I'm working on some demo data to build a binary classifier. There are 8 categorical variables (assume those 8 categorical variables were already integer-encoded) as well as 14 numerical variables.
I separated categorical inputs from numerical inputs, and create two parts of inputs: 8 categorical inputs first go to the embedding layer. The embedding layer will then be concatenated to the 14-dimensional numeric input layer.
Therefore, the actual (one record/ one row) / input of the whole model will be something like this:
[1,2,3,4,5,6,7,8, [1,2,3,4,…,14]]
And my model structure looks like this
cat_inputs = []
embeddings = []
for col in encoded_vars:
# find the cardinality of each categorical column:
cardinality = int(np.ceil(d[col].nunique() + 2))
# set the embedding dimension:
# at least 2, at most 50, otherwise cardinality//2
embedding_dim = max(min((cardinality)//2, 50),2)
print(cardinality, embedding_dim)
col_inputs = Input(shape=(1,))
# Specify the embedding
embedding = Embedding(cardinality, embedding_dim,
input_length=1, name=col+"_embed")(col_inputs)
# Add a but of dropout to the embedding layers to regularize:
embedding = SpatialDropout1D(0.1)(embedding)
# Flatten out the embeddings:
embedding = Reshape(target_shape=(embedding_dim,))(embedding)
# Add the input shape to inputs
cat_inputs.append(col_inputs)
# add the embeddings to the embeddings layer
embeddings.append(embedding)
num_inputs = Input(shape=(len(num_vars), ))
## Concatenate the cat_merged layer to the numerical input layer
x = Concatenate(axis = 1)(embeddings + [num_inputs])
## batch-norm layer
x = Dense(128, activation='relu')(x)
x = BatchNormalization()(x)
x = Dropout(0.3)(x)
x = Dense(64, activation='relu')(x)
outputs = Dense(1, activation = 'sigmoid')(x)
model = Model( [num_inputs] + cat_inputs, outputs)
model.summary()
The code was runnable and obtain desired result.
However, I was wondering if anyone can direct me how to save the model specs.
I tried this
model_inputs = [model.inputs[i].shape for i in range(len(model.inputs))]
full_model = full_model.get_concrete_function(x=tf.TensorSpec(model_inputs, model.inputs[0].dtype))
However, it gives me the error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-104-f29daca70586> in <module>
1 model_inputs = [model.inputs[i].shape for i in range(len(model.inputs))]
----> 2 full_model = full_model.get_concrete_function(x=tf.TensorSpec(model_inputs, model.inputs[0].dtype))
/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/tensorflow_core/python/framework/tensor_spec.py in __init__(self, shape, dtype, name)
52 not convertible to a `tf.DType`.
53 """
---> 54 self._shape = tensor_shape.TensorShape(shape)
55 try:
56 self._shape_tuple = tuple(self.shape.as_list())
/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/tensorflow_core/python/framework/tensor_shape.py in __init__(self, dims)
774 else:
775 # Got a list of dimensions
--> 776 self._dims = [as_dimension(d) for d in dims_iter]
777
778 #property
/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/tensorflow_core/python/framework/tensor_shape.py in <listcomp>(.0)
774 else:
775 # Got a list of dimensions
--> 776 self._dims = [as_dimension(d) for d in dims_iter]
777
778 #property
/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/tensorflow_core/python/framework/tensor_shape.py in as_dimension(value)
716 return value
717 else:
--> 718 return Dimension(value)
719
720
/opt/anaconda3/envs/tf2/lib/python3.7/site-packages/tensorflow_core/python/framework/tensor_shape.py in __init__(self, value)
191 raise TypeError("Cannot convert %s to Dimension" % value)
192 else:
--> 193 self._value = int(value)
194 if (not isinstance(value, compat.bytes_or_text_types) and
195 self._value != value):
TypeError: int() argument must be a string, a bytes-like object or a number, not 'TensorShape'
model_inputs
[TensorShape([None, 14]),
TensorShape([None, 1]),
TensorShape([None, 1]),
TensorShape([None, 1]),
TensorShape([None, 1]),
TensorShape([None, 1]),
TensorShape([None, 1]),
TensorShape([None, 1]),
TensorShape([None, 1])]
My understanding is that this is a multiple inputs case (with different input dimensional), and I'd greatly appreciate it if anyone can help.
