¡Hola, Mundo!

Sequential - To construct with a sequential structure, a stack from the input layer to the output layer. - It lets stack the layers one by one. - It connects several functions such as Wx+b, Sigmoid. model.add() - Adding the layer-an input layer, a hidden layer, and an output layer - You can construct the model using the various layers(Dense, Conv2D, MaxPooling2D, LSTM, etc.). input_shape - Only ..

VGG16 Visual Geometry Group 16 Layers deep. A convolutional neural network that is 16 layers deep. Initially, VGG is a model designed to study how the depth of neural networks affects. So, the filter size of the convolution layer was fixed at the smallest 3x3. This is because if the filter size is large, the image size quickly becomes small and it is difficult to make the depth. Models before VG..

GradientTape It records intermediate processes of functions, operations on Tape one by one. In other words, computational operation is saved in Tape. Reverse mode automatic differentiation TensorFlow calculates the differentiation of x for the loss by using the Reverse mode automatic differentiation with dx = tape.gradient(loss, x) Backpropagate the differential of x for the loss, repeat the tas..

reduce_sum Computes the sum of elements across dimensions of a tensor. - keepdims=False The rank of the tensor is reduced by 1 for each of the entries in axis A = tf.constant([[[1, 2, 3]], [[4, 5, 6]]]) tf.reduce_sum(A)=21 tf.reduce_sum(A, 0)=[[5 7 9]] tf.reduce_sum(A, 1)=[[1 2 3] [4 5 6]] tf.reduce_sum(A, 2)=[[ 6] [15]] - keepdims=True The reduced dimensions are retained with length 1. tf.reduc..

Interpolation It is estimating the value between two known values. Extrapolation It is estimating a value at an external location outside the range. Linear Interpolation A method of curve fitting using linear polynomials to construct new data points within the range of a discrete set of known data points. Formula d1 : The distance from x to x1. d2 : The distance from x to x2. If the distance rat..