I see most people confused about tf.shape(tensor) and tensor.get_shape() Let’s make it clear: tf.shape tf.shape is used for dynamic shape. If your tensor’s shape is changable, use it. An example: a input is an image with changable width and height, we want resize it to half of its size, then we can write something like: … Read more
Keras’ backend has print_tensor which enables you to do this. You can use it this way: import keras.backend as K def loss_fn(y_true, y_pred): y_true = K.print_tensor(y_true, message=”y_true = “) y_pred = K.print_tensor(y_pred, message=”y_pred = “) … The function returns an identical tensor. When that tensor is evaluated, it will print its content, preceded by message. … Read more
x has a shape of (2, 3) (two rows and three columns): 1 1 1 1 1 1 By doing tf.reduce_sum(x, 0) the tensor is reduced along the first dimension (rows), so the result is [1, 1, 1] + [1, 1, 1] = [2, 2, 2]. By doing tf.reduce_sum(x, 1) the tensor is reduced along … Read more
.data was an attribute of Variable (object representing Tensor with history tracking e.g. for automatic update), not Tensor. Actually, .data was giving access to the Variable‘s underlying Tensor. However, since PyTorch version 0.4.0, Variable and Tensor have been merged (into an updated Tensor structure), so .data disappeared along the previous Variable object (well Variable is … Read more
The idea with tensordot is pretty simple – We input the arrays and the respective axes along which the sum-reductions are intended. The axes that take part in sum-reduction are removed in the output and all of the remaining axes from the input arrays are spread-out as different axes in the output keeping the order … Read more
Let’s say you want to do digit recognition (MNIST) and you have defined your architecture of the network (CNNs). Now, you can start feeding the images from the training data one by one to the network, get the prediction (till this step it’s called as doing inference), compute the loss, compute the gradient, and then … Read more
tf.shape(input, name=None) returns a 1-D integer tensor representing the shape of input. You’re looking for: x.get_shape() that returns the TensorShape of the x variable. Update: I wrote an article to clarify the dynamic/static shapes in Tensorflow because of this answer: https://pgaleone.eu/tensorflow/2018/07/28/understanding-tensorflow-tensors-shape-static-dynamic/
Use torch.unsqueeze(input, dim, out=None): >>> import torch >>> a = torch.Tensor([1, 2, 3, 4, 5]) >>> a 1 2 3 4 5 [torch.FloatTensor of size 5] >>> a = a.unsqueeze(0) >>> a 1 2 3 4 5 [torch.FloatTensor of size 1×5]
For PyTorch v1.0 and possibly above: >>> import torch >>> var = torch.tensor([[1,0], [0,1]]) # Using .size function, returns a torch.Size object. >>> var.size() torch.Size([2, 2]) >>> type(var.size()) <class ‘torch.Size’> # Similarly, using .shape >>> var.shape torch.Size([2, 2]) >>> type(var.shape) <class ‘torch.Size’> You can cast any torch.Size object to a native Python list: >>> list(var.size()) … Read more
Computer memory is addressed linearly. Each memory cell corresponds to a number. A block of memory can be addressed in terms of a base, which is the memory address of its first element, and the item index. For example, assuming the base address is 10,000: item index 0 1 2 3 memory address 10,000 10,001 … Read more