Thank you!
Related
I'm having an issue getting Inception V3 to work as the feature extractor with a binary classifier in Pytorch. I update the primary and auxiliary nets in Inception to have the binary class (as done in https://pytorch.org/tutorials/beginner/finetuning_torchvision_models_tutorial.html)
but I'm getting an error
#Parameters for Inception V3
num_classes= 2
model_ft = models.inception_v3(pretrained=True)
# set_parameter_requires_grad(model_ft, feature_extract)
#handle auxilliary net
num_ftrs = model_ft.AuxLogits.fc.in_features
model_ft.AuxLogits.fc = nn.Linear(num_ftrs, num_classes)
#handle primary net
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs,num_classes)
# input_size = 299
#simulate data input
x = torch.rand([64, 3, 299, 299])
#create model with inception backbone
backbone = model_ft
num_filters = backbone.fc.in_features
layers = list(backbone.children())[:-1]
feature_extractor = nn.Sequential(*layers)
# use the pretrained model to classify damage 2 classes
num_target_classes = 2
classifier = nn.Linear(num_filters, num_target_classes)
feature_extractor.eval()
with torch.no_grad():
representations = feature_extractor(x).flatten(1)
x = classifier(representations)
But Im getting the error
RuntimeError Traceback (most recent call last)
<ipython-input-54-c2be64b8a99e> in <module>()
11 feature_extractor.eval()
12 with torch.no_grad():
---> 13 representations = feature_extractor(x)
14 x = classifier(representations)
9 frames
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight, bias)
442 _pair(0), self.dilation, self.groups)
443 return F.conv2d(input, weight, bias, self.stride,
--> 444 self.padding, self.dilation, self.groups)
445
446 def forward(self, input: Tensor) -> Tensor:
RuntimeError: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [64, 2]
before I updated the class to 2 (when it was 1000) I was getting the same error but with [64, 1000]. This method of creating a backbone and adding a classifier worked for Resnet but not here. I think it's because of the auxiliary net structure but not sure how to update it to deal with the dual output? Thanks
Inheriting feature_extracture by children function at line layers = list(backbone.children())[:-1] will bring the module from backbone to feature_extracture only, not the operation in forward function.
Let's take a look at the code below:
class Example(torch.nn.Module):
def __init__(self):
super().__init__()
self.avg = torch.nn.AdaptiveAvgPool2d((1,1))
self.linear = torch.nn.Linear(10, 1)
def forward(self, x):
out = self.avg(x)
out = out.squeeze()
out = self.linear(out)
return out
x = torch.randn(5, 10, 12, 12)
model = Example()
y = model(x) # work well
new_model = torch.nn.Sequential(*list(model.children()))
y = new_model(x) # error
Module model and new_model have the same blocks but not the same way of working. In new_module, the output from the pooling layer is not squeezed yet, so the shape of linear input is violate its assumption which causes the error.
In your case, the last two comments are redundant and that's why it returns the error, you did create a new fc in the InceptionV3 module at line model_ft.fc = nn.Linear(num_ftrs,num_classes). Therefore, replace the last one as the code below should work fine:
with torch.no_grad():
x = model_ft(x)
My goal is to build a multi-class image classifier using Pytorch and based on the EMNIST dataset (black and white pictures of letters).
The shape of my training data X_train is (124800, 28, 28).
The shape of the original target variables y_train is (124800, 1), however I created a one-hot encoding so that now the shape is (124800, 26).
The model that I am building should have 26 output variables, each representing the probability of one letter.
