https://github.com/javierluraschi/kartmodels

https://github.com/javierluraschi/kartmodels

Last synced: about 1 month ago
JSON representation

• Host: GitHub
• URL: https://github.com/javierluraschi/kartmodels
• Owner: javierluraschi
• Created: 2017-12-26T16:06:28.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2018-01-13T23:10:57.000Z (about 7 years ago)
• Last Synced: 2024-12-23T10:45:52.549Z (about 1 month ago)
• Language: R
• Size: 12.7 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.Rmd

Awesome Lists containing this project

README

        
---

title: "kartmodels: Kart simulation training models"

output:

  github_document:

    fig_width: 7

    fig_height: 5

---

This project makes use of `kartsim` to explore multiple training models.

## Capturing Data

We will use the `kartsim` package and `kartsim_capture()` to capture training and

test data to train the models in this repo.

1. Capture training data using:

```{r eval=FALSE}

library(kartsim)

kartsim_capture("capture/train", circuit = 3)

```

2. Followed by test data with:

```{r eval=FALSE}

kartsim_capture("capture/test", circuit = 3)

```

## Training using the CIFAR model

We will first try modeling this as an image classification problem using the

[cifar10_cnn](https://tensorflow.rstudio.com/keras/articles/examples/cifar10_cnn.html)

Keras example.

```{r eval=FALSE}

tfruns::training_run("models/tf-cifar.R")

```

or in `cloudml` runnning:

```{r eval=FALSE}

cloudml::cloudml_train("models/tf-cifar.R")

```

Next we will preload the model and predict over a `graph` object as follows:

```{r eval=F}

sess <- tensorflow::tf$Session()

graph <- tfdeploy::load_savedmodel(sess, "savedmodel")

tfdeploy::predict_savedmodel(list(array(0, c(32,32,3))), graph, type = "graph", sess = sess)

```

```

   user  system elapsed 

  0.027   0.001   0.025

```

Which we can use to control the kart based on this model:

```{r eval=F}

kartsim::kartsim_control(function(image, direction) {

  labels <- c("left", "forward", "right")

  input <- array(png::readPNG(image), c(32,32,3))

  result <- tfdeploy::predict_savedmodel(input, graph, type = "graph", sess = sess)

  scores <- result$predictions[[1]]$activation

  labels[which(scores == max(scores))][[1]]

}, circuit = 3)

```

```

517/517 [==============================] - 54s 105ms/step - loss: 6.4093 - acc: 0.6013 - val_loss: 5.4995 - val_acc: 0.6588

Epoch 2/2

517/517 [==============================] - 55s 107ms/step - loss: 6.3691 - acc: 0.6048 - val_loss: 5.5059 - val_acc: 0.6577

```

## Improving the CIFAR model with context

In order to improve accuracy, we can consider making the model "remember" the

state of the previous direction to help give continuity while steering.

```{r eval=FALSE}

tfruns::training_run("models/tf-cifar-prev.R")

```

```{r eval=F}

library(tensorflow)

sess <- tensorflow::tf$Session()

graph <- tfdeploy::load_savedmodel(sess, "savedmodel/")

tfdeploy::predict_savedmodel(

  list(

    list(

      conv2d_1_input = array(0, c(32,32,3)),

      previous = 0

    )

  ),

  graph,

  type = "graph",

  sess = sess)

```

```

$predictions

            activation_6

1 0.0462, 0.9226, 0.0312

```

We can apply this control policy as follows:

```{r eval=F}

previous <- 0

control_cifar_prev <- function(image, direction) {

  labels <- c("left", "forward", "right")

  input <- array(png::readPNG(image), c(32,32,3))

  

  result <- tfdeploy::predict_savedmodel(

    list(

      list(

        conv2d_1_input = input,

        previous = previous

      )

    ),

    graph, type = "graph", sess = sess)

  

  message(result)

  

  angle <- result$predictions$activation[[1]]

  previous <<- angle

  angle

}

kartsim::kartsim_control(control_cifar_prev)

```