I am trying to solve one multilabel problem with 270 labels and i have converted target labels into one hot encoded form. I am using BCEWithLogitsLoss(). Since training data is unbalanced, I am using pos_weight argument but i am bit confused.
pos_weight (Tensor, optional) – a weight of positive examples. Must be a vector with length equal to the number of classes.
Do i need to give total count of positive values of each label as a tensor or they mean something else by weights?
The PyTorch documentation for BCEWithLogitsLoss recommends the pos_weight to be a ratio between the negative counts and the positive counts for each class.
So, if len(dataset) is 1000, element 0 of your multihot encoding has 100 positive counts, then element 0 of the pos_weights_vector should be 900/100 = 9. That means that the binary crossent loss will behave as if the dataset contains 900 positive examples instead of 100.
Here is my implementation:
(new, based on this post)
pos_weight = (y==0.).sum()/y.sum()
(original)
def calculate_pos_weights(class_counts):
pos_weights = np.ones_like(class_counts)
neg_counts = [len(data)-pos_count for pos_count in class_counts]
for cdx, pos_count, neg_count in enumerate(zip(class_counts, neg_counts)):
pos_weights[cdx] = neg_count / (pos_count + 1e-5)
return torch.as_tensor(pos_weights, dtype=torch.float)
Where class_counts is just a column-wise sum of the positive samples. I posted it on the PyTorch forum and one of the PyTorch devs gave it his blessing.
Maybe is a little late, but here is how I calculate the same. Looking into the documentation:
For example, if a dataset contains 100 positive and 300 negative examples of a single class, then pos_weight for the class should be equal to 300/100 = 3.
So an easy way to calcule the positive weight is using the tensor methods with your label vector "y", in my case train_dataset.data.y. And then calculating the total negative labels.
num_positives = torch.sum(train_dataset.data.y, dim=0)
num_negatives = len(train_dataset.data.y) - num_positives
pos_weight = num_negatives / num_positives
Then the weights can be used easily as:
criterion = torch.nn.BCEWithLogitsLoss(pos_weight = pos_weight)
PyTorch solution
Well, actually I have gone through docs and you can simply use pos_weight indeed.
This argument gives weight to positive sample for each class, hence if you have 270 classes you should pass torch.Tensor with shape (270,) defining weight for each class.
Here is marginally modified snippet from documentation:
# 270 classes, batch size = 64
target = torch.ones([64, 270], dtype=torch.float32)
# Logits outputted from your network, no activation
output = torch.full([64, 270], 0.9)
# Weights, each being equal to one. You can input your own here.
pos_weight = torch.ones([270])
criterion = torch.nn.BCEWithLogitsLoss(pos_weight=pos_weight)
criterion(output, target) # -log(sigmoid(0.9))
Self-made solution
When it comes to weighting, there is no built-in solution, but you may code one yourself really easily:
import torch
class WeightedMultilabel(torch.nn.Module):
def __init__(self, weights: torch.Tensor):
self.loss = torch.nn.BCEWithLogitsLoss()
self.weights = weights.unsqueeze()
def forward(outputs, targets):
return self.loss(outputs, targets) * self.weights
Tensor has to be of the same length as the number of classes in your multilabel classification (270), each giving weight for your specific example.
Calculating weights
You just add labels of every sample in your dataset, divide by the minimum value and inverse at the end.
Sort of snippet:
weights = torch.zeros_like(dataset[0])
for element in dataset:
weights += element
weights = 1 / (weights / torch.min(weights))
Using this approach class occurring the least will give normal loss, while others will have weights smaller than 1.
It might cause some instability during training though, so you might want to experiment with those values a little (maybe log transform instead of linear?)
Other approach
You may think about upsampling/downsampling (though this operation is complicated as you would add/delete other classes as well, so advanced heuristics would be needed I think).
Just to provide a quick revision on #crypdick's answer, this implementation of the function worked for me:
def calculate_pos_weights(class_counts,data):
pos_weights = np.ones_like(class_counts)
neg_counts = [len(data)-pos_count for pos_count in class_counts]
for cdx, (pos_count, neg_count) in enumerate(zip(class_counts, neg_counts)):
pos_weights[cdx] = neg_count / (pos_count + 1e-5)
return torch.as_tensor(pos_weights, dtype=torch.float)
Where data is the dataset you're trying to apply weights to.