I read in my data as follows:
import scipy .io
emnist = scipy.io.loadmat(DATA_DIR + '/emnist-letters.mat')
data = emnist ['dataset']
X_train = data ['train'][0, 0]['images'][0, 0]
X_train = X_train.reshape((-1,28,28), order='F')
y_train = data ['train'][0, 0]['labels'][0, 0]
Then, I created a one-hot-encoding as follows:
y_train_one_hot = np.zeros([len(y_train), 27])
for i in range (0, len(y_train)):
y_train_one_hot[i, y_train[i][0]] = 1
y_train_one_hot = np.delete(y_train_one_hot, 0, 1)
I create the dataset with:
train_dataset = torch.utils.data.TensorDataset(torch.from_numpy(X_train), torch.from_numpy(y_train_one_hot))
batch_size = 128
n_iters = 3000
num_epochs = n_iters / (len(train_dataset) / batch_size)
num_epochs = int(num_epochs)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
And then I build my model as follows:
class CNNModel(nn.Module):
def __init__(self):
super(CNNModel, self).__init__()
# Convolution 1
self.cnn1 = nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=0)
self.relu1 = nn.ReLU()
# Max pool 1
self.maxpool1 = nn.MaxPool2d(2,2)
# Convolution 2
self.cnn2 = nn.Conv2d(in_channels=16, out_channels=32, kernel_size=5, stride=1, padding=0)
self.relu2 = nn.ReLU()
# Max pool 2
self.maxpool2 = nn.MaxPool2d(kernel_size=2)
# Fully connected 1 (readout)
self.fc1 = nn.Linear(32 * 4 * 4, 26)
def forward(self, x):
# Convolution 1
out = self.cnn1(x.float())
out = self.relu1(out)
# Max pool 1
out = self.maxpool1(out)
# Convolution 2
out = self.cnn2(out)
out = self.relu2(out)
# Max pool 2
out = self.maxpool2(out)
# Resize
# Original size: (100, 32, 7, 7)
# out.size(0): 100
# New out size: (100, 32*7*7)
out = out.view(out.size(0), -1)
# Linear function (readout)
out = self.fc1(out)
return out
model = CNNModel()
criterion = nn.CrossEntropyLoss()
learning_rate = 0.01
optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate)
And then I train the model as follows:
iter = 0
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
# Add a single channel dimension
# From: [batch_size, height, width]
# To: [batch_size, 1, height, width]
images = images.unsqueeze(1)
# Forward pass to get output/logits
outputs = model(images)
# Clear gradients w.r.t. parameters
optimizer.zero_grad()
# Forward pass to get output/logits
outputs = model(images)
# Calculate Loss: softmax --> cross entropy loss
loss = criterion(outputs, labels)
# Getting gradients w.r.t. parameters
loss.backward()
# Updating parameters
optimizer.step()
iter += 1
if iter % 500 == 0:
# Calculate Accuracy
correct = 0
total = 0
# Iterate through test dataset
for images, labels in test_loader:
images = images.unsqueeze(1)
# Forward pass only to get logits/output
outputs = model(images)
# Get predictions from the maximum value
_, predicted = torch.max(outputs.data, 1)
# Total number of labels
total += labels.size(0)
correct += (predicted == labels).sum()
accuracy = 100 * correct / total
# Print Loss
print('Iteration: {}. Loss: {}. Accuracy: {}'.format(iter, loss.data[0], accuracy))
However, when I run this, I get the following error:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-11-c26c43bbc32e> in <module>()
21
22 # Calculate Loss: softmax --> cross entropy loss
---> 23 loss = criterion(outputs, labels)
24
25 # Getting gradients w.r.t. parameters
3 frames
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
548 result = self._slow_forward(*input, **kwargs)
549 else:
--> 550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
552 hook_result = hook(self, input, result)
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/loss.py in forward(self, input, target)
930 def forward(self, input, target):
931 return F.cross_entropy(input, target, weight=self.weight,
--> 932 ignore_index=self.ignore_index, reduction=self.reduction)
933
934
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction)
2315 if size_average is not None or reduce is not None:
2316 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 2317 return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
2318
2319
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce, reduction)
2113 .format(input.size(0), target.size(0)))
2114 if dim == 2:
-> 2115 ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
2116 elif dim == 4:
2117 ret = torch._C._nn.nll_loss2d(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
RuntimeError: 1D target tensor expected, multi-target not supported
I expect that I do something wrong when I initialize/use my loss function. What can I do so that I can start training my model?
