Neural Networks: Modifiying NN structures?

From this nice answer one can import pretrained NN models and structures for state of art models.

URLDownload[
  "http://data.dmlc.ml/mxnet/models/imagenet/inception-v3.tar.gz",
   FileNameJoin[{$UserDocumentsDirectory, "inception-v3.tar.gz"}]
];

ExtractArchive["inception-v3.tar.gz"];

Needs["NeuralNetworks`"]

net = NeuralNetworks`ImportMXNetModel[
 "model//Inception-7-symbol.json",
 "model//Inception-7-0001.params"
]

The returned result is NetGraph object. In this object, imported models uses NetPort for inputs, as a result one must enter tensor with given dimensions. However, Mathematica has some nice encoders:

enc = NetEncoder[{"Image", {150, 150}}]

My question:

Is it possible to change ports inputting tensors to these Mathematica defined encoders? If so, how?

Upadate:

In addition, I would like to know if it's possible in the inception model to change the number of output classes. Currently, I want to use the structure but not pretrained model with 1008 classes. Lets say I want 10 new classes for output. How can I modify DotPlusLayer("fc1"), SoftMaxLayer("softmax") and Port "Output" for this 10 classes?

Answer

net = NeuralNetworks`ImportMXNetModel[
  "model//Inception-7-symbol.json",
  "model//Inception-7-0001.params"
  ]

This network accepts images in resolution 299x299.

SeedRandom[1];
img = RandomImage[1, {299, 299}, ColorSpace -> "RGB"];

net2 = NetGraph[
  {
   net,
   SoftmaxLayer[]
   },
  {1 -> 2},

  "Input" -> NetEncoder[{"Image", {299, 299}, ColorSpace -> "RGB"}],
  "Output" -> NetDecoder[{"Class", Range[1008]}]
  ]

net2[img]

920

UPDATE

If we want to keep neural architecture but change the number of classes (for example, add 10 new), we can trim original architecture using Take.

net3 = NetGraph[
  {
   Take[net, {NetPort["Input"], "flatten"}],
   1008 + 10,
   SoftmaxLayer[]
   },
  {1 -> 2 -> 3},
  "Input" -> NetEncoder[{"Image", {299, 299}, ColorSpace -> "RGB"}], 

  "Output" -> NetDecoder[{"Class", Range[1008 + 10]}]
  ]

But this network should be trained again, because it doesn't keep information about previously learned classes.

NetExtract[net3, {2, "Weights"}]

Automatic

Comments

plotting - Filling between two spheres in SphericalPlot3D

Manipulate[ SphericalPlot3D[{1, 2 - n}, {θ, 0, Pi}, {ϕ, 0, 1.5 Pi}, Mesh -> None, PlotPoints -> 15, PlotRange -> {-2.2, 2.2}], {n, 0, 1}] I cant' seem to be able to make a filling between two spheres. I've already tried the obvious Filling -> {1 -> {2}} but Mathematica doesn't seem to like that option. Is there any easy way around this or ... Answer There is no built-in filling in SphericalPlot3D . One option is to use ParametricPlot3D to draw the surfaces between the two shells: Manipulate[ Show[SphericalPlot3D[{1, 2 - n}, {θ, 0, Pi}, {ϕ, 0, 1.5 Pi}, PlotPoints -> 15, PlotRange -> {-2.2, 2.2}], ParametricPlot3D[{ r {Sin[t] Cos[1.5 Pi], Sin[t] Sin[1.5 Pi], Cos[t]}, r {Sin[t] Cos[0 Pi], Sin[t] Sin[0 Pi], Cos[t]}}, {r, 1, 2 - n}, {t, 0, Pi}, PlotStyle -> Yellow, Mesh -> {2, 15}]], {n, 0, 1}]

plotting - Plot 4D data with color as 4th dimension

I have a list of 4D data (x position, y position, amplitude, wavelength). I want to plot x, y, and amplitude on a 3D plot and have the color of the points correspond to the wavelength. I have seen many examples using functions to define color but my wavelength cannot be expressed by an analytic function. Is there a simple way to do this? Answer Here a another possible way to visualize 4D data: data = Flatten[Table[{x, y, x^2 + y^2, Sin[x - y]}, {x, -Pi, Pi,Pi/10}, {y,-Pi,Pi, Pi/10}], 1]; You can use the function Point along with VertexColors . Now the points are places using the first three elements and the color is determined by the fourth. In this case I used Hue, but you can use whatever you prefer. Graphics3D[ Point[data[[All, 1 ;; 3]], VertexColors -> Hue /@ data[[All, 4]]], Axes -> True, BoxRatios -> {1, 1, 1/GoldenRatio}]

plotting - Adding a thick curve to a regionplot

Suppose we have the following simple RegionPlot: f[x_] := 1 - x^2 g[x_] := 1 - 0.5 x^2 RegionPlot[{y < f[x], f[x] < y < g[x], y > g[x]}, {x, 0, 2}, {y, 0, 2}] Now I'm trying to change the curve defined by $y=g[x]$ into a thick black curve, while leaving all other boundaries in the plot unchanged. I've tried adding the region $y=g[x]$ and playing with the plotstyle, which didn't work, and I've tried BoundaryStyle, which changed all the boundaries in the plot. Now I'm kinda out of ideas... Any help would be appreciated! Answer With f[x_] := 1 - x^2 g[x_] := 1 - 0.5 x^2 You can use Epilog to add the thick line: RegionPlot[{y < f[x], f[x] < y < g[x], y > g[x]}, {x, 0, 2}, {y, 0, 2}, PlotPoints -> 50, Epilog -> (Plot[g[x], {x, 0, 2}, PlotStyle -> {Black, Thick}][[1]]), PlotStyle -> {Directive[Yellow, Opacity[0.4]], Directive[Pink, Opacity[0.4]],

Blog

Search This Blog