Related
I have a single-label, multi-class classification problem, i.e., a given sample is in exactly one class (say, class 3), but for training purposes, predicting class 2 or 5 is still okay to not penalise the model that heavily.
For example, the ground truth for 1 sample is [0,1,1,0,1] of 5 classes, instead of a one-hot vector. This implies that, the model predicting any one (not necessarily all) of the above classes (2,3 or 5) is fine.
For every batch, the predicted output dimension is of the shape bs x n x nc, where bs is the batch size, n is the number of samples per point and nc is the number of classes. The ground truth is also of the same shape as the predicted tensor.
For every batch, I'm expecting my loss function to compare n tensors across nc classes and then average it across n.
Eg: When dimensions are 32 x 8 x 5000. There are 32 batch points in a batch (for bs=32). Each batch point has 8 vector points, and each vector point has 5000 classes. For a given batch point, I wish to compute loss across all (8) vector points, compute their average and do so for the rest of the batch points (32). Final loss would be loss over all losses from each batch point.
How can I approach designing such a loss function? Any help would be deeply appreciated
P.S.: Let me know if the question is ambiguous
One way to go about this was to use a sigmoid function on the network output, which removes the implicit interdependency between class scores that a softmax function has.
As for the loss function, you can then calculate the loss based on the highest prediction for any of your target classes and ignore all other class predictions. For your example:
# your model output
y_out = torch.tensor([[0.1, 0.2, 0.95, 0.1, 0.01]], requires_grad=True)
# class labels
y = torch.tensor([[0,1,1,0,1]])
since we only care about the highest class probability, we set all other class scores to the maximum value achieved for one of the classes:
class_mask = y == 1
max_class_score = torch.max(y_out[class_mask])
y_hat = torch.where(class_mask, max_class_score, y_out)
From which we can use a regular Cross-Entropy loss function
loss_fn = torch.nn.CrossEntropyLoss()
loss = loss_fn(y_hat, y.float())
loss.backward()
when inspecting the gradients, we see that this only updates the prediction that achieved the highest score as well ass all predictions outside of any of the classes.
>>> y_out.grad
tensor([[ 0.3326, 0.0000, -0.6653, 0.3326, 0.0000]])
Predictions for other target classes do not receive a gradient update. Note that if you have a very high ratio of possible classes, this might slow down your convergence.
I am training a PyTorch model to perform binary classification. My minority class makes up about 10% of the data, so I want to use a weighted loss function. The docs for BCELoss and CrossEntropyLoss say that I can use a 'weight' for each sample.
However, when I declare CE_loss = nn.BCELoss() or nn.CrossEntropyLoss() and then do CE_Loss(output, target, weight=batch_weights), where output, target, and batch_weights are Tensors of batch_size, I get the following error message:
forward() got an unexpected keyword argument 'weight'
Another way you could accomplish your goal is to use reduction=none when initializing the loss and then multiply the resulting tensor by your weights before computing the mean.
e.g.
loss = torch.nn.BCELoss(reduction='none')
model = torch.sigmoid
weights = torch.rand(10,1)
inputs = torch.rand(10,1)
targets = torch.rand(10,1)
intermediate_losses = loss(model(inputs), targets)
final_loss = torch.mean(weights*intermediate_losses)
Of course for your scenario you still would need to calculate the weights tensor. But hopefully this helps!
Could it be that you want to apply separate fixed weights to all elements of class 0 and class 1 in your dataset? It is not clear what value you are passing for batch_weights here. If so, then that is not what the weight parameter in BCELoss does. The weight parameter expects you to pass a separate weight for every ELEMENT in the dataset, not for every CLASS. There are several ways around this. You could construct a weight table for every element. Alternatively, you could use a custom loss function that does what you want:
def BCELoss_class_weighted(weights):
def loss(input, target):
input = torch.clamp(input,min=1e-7,max=1-1e-7)
bce = - weights[1] * target * torch.log(input) - (1 - target) * weights[0] * torch.log(1 - input)
return torch.mean(bce)
return loss
Note that it is important to add a clamp to avoid numerical instability.