If you are using crossentropy loss you shouldn't one-hot encode your target variable y.
Pytorch crossentropy expects just the class indices as target not their one-hot encoded version.
To cite the doc https://pytorch.org/docs/master/generated/torch.nn.CrossEntropyLoss.html :
This criterion expects a class index in the range [0, C-1] as the target for each value of a 1D tensor of size minibatch;
I am trying to perform hyperparameter tuning for Spatio-Temporal K-Means clustering by using it in a pipeline with a Decision Tree classifier. The idea is to use K-Means clustering algorithm to generate cluster-distance space matrix and clustered labels which will be then passed to Decision Tree classifier. For hyperparameter tuning, just use parameters for K-Means algorithm.
I am using Python 3.8 and sklearn 0.22.
The data I am interested is having 3 columns/attributes: 'time', 'x' and 'y' (x and y are spatial coordinates).
The code is:
class ST_KMeans(BaseEstimator, TransformerMixin):
# class ST_KMeans():
"""
Note that K-means clustering algorithm is designed for Euclidean distances.
It may stop converging with other distances, when the mean is no longer a
best estimation for the cluster 'center'.
The 'mean' minimizes squared differences (or, squared Euclidean distance).
If you want a different distance function, you need to replace the mean with
an appropriate center estimation.
Parameters:
k: number of clusters
eps1 : float, default=0.5
The spatial density threshold (maximum spatial distance) between
two points to be considered related.
eps2 : float, default=10
The temporal threshold (maximum temporal distance) between two
points to be considered related.
metric : string default='euclidean'
The used distance metric - more options are
‘braycurtis’, ‘canberra’, ‘chebyshev’, ‘cityblock’, ‘correlation’,
‘cosine’, ‘dice’, ‘euclidean’, ‘hamming’, ‘jaccard’, ‘jensenshannon’,
‘kulsinski’, ‘mahalanobis’, ‘matching’, ‘rogerstanimoto’, ‘sqeuclidean’,
‘russellrao’, ‘seuclidean’, ‘sokalmichener’, ‘sokalsneath’, ‘yule’.
n_jobs : int or None, default=-1
The number of processes to start; -1 means use all processors (BE AWARE)
Attributes:
labels : array, shape = [n_samples]
Cluster labels for the data - noise is defined as -1
"""
def __init__(self, k, eps1 = 0.5, eps2 = 10, metric = 'euclidean', n_jobs = 1):
self.k = k
self.eps1 = eps1
self.eps2 = eps2
# self.min_samples = min_samples
self.metric = metric
self.n_jobs = n_jobs
def fit(self, X):
"""
Apply the ST K-Means algorithm
X : 2D numpy array. The first attribute of the array should be time attribute
as float. The following positions in the array are treated as spatial
coordinates.
The structure should look like this [[time_step1, x, y], [time_step2, x, y]..]
For example 2D dataset:
array([[0,0.45,0.43],
[0,0.54,0.34],...])
Returns:
self
"""
# check if input is correct
X = check_array(X)
# type(X)
# numpy.ndarray
# Check arguments for DBSCAN algo-
if not self.eps1 > 0.0 or not self.eps2 > 0.0:
raise ValueError('eps1, eps2, minPts must be positive')
# Get dimensions of 'X'-
# n - number of rows
# m - number of attributes/columns-
n, m = X.shape
# Compute sqaured form Euclidean Distance Matrix for 'time' and spatial attributes-
time_dist = squareform(pdist(X[:, 0].reshape(n, 1), metric = self.metric))
euc_dist = squareform(pdist(X[:, 1:], metric = self.metric))
'''
Filter the euclidean distance matrix using time distance matrix. The code snippet gets all the
indices of the 'time_dist' matrix in which the time distance is smaller than 'eps2'.
