Given that this model is intended to predict continuous values, the mean squared error (MSE) is a good choice for the loss function. Given a vector of predictions, \(\hat{y}\), and a vector of true targets, \(y\), the MSE is defined as the mean of the squared differences between the predicted values and the ground truth.

You may run across not-fully-specified shapes. Either the shape contains a None (an axis-length is unknown) or the whole shape is None (the rank of the tensor is unknown). TensorFlow follows standard Python indexing rules, similar to indexing a list or a string in Python, and the basic rules for NumPy indexing. The shape of a tf.RaggedTensor will contain some axes with unknown lengths: print(ragged_tensor.shape)The base tf.Tensor class requires tensors to be "rectangular"---that is, along each axis, every element is the same size. However, there are specialized types of tensors that can handle different shapes: Please note no SLs were placed on any of these trades, if you wanted to place a SL at the most recent high/low you would have had only a few instances where they were hit. See last two pictures. This affects only type 2 entries. The simplest and most common case is when you attempt to multiply or add a tensor to a scalar. In that case, the scalar is broadcast to be the same shape as the other argument. x = tf.constant([1, 2, 3])

Likewise, axes with length 1 can be stretched out to match the other arguments. Both arguments can be stretched in the same computation. Passing an integer for each index, the result is a scalar. # Pull out a single value from a 2-rank tensor A "vector" or "rank-1" tensor is like a list of values. A vector has one axis: # Let's make this a float tensor.Normal tf.Tensor objects are immutable. To store model weights (or other mutable state) in TensorFlow use a tf.Variable. var = tf.Variable([0.0, 0.0, 0.0]) Here is a "scalar" or "rank-0" tensor . A scalar contains a single value, and no "axes". # This will be an int32 tensor by default; see "dtypes" below.