Related
C:\Users\Viktor\miniconda3\lib\site-packages\torch\utils\data_utils\collate.py:172: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at C:\cb\pytorch_1000000000000\work\torch\csrc\utils\tensor_numpy.cpp:205.)
return collate([torch.as_tensor(b) for b in batch], collate_fn_map=collate_fn_map)
C:\Users\Viktor\miniconda3\lib\site-packages\torch\utils\data_utils\collate.py:172: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at C:\cb\pytorch_1000000000000\work\torch\csrc\utils\tensor_numpy.cpp:205.)
return collate([torch.as_tensor(b) for b in batch], collate_fn_map=collate_fn_map)
C:\Users\Viktor\miniconda3\lib\site-packages\torch\utils\data_utils\collate.py:172: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at C:\cb\pytorch_1000000000000\work\torch\csrc\utils\tensor_numpy.cpp:205.)
return collate([torch.as_tensor(b) for b in batch], collate_fn_map=collate_fn_map)
C:\Users\Viktor\miniconda3\lib\site-packages\torch\utils\data_utils\collate.py:172: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at C:\cb\pytorch_1000000000000\work\torch\csrc\utils\tensor_numpy.cpp:205.)
return collate([torch.as_tensor(b) for b in batch], collate_fn_map=collate_fn_map)
the indiex is : 0 rest is: torch.Size([64, 240, 320, 3]) torch.Size([64, 240, 320, 3])
Traceback (most recent call last):
File "c:\Users\Viktor\Desktop\Infrarens.py", line 174, in
outputs = model(inputs)
File "C:\Users\Viktor\miniconda3\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
return forward_call(*input, **kwargs)
File "c:\Users\Viktor\Desktop\Infrarens.py", line 135, in forward
x = self.encoder(x)
File "C:\Users\Viktor\miniconda3\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Viktor\miniconda3\lib\site-packages\torch\nn\modules\container.py", line 204, in forward
input = module(input)
File "C:\Users\Viktor\miniconda3\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Viktor\miniconda3\lib\site-packages\torch\nn\modules\conv.py", line 463, in forward
return self._conv_forward(input, self.weight, self.bias)
File "C:\Users\Viktor\miniconda3\lib\site-packages\torch\nn\modules\conv.py", line 459, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Given groups=1, weight of size [64, 1, 3, 3], expected input[64, 240, 320, 3] to have 1 channels, but got 240 channels instead
Im trying to train a Unet on a image set, I don't know how to interprate this output
Is there any way in Keras to specify a loss function which does not need to be passed target data?
I attempted to specify a loss function which omitted the y_true parameter like so:
def custom_loss(y_pred):
But I got the following error:
Traceback (most recent call last):
File "siamese.py", line 234, in <module>
model.compile(loss=custom_loss,optimizer=Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0))
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 911, in compile
sample_weight, mask)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 436, in weighted
score_array = fn(y_true, y_pred)
TypeError: custom_loss() takes exactly 1 argument (2 given)
I then tried to call fit() without specifying any target data:
model.fit(x=[x_train,x_train_warped, affines], batch_size = bs, epochs=1)
But it looks like not passing any target data causes an error:
Traceback (most recent call last):
File "siamese.py", line 264, in <module>
model.fit(x=[x_train,x_train_warped, affines], batch_size = bs, epochs=1)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1435, in fit
batch_size=batch_size)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1322, in _standardize_user_data
in zip(y, sample_weights, class_weights, self._feed_sample_weight_modes)]
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 577, in _standardize_weights
return np.ones((y.shape[0],), dtype=K.floatx())
AttributeError: 'NoneType' object has no attribute 'shape'
I could manually create dummy data in the same shape as my neural net's output but this seems extremely messy. Is there a simple way to specify an unsupervised loss function in Keras that I am missing?
I think the best solution is customizing the training instead of using the model.fit method.
The complete walkthrough is published in the Tensorflow tutorials page.
Write your loss function as if it had two arguments:
y_true
y_pred
If you don't have y_true, that's fine, you don't need to use it inside to compute the loss, but leave a placeholder in your function prototype, so keras wouldn't complain.
def custom_loss(y_true, y_pred):
# do things with y_pred
return loss
Adding custom arguments
You may also need to use another parameter like margin inside your loss function, even then your custom function should only take in those two arguments. But there is a workaround, use lambda functions
def custom_loss(y_pred, margin):
# do things with y_pred
return loss
but use it like
model.compile(loss=lambda y_true, y_pred: custom_loss(y_pred, margin), ...)