Afterward, for the same indices in the euclidean distance matrix the 'eps1' is doubled which results
in the fact that the indices are not considered during clustering - as they are bigger than 'eps1'.
'''
# filter 'euc_dist' matrix using 'time_dist' matrix-
dist = np.where(time_dist <= self.eps2, euc_dist, 2 * self.eps1)
# Initialize K-Means clustering model-
kmeans_clust_model = KMeans(
n_clusters = self.k, init = 'k-means++',
n_init = 10, max_iter = 300,
precompute_distances = 'auto', algorithm = 'auto')
# Train model-
kmeans_clust_model.fit(dist)
self.labels = kmeans_clust_model.labels_
self.X_transformed = kmeans_clust_model.fit_transform(X)
return self
def transform(self, X):
pass
# Initialize ST-K-Means object-
st_kmeans_algo = ST_KMeans(
k = 5, eps1=0.6,
eps2=9, metric='euclidean',
n_jobs=1
)
# Train on a chunk of dataset-
st_kmeans_algo.fit(data.loc[:500, ['time', 'x', 'y']])
# Get clustered data points labels-
kmeans_labels = st_kmeans_algo.labels
kmeans_labels.shape
# (501,)
# Get labels for points clustered using trained model-
kmeans_transformed = st_kmeans_algo.X_transformed
kmeans_transformed.shape
# (501, 5)
dtc = DecisionTreeClassifier()
dtc.fit(kmeans_transformed, kmeans_labels)
y_pred = dtc.predict(kmeans_transformed)
# Get model performance metrics-
accuracy = accuracy_score(kmeans_labels, y_pred)
precision = precision_score(kmeans_labels, y_pred, average='macro')
recall = recall_score(kmeans_labels, y_pred, average='macro')
print("\nDT model metrics are:")
print("accuracy = {0:.4f}, precision = {1:.4f} & recall = {2:.4f}\n".format(
accuracy, precision, recall
))
# DT model metrics are:
# accuracy = 1.0000, precision = 1.0000 & recall = 1.0000
However, when I try to perform hyper-paramter tuning using sklearn's pipeline:
# Hyper-parameter Tuning:
# Define steps of pipeline-
pipeline_steps = [
('st_kmeans_algo' ,ST_KMeans(k = 5, eps1=0.6, eps2=9, metric='euclidean', n_jobs=1)),
('dtc', DecisionTreeClassifier())
]
# Instantiate a pipeline-
pipeline = Pipeline(pipeline_steps)
# Train pipeline-
pipeline.fit(kmeans_transformed, kmeans_labels)
It gives me the following error:
--------------------------------------------------------------------------- TypeError Traceback (most recent call
last) in
8
9 # Train pipeline-
---> 10 pipeline.fit(kmeans_transformed, kmeans_labels)
~/.local/lib/python3.8/site-packages/sklearn/pipeline.py in fit(self,
X, y, **fit_params)
348 This estimator
349 """
--> 350 Xt, fit_params = self._fit(X, y, **fit_params)
351 with _print_elapsed_time('Pipeline',
352 self._log_message(len(self.steps) - 1)):
~/.local/lib/python3.8/site-packages/sklearn/pipeline.py in _fit(self,
X, y, **fit_params)
309 cloned_transformer = clone(transformer)
310 # Fit or load from cache the current transformer
--> 311 X, fitted_transformer = fit_transform_one_cached(
312 cloned_transformer, X, y, None,
313 message_clsname='Pipeline',
~/.local/lib/python3.8/site-packages/joblib/memory.py in
call(self, *args, **kwargs)
353
354 def call(self, *args, **kwargs):
--> 355 return self.func(*args, **kwargs)
356
357 def call_and_shelve(self, *args, **kwargs):
~/.local/lib/python3.8/site-packages/sklearn/pipeline.py in
_fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
