I'm trying to run a classifier on Chainer, but failed due to the following error.
I have no idea about the error, because I confirmed that the iterator actually sent a batch to the trainer.
Is there a problem with the neural network model? Or, the way the data has been fed into the model is wrong?
Input.py
from chainer.datasets import split_dataset_random
from chainer.iterators import SerialIterator
from chainer.optimizers import Adam
from chainer.training import Trainer
from chainer.training.updaters import StandardUpdater
from chainer import functions as F, links as L
from chainer import Sequential
import numpy as np
batch_size = 3
X_train = np.ones((9957, 60, 80, 3), dtype=np.float32)
X_train, _ = split_dataset_random(X_train, 8000, seed=0)
train_iter = SerialIterator(X_train, batch_size)
model = Sequential(
L.Convolution2D(None, 64, 3, 2),
F.relu,
L.Convolution2D(64, 32, 3, 2),
F.relu,
L.Linear(None, 16),
F.dropout,
L.Linear(16, 4)
)
model_loss = L.Classifier(model)
optimizer = Adam()
optimizer.setup(model_loss)
updater = StandardUpdater(train_iter, optimizer)
trainer = Trainer(updater, (25, 'epoch'))
trainer.run()
Stacktrace.py
Exception in main training loop: forward() missing 1 required positional argument: 'x'
Traceback (most recent call last):
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/training/trainer.py", line 315, in run
update()
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/training/updaters/standard_updater.py", line 165, in update
self.update_core()
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/training/updaters/standard_updater.py", line 181, in update_core
optimizer.update(loss_func, in_arrays)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/optimizer.py", line 680, in update
loss = lossfun(*args, **kwds)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/link.py", line 242, in __call__
out = forward(*args, **kwargs)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/links/model/classifier.py", line 143, in forward
self.y = self.predictor(*args, **kwargs)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/link.py", line 242, in __call__
out = forward(*args, **kwargs)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/sequential.py", line 210, in forward
x = layer(*x)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/link.py", line 242, in __call__
out = forward(*args, **kwargs)
Will finalize trainer extensions and updater before reraising the exception.
Traceback (most recent call last):
File "/home/user/deploy/aaa.py", line 33, in <module>
trainer.run()
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/training/trainer.py", line 348, in run
six.reraise(*exc_info)
File "/home/user/miniconda3/lib/python3.7/site-packages/six.py", line 693, in reraise
raise value
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/training/trainer.py", line 315, in run
update()
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/training/updaters/standard_updater.py", line 165, in update
self.update_core()
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/training/updaters/standard_updater.py", line 181, in update_core
optimizer.update(loss_func, in_arrays)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/optimizer.py", line 680, in update
loss = lossfun(*args, **kwds)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/link.py", line 242, in __call__
out = forward(*args, **kwargs)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/links/model/classifier.py", line 143, in forward
self.y = self.predictor(*args, **kwargs)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/link.py", line 242, in __call__
out = forward(*args, **kwargs)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/sequential.py", line 210, in forward
x = layer(*x)
File "/home/user/miniconda3/lib/python3.7/site-packages/chainer/link.py", line 242, in __call__
out = forward(*args, **kwargs)
TypeError: forward() missing 1 required positional argument: 'x'
Is there a problem with the neural network model or the way the data has been fed into the model? Please let me know if you need to see the whole code
All you had to do is to give a tuple of ndarray and int to the model, because this is the specification of L.Classifier.
Is there a problem with the neural network model? Or, the way the data has been fed into the model is wrong?
Therefore, the absolute answer is "the way the data has been fed in to the model is wrong".
In the following code, I defined a class inheriting DatasetMixin to feed a tuple of ndarray and int. (This is a conventional way how Chainer goes)
It should be noted that the input argument of L.Convolution2D must be an ndarray whose shape is (batch, channel, width, height). So I transpose the array in the dataset.
Solution.py
from chainer.datasets import split_dataset_random
from chainer.iterators import SerialIterator
from chainer.optimizers import Adam
from chainer.training import Trainer
from chainer.training.updaters import StandardUpdater
from chainer import functions as F, links as L
from chainer import Sequential
from chainer.dataset import DatasetMixin
import numpy as np
class MyDataset(DatasetMixin):
def __init__(self, X, labels):
super(MyDataset, self).__init__()
self.X_ = X
self.labels_ = labels
self.size_ = X.shape[0]
def __len__(self):
return self.size_
def get_example(self, i):
return np.transpose(self.X_[i, ...], (2, 0, 1)), self.labels_[i]
batch_size = 3
X_train = np.ones((9957, 60, 80, 3), dtype=np.float32)
label_train = np.random.randint(0, 4, (9957,), dtype=np.int32)
dataset = MyDataset(X_train, label_train)
dataset_train, _ = split_dataset_random(dataset, 8000, seed=0)
train_iter = SerialIterator(dataset_train, batch_size)
model = Sequential(
L.Convolution2D(None, 64, 3, 2),
F.relu,
L.Convolution2D(64, 32, 3, 2),
F.relu,
L.Linear(None, 16),
F.dropout,
L.Linear(16, 4)
)
model_loss = L.Classifier(model)
optimizer = Adam()
optimizer.setup(model_loss)
updater = StandardUpdater(train_iter, optimizer)
trainer = Trainer(updater, (25, 'epoch'))
trainer.run()