The training dataset is correct? about chartreader HOT 2 OPEN

哥，我问个问题，detection和group的数据集是怎么来的？是根据EC400K数据集处理来的吗？

from chartreader.

nohup: 忽略输入
wandb: Currently logged in as: aoeyuu-con (esheeper). Use wandb login --relogin to force relogin
wandb: - Waiting for wandb.init()...
wandb: \ Waiting for wandb.init()...
wandb: wandb version 0.16.3 is available! To upgrade, please run:
wandb: $ pip install wandb --upgrade
wandb: Tracking run with wandb version 0.15.4
wandb: Run data is saved locally in /home/dmind/workspace/ChartReader/ChartReader/wandb/run-20240304_114850-d3gmyn77
wandb: Run wandb offline to turn off syncing.
wandb: Syncing run bar only
wandb: Network error (TransientError), entering retry loop.

0%| | 0/100000 [00:00<?, ?it/s]Traceback (most recent call last):
File "/home/dmind/workspace/ChartReader/ChartReader/train_extraction.py", line 144, in train
training_loss = nnet.train_step(*training_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 50, in train_step
loss = self(xs, ys)
^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 44, in forward
loss = self.loss_function(preds, ys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/models/py_utils/kp.py", line 623, in forward
group_loss += self.group_loss(group_preds[b_ind], group_targets_trim[b_ind])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (87) to match target batch_size (64).

0%| | 1/100000 [00:04<122:40:59, 4.42s/it]Traceback (most recent call last):
File "/home/dmind/workspace/ChartReader/ChartReader/train_extraction.py", line 144, in train
training_loss = nnet.train_step(*training_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 50, in train_step
loss = self(xs, ys)
^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 44, in forward
loss = self.loss_function(preds, ys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/models/py_utils/kp.py", line 623, in forward
group_loss += self.group_loss(group_preds[b_ind], group_targets_trim[b_ind])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (88) to match target batch_size (52).

0%| | 2/100000 [00:04<53:39:36, 1.93s/it] Traceback (most recent call last):
File "/home/dmind/workspace/ChartReader/ChartReader/train_extraction.py", line 144, in train
training_loss = nnet.train_step(*training_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 50, in train_step
loss = self(xs, ys)
^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 44, in forward
loss = self.loss_function(preds, ys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/models/py_utils/kp.py", line 623, in forward
group_loss += self.group_loss(group_preds[b_ind], group_targets_trim[b_ind])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (828) to match target batch_size (60).

0%| | 3/100000 [00:04<31:42:12, 1.14s/it]Traceback (most recent call last):
File "/home/dmind/workspace/ChartReader/ChartReader/train_extraction.py", line 144, in train
training_loss = nnet.train_step(*training_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 50, in train_step
loss = self(xs, ys)
^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 44, in forward
loss = self.loss_function(preds, ys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/models/py_utils/kp.py", line 623, in forward
group_loss += self.group_loss(group_preds[b_ind], group_targets_trim[b_ind])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (112) to match target batch_size (48).

0%| | 4/100000 [00:04<21:15:02, 1.31it/s]Traceback (most recent call last):
File "/home/dmind/workspace/ChartReader/ChartReader/train_extraction.py", line 144, in train
training_loss = nnet.train_step(*training_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 50, in train_step
loss = self(xs, ys)
^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 44, in forward
loss = self.loss_function(preds, ys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/models/py_utils/kp.py", line 623, in forward
group_loss += self.group_loss(group_preds[b_ind], group_targets_trim[b_ind])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (1536) to match target batch_size (768).

0%| | 5/100000 [00:05<15:32:47, 1.79it/s]Traceback (most recent call last):
File "/home/dmind/workspace/ChartReader/ChartReader/train_extraction.py", line 144, in train
training_loss = nnet.train_step(*training_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 50, in train_step
loss = self(xs, ys)
^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 44, in forward
loss = self.loss_function(preds, ys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/models/py_utils/kp.py", line 623, in forward
group_loss += self.group_loss(group_preds[b_ind], group_targets_trim[b_ind])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (1255) to match target batch_size (231).

0%| | 6/100000 [00:05<12:07:42, 2.29it/s]Traceback (most recent call last):
File "/home/dmind/workspace/ChartReader/ChartReader/train_extraction.py", line 144, in train
training_loss = nnet.train_step(*training_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 50, in train_step
loss = self(xs, ys)
^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 44, in forward
loss = self.loss_function(preds, ys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/models/py_utils/kp.py", line 623, in forward
group_loss += self.group_loss(group_preds[b_ind], group_targets_trim[b_ind])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (1536) to match target batch_size (768).

0%| | 7/100000 [00:05<10:01:52, 2.77it/s]Traceback (most recent call last):
File "/home/dmind/workspace/ChartReader/ChartReader/train_extraction.py", line 144, in train
training_loss = nnet.train_step(*training_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 50, in train_step
loss = self(xs, ys)
^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 44, in forward
loss = self.loss_function(preds, ys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/models/py_utils/kp.py", line 623, in forward
group_loss += self.group_loss(group_preds[b_ind], group_targets_trim[b_ind])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (250) to match target batch_size (64).

0%| | 8/100000 [00:05<8:40:40, 3.20it/s] Traceback (most recent call last):
File "/home/dmind/workspace/ChartReader/ChartReader/train_extraction.py", line 144, in train
training_loss = nnet.train_step(*training_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 50, in train_step
loss = self(xs, ys)
^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 44, in forward
loss = self.loss_function(preds, ys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/models/py_utils/kp.py", line 623, in forward
group_loss += self.group_loss(group_preds[b_ind], group_targets_trim[b_ind])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (337) to match target batch_size (13).

0%| | 9/100000 [00:05<7:36:12, 3.65it/s]Traceback (most recent call last):
File "/home/dmind/workspace/ChartReader/ChartReader/train_extraction.py", line 144, in train
training_loss = nnet.train_step(*training_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 50, in train_step
loss = self(xs, ys)
^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 44, in forward
loss = self.loss_function(preds, ys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/models/py_utils/kp.py", line 623, in forward
group_loss += self.group_loss(group_preds[b_ind], group_targets_trim[b_ind])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (832) to match target batch_size (64).

0%| | 10/100000 [00:06<7:06:05, 3.91it/s]Traceback (most recent call last):
File "/home/dmind/workspace/ChartReader/ChartReader/train_extraction.py", line 144, in train
training_loss = nnet.train_step(*training_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 50, in train_step
loss = self(xs, ys)
^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/model_factory.py", line 44, in forward
loss = self.loss_function(preds, ys, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/workspace/ChartReader/ChartReader/models/py_utils/kp.py", line 623, in forward
group_loss += self.group_loss(group_preds[b_ind], group_targets_trim[b_ind])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dmind/.conda/envs/chart_reader/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (232) to match target batch_size (36).

0%| | 10/100000 [00:07<20:33:31, 1.35it/s]
wandb: Waiting for W&B process to finish... (success).
wandb: Network error (TransientError), entering retry loop.
wandb: Network error (TransientError), entering retry loop.

from chartreader.