726 with _print_elapsed_time(message_clsname, message):
727 if hasattr(transformer, 'fit_transform'):
--> 728 res = transformer.fit_transform(X, y, **fit_params)
729 else:
730 res = transformer.fit(X, y, **fit_params).transform(X)
~/.local/lib/python3.8/site-packages/sklearn/base.py in
fit_transform(self, X, y, **fit_params)
572 else:
573 # fit method of arity 2 (supervised transformation)
--> 574 return self.fit(X, y, **fit_params).transform(X)
575
576
TypeError: fit() takes 2 positional arguments but 3 were given
The fit method in your ST_KMeans takes in only X as input but in this line:
pipeline.fit(kmeans_transformed, kmeans_labels)
you pass both X and Y as input to your pipeline which tries to call the fit method of the first stage of your pipeline i.e. ST_KKeans with these two arguments resulting in this error. In order to overcome this just add a dummy parameter y to the fit method of your ST_KMeans objects as shown below:
def fit(self, X, Y):
The additional parameter Y is not used anywhere inside the method it just maintains the consistency.
my method has 2 input data model
network
branches:
49The first branch is composed of an embedding followed by simple Multi-layer
Perceptron (MLP) designed to handle input of the product description.
The second branch is a CNN to operate over the product image data.
These branches are then be concatenated together to form the final.
The problem is when we try to split the data with train_test_split by Cross Validation, It given as this error.
ValueError: Found input variables with inconsistent numbers of samples: [2, 8382]
MLP and CNN
def create_mlp(dim, regress=False):
# define our MLP network
model = Sequential()
model.add(Dense(8, input_dim=dim, activation="relu"))
model.add(Dense(4, activation="relu"))
# check to see if the regression node should be added
if regress:
model.add(Dense(1, activation="linear"))
# return our model
return model
def create_cnn(width, height, depth, filters=(64, 32, 16), regress=False):
# initialize the input shape and channel dimension, assuming
# TensorFlow/channels-last ordering
inputShape = (height, width, depth)
chanDim = -1
# define the model input
inputs = Input(shape=inputShape)
# loop over the number of filters
for (i, f) in enumerate(filters):
# if this is the first CONV layer then set the input
# appropriately
if i == 0:
x = inputs
# CONV => RELU => BN => POOL
x = Conv2D(f, (3, 3), padding="same")(x)
x = Activation("relu")(x)
x = BatchNormalization(axis=chanDim)(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
# flatten the volume, then FC => RELU => BN => DROPOUT
x = Flatten()(x)
x = Dense(16)(x)
x = Activation("relu")(x)
x = BatchNormalization(axis=chanDim)(x)
x = Dropout(0.5)(x)
# apply another FC layer, this one to match the number of nodes
# coming out of the MLP
x = Dense(4)(x)
x = Activation("relu")(x)
# check to see if the regression node should be added
if regress:
x = Dense(1, activation="linear")(x)
# construct the CNN
model = Model(inputs, x)
# return the CNN
return model
mlp = create_mlp(trainEmbedX.shape[1], regress=False)
cnn = create_cnn(64, 64, 3, regress=False)
combinedInput = concatenate([mlp.output, cnn.output])
x = Dense(4, activation="relu")(combinedInput)
x = Dense(1, activation="sigmoid")(x)
