I am doing a multivariate forecasting using the Rossmann dataset. I now need to use the RMSPE metric to evaluate my model. I saw the relevant formula here. But I am not sure how to efficiently implement this using numpy. Any help is much appreciated.
You can take advantage of numpy's vectorisation capability for an error metric like this. The following function can be used to compute RMSPE:
def rmse(y_true, y_pred):
'''
Compute Root Mean Square Percentage Error between two arrays.
'''
loss = np.sqrt(np.mean(np.square(((y_true - y_pred) / y_true)), axis=0))
return loss
(For the error between vectors, axis=0 makes it explicit that the error is computed row-wise, returning a vector. It isn't required, as this is the default behaviour for np.mean.)
It should be normalized by ground truths.
RMSPE equation
def rmspe(y_true, y_pred):
return np.sqrt(np.nanmean(np.square(((y_true - y_pred) / y_true))))*100
Related
I try to write a cross entropy loss function by myself. My loss function gives the same loss value as the official one, but when i use my loss function in the code instead of official cross entropy loss function, the code does not converge. When i use the official cross entropy loss function, the code converges. Here is my code, please give me some suggestions. Thanks very much
The input 'out' is a tensor (B*C) and 'label' contains class indices (1 * B)
class MylossFunc(nn.Module):
def __init__(self):
super(MylossFunc, self).__init__()
def forward(self, out, label):
out = torch.nn.functional.softmax(out, dim=1)
n = len(label)
loss = torch.FloatTensor([0])
loss = Variable(loss, requires_grad=True)
tmp = torch.log(out)
#print(out)
torch.scalar_tensor(-100)
for i in range(n):
loss = loss - torch.max(tmp[i][label[i]], torch.scalar_tensor(-100) )/n
loss = torch.sum(loss)
return loss
Instead of using torch.softmax and torch.log, you should use torch.log_softmax, otherwise your training will become unstable with nan values everywhere.
This happens because when you take the softmax of your logits using the following line:
out = torch.nn.functional.softmax(out, dim=1)
you might get a zero in one of the components of out, and when you follow that by applying torch.log it will result in nan (since log(0) is undefined). That is why torch (and other common libraries) provide a single stable operation, log_softmax, to avoid the numerical instabilities that occur when you use torch.softmax and torch.log individually.
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 am trying to define a loss function in Keras
def rmseApprox(y_true, y_pred):
dum = y_pred
dum[y_pred>=0]=1.1
dum[y_pred<0]=1
return k.abs(K.mean(y_true - dum*y_pred), axis=-1)
which increase the positive values by a factor of 1.1 and the compare it with the true values. I got the following error:
TypeError: 'Tensor' object does not support item assignment
The loss function is a tensor and part of the computational graph. It therefore must be defined using the keras backend, and doesn't behave like a "regular" numpy array.
This example should work for you:
def rmseApprox(y_true, y_pred):
y_pred_corrected = y_pred*(1.05 + K.sign(y_pred)*0.05)
return K.abs(K.mean(y_true - y_pred_corrected, axis=-1))
Please note that in the above code, the weight for the case y_pred==0 will be 1.05.
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
I am trying to use a custom scoring function that calculates multi-class log loss with the ground truth and predict_proba y array. Is there a way to make GridSearchCV use this scoring function?
def multiclass_log_loss(y_true, y_pred):
Parameters
----------
y_true : array, shape = [n_samples]
true class, intergers in [0, n_classes - 1)
y_pred : array, shape = [n_samples, n_classes]
Returns
-------
loss : float
"""
eps=1e-15
predictions = np.clip(y_pred, eps, 1 - eps)
# normalize row sums to 1
predictions /= predictions.sum(axis=1)[:, np.newaxis]
actual = np.zeros(y_pred.shape)
n_samples = actual.shape[0]
actual[np.arange(n_samples), y_true.astype(int)] = 1
vectsum = np.sum(actual * np.log(predictions))
loss = -1.0 / n_samples * vectsum
return loss
I see that there are multiple options, score_func, loss_func and make_scorer. I tried using make_scorer with greater_is_better=False and also tried the loss_func parameter but it seems to still use the .predict method. How can I get around this problem?
UPDATE - if I set needs_threshold=True I get a multi-class error. Am I correct to understand multi-class is not supported in this case? If yes, can someone suggest a workaround?
Thanks.
The top answer to this question:
Pass estimator to custom score function via sklearn.metrics.make_scorer
might have what you need. One can define a scorer that takes as arguments a classifier clf, feature array X, and targets y_true, and feed the result of the clf.predict_proba() method to a scoring function that returns the error. As a hint, for binary classification, you probably need to use
clf.predict_proba(X)[:,1]
This worked for my needs (a normalized Gini score). For some reason, I couldn't get sklearn's metrics.make_scorer to work with my custom function that needs probabilities.