasicBlock(
            (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
          )
        )
        (conv3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (layer4): Sequential(
          (0): BasicBlock(
            (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
          )
          (1): BasicBlock(
            (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
          )
          (2): BasicBlock(
            (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
          )
        )
        (conv4_1): Conv2d(512, 512, kernel_size=(2, 2), stride=(2, 1), padding=(0, 1), bias=False)
        (bn4_1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv4_2): Conv2d(512, 512, kernel_size=(2, 2), stride=(1, 1), bias=False)
        (bn4_2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (AdaptiveAvgPool): AdaptiveAvgPool2d(output_size=(None, 1))
    (SequenceModeling): Sequential(
      (0): BidirectionalLSTM(
        (rnn): LSTM(512, 256, batch_first=True, bidirectional=True)
        (linear): Linear(in_features=512, out_features=256, bias=True)
      )
      (1): BidirectionalLSTM(
        (rnn): LSTM(256, 256, batch_first=True, bidirectional=True)
        (linear): Linear(in_features=512, out_features=256, bias=True)
      )
    )
    (Prediction): Attention(
      (attention_cell): AttentionCell(
        (i2h): Linear(in_features=256, out_features=256, bias=False)
        (h2h): Linear(in_features=256, out_features=256, bias=True)
        (score): Linear(in_features=256, out_features=1, bias=False)
        (rnn): LSTMCell(269, 256)
      )
      (generator): Linear(in_features=256, out_features=13, bias=True)
    )
  )
)
Trainable params num :  49523157
Optimizer:
Adadelta (
Parameter Group 0
    differentiable: False
    eps: 1e-08
    foreach: None
    lr: 1
    maximize: False
    rho: 0.95
    weight_decay: 0
)
------------ Options -------------
exp_name: test-train
train_data: data/train
valid_data: data/valid
manualSeed: 1111
workers: 2
batch_size: 192
num_iter: 300000
valInterval: 2000
saved_model: 
FT: False
adam: False
lr: 1
beta1: 0.9
rho: 0.95
eps: 1e-08
grad_clip: 5
baiduCTC: False
select_data: ['train']
batch_ratio: ['1']
total_data_usage_ratio: 1.0
batch_max_length: 25
imgH: 23
imgW: 80
rgb: False
character: 0123456789b
sensitive: False
PAD: False
data_filtering_off: False
Transformation: TPS
FeatureExtraction: ResNet
SequenceModeling: BiLSTM
Prediction: Attn
num_fiducial: 20
input_channel: 1
output_channel: 512
hidden_size: 256
num_gpu: 1
num_class: 13
---------------------------------------

Would be grateful for any advice. Thank you in advance.