model = Model(inputs=[mlp.input, cnn.input], outputs=x)
model.compile(loss="binary_crossentropy", metrics=['accuracy'], optimizer="adam") # binary_crossentropy
The error occurs here
n_folds=3
epochs=3
batch_size=128
#save the model history in a list after fitting so that we can plot later
model_history = []
for i in range(n_folds):
print("Training on Fold: ",i+1)
t_x, val_x, t_y, val_y = train_test_split([trainEmbedX,trainImagesX], trainY, test_size = 0.2, random_state = np.random.randint(1,1000, 1)[0])
model_history.append(fit_and_evaluate(t_x, val_x, t_y, val_y, epochs, batch_size))
print("======="*12, end="\n\n\n")
Training on Fold: 1
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-84-651638774259> in <module>
7 for i in range(n_folds):
8 print("Training on Fold: ",i+1)
----> 9 t_x, val_x, t_y, val_y = train_test_split([trainEmbedX,trainImagesX], trainY, test_size = 0.2, random_state = np.random.randint(1,1000, 1)[0])
10 model_history.append(fit_and_evaluate(t_x, val_x, t_y, val_y, epochs, batch_size))
11 print("======="*12, end="\n\n\n")
~/anaconda3/envs/baron/lib/python3.6/site-packages/sklearn/model_selection/_split.py in train_test_split(*arrays, **options)
2182 test_size = 0.25
2183
-> 2184 arrays = indexable(*arrays)
2185
2186 if shuffle is False:
~/anaconda3/envs/baron/lib/python3.6/site-packages/sklearn/utils/validation.py in indexable(*iterables)
258 else:
259 result.append(np.array(X))
--> 260 check_consistent_length(*result)
261 return result
262
~/anaconda3/envs/baron/lib/python3.6/site-packages/sklearn/utils/validation.py in check_consistent_length(*arrays)
233 if len(uniques) > 1:
234 raise ValueError("Found input variables with inconsistent numbers of"
--> 235 " samples: %r" % [int(l) for l in lengths])
236
237
ValueError: Found input variables with inconsistent numbers of samples: [2, 8382]
This error happens with mismatching dimensions of X and Y in train_test_split.
By looking at your snippet, you try to concatenate two arrays by [trainEmbedX,trainImagesX] which will add a dimension if the original arrays trainEmbedX and trainImagesX are not 1D, hence you have the shape [2, 8382] in the error.
So instead of [trainEmbedX,trainImagesX], I suggest to use np.concatenate to merge these two arrays by np.concatenate((trainEmbedX,trainImagesX),axis=1).
ConvLSTMCell Official Docs
GitHub _conv where the error occurs
Issue
I'm experimenting with the ConvLSTMCell in tensorflow r1.8. The error I'm continuing to generate occurs in the __call__ method of ConvLSTMCell. The _conv method is invoked and the error is raised.
ValueError: Conv Linear Expects 3D, 4D, 5D
The error is raised from the unstacked inputs. unstacked (in this example) has dimensions of [BATCH_SIZE, N_INPUTS] = [2,5]. I am using tf.unstack to generate the required sequence that the ConvLSTMCell requires.
Why use tf.unstack?
If the input array is not unstacked, the TypeError below is raised.
TypeError: inputs must be a sequence
Question
What am I missing on the formatting? I've read through related issues but have not found anything that has guided me into a working implementation.
Are the placeholder dimensions correct?
Should I be unstacking or is there a better way?
Am I providing the proper input dimension into the ConvLSTMCell?