I am learning machine learning using Titanic dataset from Kaggle. I am using LabelEncoder of sklearn to transform text data to numeric labels. The following code works fine for "Sex" but not for "Embarked".
encoder = preprocessing.LabelEncoder()
features["Sex"] = encoder.fit_transform(features["Sex"])
features["Embarked"] = encoder.fit_transform(features["Embarked"])
This is the error I got
Traceback (most recent call last):
File "../src/script.py", line 20, in <module>
features["Embarked"] = encoder.fit_transform(features["Embarked"])
File "/opt/conda/lib/python3.6/site-packages/sklearn/preprocessing/label.py", line 131, in fit_transform
self.classes_, y = np.unique(y, return_inverse=True)
File "/opt/conda/lib/python3.6/site-packages/numpy/lib/arraysetops.py", line 211, in unique
perm = ar.argsort(kind='mergesort' if return_index else 'quicksort')
TypeError: '>' not supported between instances of 'str' and 'float'
I solved it myself. The problem was that the particular feature had NaN values. Replacing it with a numerical value it will still throw an error since it is of different datatypes. So I replaced it with a character value
features["Embarked"] = encoder.fit_transform(features["Embarked"].fillna('0'))
Try this function, you’ll need to pass a Pandas Dataframe. It will look at the type of your column and encode. So you won’t need to even bother checking the types yourself.
def encoder(data):
'''Map the categorical variables to numbers to work with scikit learn'''
for col in data.columns:
if data.dtypes[col] == "object":
le = preprocessing.LabelEncoder()
le.fit(data[col])
data[col] = le.transform(data[col])
return data
I have a csv dataset that I'm trying to use with sklearn. The goal is to predict future webtraffic. However, my dataset contains zeros on days that there were no visitors and I'd like to keep that value. There are more days with zero visitors then there are with visitors (it's a tiny tiny site). Here's a look at the data
Col1 is the date:
10/1/11
10/2/11
10/3/11
etc....
Col2 is the # of visitors:
12
1
0
0
1
5
0
0
etc....
sklearn seems to interpret the zero values as NaN values which is understandable. How can I use those zero values in a logistic function (is that even possible)?
Update:
The estimator is https://github.com/facebookincubator/prophet and when I run the following:
df = pd.read_csv('~/tmp/datafile.csv')
df['y'] = np.log(df['y'])
df.head()
m = Prophet()
m.fit(df);
future = m.make_future_dataframe(periods=365)
future.tail()
forecast = m.predict(future)
forecast[['ds', 'yhat', 'yhat_lower', 'yhat_upper']].tail()
m.plot(forecast);
m.plot_components(forecast);
plt.show
I get the following:
growthprediction.py:7: RuntimeWarning: divide by zero encountered in log
df['y'] = np.log(df['y'])
/usr/local/lib/python3.6/site-packages/fbprophet/forecaster.py:307: RuntimeWarning: invalid value encountered in double_scalars
k = (df['y_scaled'].ix[i1] - df['y_scaled'].ix[i0]) / T
Traceback (most recent call last):
File "growthprediction.py", line 11, in <module>
m.fit(df);
File "/usr/local/lib/python3.6/site-packages/fbprophet/forecaster.py", line 387, in fit
params = model.optimizing(dat, init=stan_init, iter=1e4)
File "/usr/local/lib/python3.6/site-packages/pystan/model.py", line 508, in optimizing
ret, sample = fit._call_sampler(stan_args)
File "stanfit4anon_model_35bf14a7f93814266f16b4cf48b40a5a_4758371668158283666.pyx", line 804, in stanfit4anon_model_35bf14a7f93814266f16b4cf48b40a5a_4758371668158283666.StanFit4Model._call_sampler (/var/folders/ym/m6j7kw0d3kj_0frscrtp58800000gn/T/tmp5wq7qltr/stanfit4anon_model_35bf14a7f93814266f16b4cf48b40a5a_4758371668158283666.cpp:16585)
File "stanfit4anon_model_35bf14a7f93814266f16b4cf48b40a5a_4758371668158283666.pyx", line 398, in stanfit4anon_model_35bf14a7f93814266f16b4cf48b40a5a_4758371668158283666._call_sampler (/var/folders/ym/m6j7kw0d3kj_0frscrtp58800000gn/T/tmp5wq7qltr/stanfit4anon_model_35bf14a7f93814266f16b4cf48b40a5a_4758371668158283666.cpp:8818)
RuntimeError: k initialized to invalid value (nan)
In this line of your code:
df['y'] = np.log(df['y'])
you are taking logarithm of 0 when your df['y'] is zero, which results in warnings and NaNs in your resulting dataset, because logarithm of 0 is not defined.
sklearn itself does NOT interpret zero values as NaNs unless you replace them with NaNs in your preprocessing.