HTH Jeroen
the issue is wherein your providing the weight parameter. As it is mentioned in the docs, here, the weights parameter should be provided during module instantiation.
For example, something like,
from torch import nn
weights = torch.FloatTensor([2.0, 1.2])
loss = nn.BCELoss(weights=weights)
You can find a more concrete example here or another helpful PT forum discussion here.
you need to pass weights like below:
CE_loss = CrossEntropyLoss(weight=[…])
This is similar to the idea of #Jeroen Vuurens, but the class weights are determined by the target mean:
y_train_mean = y_train.mean()
bi_cls_w2 = 1/(1 - y_train_mean)
bi_cls_w1 = 1/y_train_mean - bi_cls_w2
bce_loss = nn.BCELoss(reduction='none')
loss_fun = lambda pred, target: ((bi_cls_w1*target + bi_cls_w2) * bce_loss(pred, target)).mean()
I have a task in which I input a 500x500x1 image and get out a 500x500x1 binary segmentation. When working, only a small fraction of the 500x500 should be triggered (small "targets"). I'm using a sigmoid activation at the output. Since such a small fraction is desired to be positive, the training tends to stall with all outputs at zero, or very close. I've written my own loss function that partially deals with it, but I'd like to use binary cross entropy with a class weighting if possible.
My question is in two parts:
If I naively apply binary_crossentropy as the loss to my 500x500x1 output, will it apply on a per pixel basis as desired?
Is there a way for keras to apply class weighting with the single sigmoid output per pixel?
To answer your questions.
Yes, binary_cross_entropy will work per-pixel based, provided you feed to your image segmentation neural network pairs of the form (500x500x1 image(grayscale image) + 500x500x1 (corresponding mask to your image).
By feeding the parameter 'class_weight' parameter in model.fit()
Suppose you have 2 classes with 90%-10% distribution. Then you may want to penalise your algorithm 9 times more when it makes a mistake for the less well represented class(the class with 10% in this case). Suppose you have 900 examples of class 1 and 100 examples of class 2.
Then your class weights dictionary(there are multiple ways to compute it, what is important is to assign a greater weight to the less well represented class),
class_weights = {0:1000/900,1:1000/100}
Example : model.fit(X_train, Y_train, epochs = 30, batch_size=32, class_weight=class_weight)
NOTE: This is available only on 2d cases(class_weight). For 3D or higher dimensional spaces, one should use 'sample_weights'. For segmentation purposes, you would rather use sample_weights parameter.
The biggest gain you will have is by means of other loss functions. Other losses, apart from binary_crossentropy and categorical_crossentropy, inherently perform better on unbalanced datasets. Dice Loss is such a loss function.
Keras implementation:
smooth = 1.
def dice_coef(y_true, y_pred):
y_true_f = K.flatten(y_true)
y_pred_f = K.flatten(y_pred)
intersection = K.sum(y_true_f * y_pred_f)
return (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)
def dice_coef_loss(y_true, y_pred):
return 1 - dice_coef(y_true, y_pred)
You can also use as a loss function the sum of binary_crossentropy
and other losses if it suits you : i.e. loss = dice_loss + bce
I have a 1000 classes in the network and they have multi-label outputs. For each training example, the number of positive output is same(i.e 10) but they can be assigned to any of the 1000 classes. So 10 classes have output 1 and rest 990 have output 0.