Code
# Parameters
TIME_STEPS = 28
N_INPUT = 5
N_HIDDEN = 128
LEARNING_RATE = 0.001
NUM_UNITS = 28
CHANNEL = 1
tf.reset_default_graph()
# Input placeholders
x = tf.placeholder(tf.float32, [BATCH_SIZE, TIME_STEPS, N_INPUT])
y = tf.placeholder(tf.float32, [None, 1])
# Format input as a sequence for LSTM Input
unstacked = tf.unstack(x, TIME_STEPS, 1) # shape=(timesteps, batch, inputs)
# Convolutional LSTM Layer
lstm_layer = tf.contrib.rnn.ConvLSTMCell(
conv_ndims=1,
input_shape=[BATCH_SIZE, N_INPUT],
output_channels=5,
kernel_shape=[7,5]
)
# Error is generated when the lstm_layer is invoked
outputs, _ = tf.contrib.rnn.static_rnn(
lstm_layer,
unstacked,
dtype=tf.float32)
Error Message
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-83-3568a097e4ea> in <module>()
10 lstm_layer,
11 unstacked,
---> 12 dtype=tf.float32)
~/miniconda3/envs/MultivariateTimeSeries/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py in static_rnn(cell, inputs, initial_state, dtype, sequence_length, scope)
1322 state_size=cell.state_size)
1323 else:
-> 1324 (output, state) = call_cell()
1325
1326 outputs.append(output)
~/miniconda3/envs/MultivariateTimeSeries/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py in <lambda>()
1309 varscope.reuse_variables()
1310 # pylint: disable=cell-var-from-loop
-> 1311 call_cell = lambda: cell(input_, state)
1312 # pylint: enable=cell-var-from-loop
1313 if sequence_length is not None:
~/miniconda3/envs/MultivariateTimeSeries/lib/python3.6/site-packages/tensorflow/python/ops/rnn_cell_impl.py in __call__(self, inputs, state, scope)
230 setattr(self, scope_attrname, scope)
231 with scope:
--> 232 return super(RNNCell, self).__call__(inputs, state)
233
234 def _rnn_get_variable(self, getter, *args, **kwargs):
~/miniconda3/envs/MultivariateTimeSeries/lib/python3.6/site-packages/tensorflow/python/layers/base.py in __call__(self, inputs, *args, **kwargs)
715
716 if not in_deferred_mode:
--> 717 outputs = self.call(inputs, *args, **kwargs)
718 if outputs is None:
719 raise ValueError('A layer\'s `call` method should return a Tensor '
~/miniconda3/envs/MultivariateTimeSeries/lib/python3.6/site-packages/tensorflow/contrib/rnn/python/ops/rnn_cell.py in call(self, inputs, state, scope)
2110 cell, hidden = state
2111 new_hidden = _conv([inputs, hidden], self._kernel_shape,
-> 2112 4 * self._output_channels, self._use_bias)
2113 gates = array_ops.split(
2114 value=new_hidden, num_or_size_splits=4, axis=self._conv_ndims + 1)
~/miniconda3/envs/MultivariateTimeSeries/lib/python3.6/site-packages/tensorflow/contrib/rnn/python/ops/rnn_cell.py in _conv(args, filter_size, num_features, bias, bias_start)
2184 if len(shape) not in [3, 4, 5]:
2185 raise ValueError("Conv Linear expects 3D, 4D "
-> 2186 "or 5D arguments: %s" % str(shapes))
2187 if len(shape) != len(shapes[0]):
2188 raise ValueError("Conv Linear expects all args "
ValueError: Conv Linear expects 3D, 4D or 5D arguments: [[2, 5], [2, 2, 5]]
Here's an example with a couple tweaks, which at least passes static shape checking:
import tensorflow as tf
# Parameters
TIME_STEPS = 28
N_INPUT = 5
N_HIDDEN = 128
LEARNING_RATE = 0.001
NUM_UNITS = 28
CHANNEL = 1
BATCH_SIZE = 16
# Input placeholders
x = tf.placeholder(tf.float32, [BATCH_SIZE, TIME_STEPS, N_INPUT])
y = tf.placeholder(tf.float32, [None, 1])
# Format input as a sequence for LSTM Input
unstacked = tf.unstack(x[..., None], TIME_STEPS, 1) # shape=(timesteps, batch, inputs)
# Convolutional LSTM Layer
lstm_layer = tf.contrib.rnn.ConvLSTMCell(
conv_ndims=1,
input_shape=[N_INPUT, 1],
output_channels=5,
kernel_shape=[7]
)
# Error is generated when the lstm_layer is invoked
outputs, _ = tf.contrib.rnn.static_rnn(
lstm_layer,
unstacked,
dtype=tf.float32)
Notes:
input_shape does not include the batch dimension (see docstring)
The input needs a channels dimension. Fine for it to be one in the input (that's what I've done).
Not sure what more than one dimension on kernel_shape would mean for a 1-D convolution.