I am using the keras functional API with input images of dimension (224, 224, 3). I have the following model using the functional API, although a similar problem seems to arise with sequential models:
input = Input(shape=(224, 224, 3,))
shared_layers = Dense(16)(input)
model = KerasModel(input=input, output=shared_layers)
model.compile(loss='binary_crossentropy', optimizer='sgd', metrics='accuracy'])
I am calling model.fit_generator where my generator has
yield ({'input_1': image}, {'output': classification})
image is the input (224, 224, 3) image and classification is in {-1,1}.
On fitting the model, I get an error
ValueError: No data provided for "dense_1". Need data for each key in: ['dense_1']
One strange thing is that if I switch the input_1 target of the dict to dense_1, the error switches to missing an input for input_1, but goes back to missing dense_1 if both keys are in the data generator.
This happens whether I call fit_generator or get batches from the generator and call train_on_batch.
Does anyone know what's going on? From what I can tell, this should be the same as given in the documentation although with a different input size.
Full traceback:
Traceback (most recent call last):
File "pymask.py", line 303, in <module>
main(sys.argv)
File "pymask.py", line 285, in main
keras.callbacks.ProgbarLogger()
File "/home/danielunderwood/virtualenvs/keras/lib/python3.6/site-packages/keras/engine/training.py", line 1557, in fit_generator
class_weight=class_weight)
File "/home/danielunderwood/virtualenvs/keras/lib/python3.6/site-packages/keras/engine/training.py", line 1314, in train_on_batch
check_batch_axis=True)
File "/home/danielunderwood/virtualenvs/keras/lib/python3.6/site-packages/keras/engine/training.py", line 1029, in _standardize_user_data
exception_prefix='model input')
File "/home/danielunderwood/virtualenvs/keras/lib/python3.6/site-packages/keras/engine/training.py", line 52, in standardize_input_data
str(names))
ValueError: No data provided for "input_1". Need data for each key in: ['input_1']
I encountered this error on 3 cases (In R):
The input data does not have the same dimension as was declared in the first layer
The input data includes missing values
The input data is not a matrix (for example, a data frame)
Please check all of the above.
Maybe this code in R can help:
library(keras)
#The network should identify the rule that a row sum greater than 1.5 should yield an output of 1
my_x=matrix(data=runif(30000), nrow=10000, ncol=3)
my_y=ifelse(rowSums(my_x)>1.5,1,0)
my_y=to_categorical(my_y, 2)
model = keras_model_sequential()
layer_dense(model,units = 2000, activation = "relu", input_shape = c(3))
layer_dropout(model,rate = 0.4)
layer_dense(model,units = 50, activation = "relu")
layer_dropout(model,rate = 0.3)
layer_dense(model,units = 2, activation = "softmax")
compile(model,loss = "categorical_crossentropy",optimizer = optimizer_rmsprop(),metrics = c("accuracy"))
history <- fit(model, my_x, my_y, epochs = 5, batch_size = 128, validation_split = 0.2)
evaluate(model,my_x, my_y,verbose = 0)
predict_classes(model,my_x)
I have encountered this issue as well and none of the above mentioned answers worked. According to the keras documentation you can pass the arguments either as a dictionary like that:
model.fit({'main_input': headline_data, 'aux_input': additional_data},
{'main_output': labels, 'aux_output': labels},
epochs=50, batch_size=32)
or as a list like that:
model.fit([headline_data, additional_data], [labels, labels],
epochs=50, batch_size=32)
The dictionary version didn't work for me with keras version 2.0.9. I have used the list version as a workaround for now.
This was due to me misunderstanding how the keras outputs work. The layer specified by the output argument to Model requires the output from the data. I misunderstood that the output key in the data dictionary automatically goes to the layer specified by the output argument.
yield ({'input_1': image}, {'output': classification})
Replace output with dense_1.
It will work.