For the multi-label classification, I am using 'binary-cross entropy' as cost function and 'sigmoid' as the activation function. When I tried this rule of 0.5 as the cut-off for 1 or 0. All of them were 0. I understand this is a class imbalance problem. From this link, I understand that, I might have to create extra output labels.Unfortunately, I haven't been able to figure out how to incorporate that into a simple neural network in keras.
nclasses = 1000
# if we wanted to maximize an imbalance problem!
#class_weight = {k: len(Y_train)/(nclasses*(Y_train==k).sum()) for k in range(nclasses)}
inp = Input(shape=[X_train.shape[1]])
x = Dense(5000, activation='relu')(inp)
x = Dense(4000, activation='relu')(x)
x = Dense(3000, activation='relu')(x)
x = Dense(2000, activation='relu')(x)
x = Dense(nclasses, activation='sigmoid')(x)
model = Model(inputs=[inp], outputs=[x])
adam=keras.optimizers.adam(lr=0.00001)
model.compile('adam', 'binary_crossentropy')
history = model.fit(
X_train, Y_train, batch_size=32, epochs=50,verbose=0,shuffle=False)
Could anyone help me with the code here and I would also highly appreciate if you could suggest a good 'accuracy' metric for this problem?
Thanks a lot :) :)
I have a similar problem and unfortunately have no answer for most of the questions. Especially the class imbalance problem.
In terms of metric there are several possibilities: In my case I use the top 1/2/3/4/5 results and check if one of them is right. Because in your case you always have the same amount of labels=1 you could take your top 10 results and see how many percent of them are right and average this result over your batch size. I didn't find a possibility to include this algorithm as a keras metric. Instead, I wrote a callback, which calculates the metric on epoch end on my validation data set.
Also, if you predict the top n results on a test dataset, see how many times each class is predicted. The Counter Class is really convenient for this purpose.
Edit: If found a method to include class weights without splitting the output.
You need a numpy 2d array containing weights with shape [number classes to predict, 2 (background and signal)].
Such an array could be calculated with this function:
def calculating_class_weights(y_true):
from sklearn.utils.class_weight import compute_class_weight
number_dim = np.shape(y_true)[1]
weights = np.empty([number_dim, 2])
for i in range(number_dim):
weights[i] = compute_class_weight('balanced', [0.,1.], y_true[:, i])
return weights
The solution is now to build your own binary crossentropy loss function in which you multiply your weights yourself:
def get_weighted_loss(weights):
def weighted_loss(y_true, y_pred):
return K.mean((weights[:,0]**(1-y_true))*(weights[:,1]**(y_true))*K.binary_crossentropy(y_true, y_pred), axis=-1)
return weighted_loss
weights[:,0] is an array with all the background weights and weights[:,1] contains all the signal weights.
All that is left is to include this loss into the compile function:
model.compile(optimizer=Adam(), loss=get_weighted_loss(class_weights))
I have built a Keras model for image segmentation (U-Net). However in my samples some misclassifications (areas) are not that important, while other are crucial, so I want to assign higher weight in loss function to them. To complicate things further, I would like some misclassifications (class 1 instead of 2) to have very high penalty while inverse (class 2 instead of 1) shouldn't be penalized that much.
The way I see it, I need to use a sum (across all of the pixels) of weighted categorical crossentropy, but the best I could find is this:
def w_categorical_crossentropy(y_true, y_pred, weights):
nb_cl = len(weights)
final_mask = K.zeros_like(y_pred[:, 0])
y_pred_max = K.max(y_pred, axis=1)
y_pred_max = K.reshape(y_pred_max, (K.shape(y_pred)[0], 1))
y_pred_max_mat = K.cast(K.equal(y_pred, y_pred_max), K.floatx())
for c_p, c_t in product(range(nb_cl), range(nb_cl)):
final_mask += (weights[c_t, c_p] * y_pred_max_mat[:, c_p] * y_true[:, c_t])
return K.categorical_crossentropy(y_pred, y_true) * final_mask
However this code only works with a single prediction and my knowledge of Keras inner workings is lacking (and math side of it is not much better). Anyone know how I can adapt it, or even better, is there a ready-made loss function which would suit my case?
I would appreciate some pointers.
EDIT: my question is similar to How to do point-wise categorical crossentropy loss in Keras?, except that I would like to use weighted categorical crossentropy.
You can use weight maps (as proposed in the U-Net paper). In those weight maps, you can weight regions with more weight or less weight. Here is some pseudocode:
loss = compute_categorical_crossentropy()
weighted_loss = loss * weight_map # using element-wise multiplication