{"metadata":{"kernelspec":{"name":"ir","display_name":"R","language":"R"},"language_info":{"name":"R","codemirror_mode":"r","pygments_lexer":"r","mimetype":"text/x-r-source","file_extension":".r","version":"4.4.0"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[],"dockerImageVersionId":30751,"isInternetEnabled":true,"language":"r","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# Install the Keras package from CRAN\ninstall.packages(\"keras\")\n\n# Load the Keras library\nlibrary(keras)\n\n# Install TensorFlow and Keras Python packages\n# This command installs TensorFlow and Keras for Python and sets up the necessary environment\ninstall_keras()\n\n# Check TensorFlow version\nlibrary(tensorflow)\ntf$constant(\"Hello TensorFlow!\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-11T06:02:40.329064Z","iopub.execute_input":"2026-03-11T06:02:40.331175Z","iopub.status.idle":"2026-03-11T06:04:22.902860Z","shell.execute_reply":"2026-03-11T06:04:22.901219Z"}},"outputs":[{"name":"stderr","text":"Installing package into ‘/usr/local/lib/R/site-library’\n(as ‘lib’ is unspecified)\n\nThe keras package is deprecated. Please use the keras3 package instead.\nAlternatively, to continue using legacy keras, call `py_require_legacy_keras()`.\n\n","output_type":"stream"},{"name":"stdout","text":"Using Python: /usr/bin/python3.10\nCreating virtual environment 'r-tensorflow' ... \n","output_type":"stream"},{"name":"stderr","text":"+ /usr/bin/python3.10 -m venv /root/.virtualenvs/r-tensorflow\n\n","output_type":"stream"},{"name":"stdout","text":"Done!\nInstalling packages: pip, wheel, setuptools\n","output_type":"stream"},{"name":"stderr","text":"+ /root/.virtualenvs/r-tensorflow/bin/python -m pip install --upgrade pip wheel setuptools\n\n","output_type":"stream"},{"name":"stdout","text":"Virtual environment 'r-tensorflow' successfully created.\nUsing virtual environment 'r-tensorflow' ...\n","output_type":"stream"},{"name":"stderr","text":"+ /root/.virtualenvs/r-tensorflow/bin/python -m pip install --upgrade --no-user 'tensorflow==2.15.*' tensorflow-hub tensorflow-datasets scipy requests Pillow h5py pandas pydot tf-keras\n\n","output_type":"stream"},{"name":"stdout","text":"\nInstallation complete.\n\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"tf.Tensor(b'Hello TensorFlow!', shape=(), dtype=string)"},"metadata":{}}],"execution_count":1},{"cell_type":"code","source":"# Load the keras library\nlibrary(keras)\n\n# Load the MNIST dataset\nmnist <- dataset_mnist()\n\n# Split into training and testing datasets\nx_train <- mnist$train$x\ny_train <- mnist$train$y\nx_test <- mnist$test$x\ny_test <- mnist$test$y","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-11T06:04:35.410412Z","iopub.execute_input":"2026-03-11T06:04:35.411765Z","iopub.status.idle":"2026-03-11T06:04:36.405892Z","shell.execute_reply":"2026-03-11T06:04:36.404340Z"}},"outputs":[],"execution_count":3},{"cell_type":"code","source":"# Reshape the images to (28, 28, 1) and normalize pixel values to the range [0, 1]\nx_train <- array_reshape(x_train, c(nrow(x_train), 28, 28, 1))\nx_test <- array_reshape(x_test, c(nrow(x_test), 28, 28, 1))\n\nx_train <- x_train / 255\nx_test <- x_test / 255","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-11T06:04:47.313341Z","iopub.execute_input":"2026-03-11T06:04:47.314725Z","iopub.status.idle":"2026-03-11T06:04:48.254868Z","shell.execute_reply":"2026-03-11T06:04:48.253265Z"}},"outputs":[],"execution_count":4},{"cell_type":"code","source":"one_hot_encode <- function(labels, num_classes) {\n  # Create a matrix of zeros\n  encoded_labels <- matrix(0, nrow = length(labels), ncol = num_classes)\n  \n  # Set the appropriate index to 1 for each label\n  for (i in seq_along(labels)) {\n    encoded_labels[i, labels[i] + 1] <- 1\n  }\n  \n  return(encoded_labels)\n}\n\n# Apply the custom one-hot encoding function\ny_train <- one_hot_encode(y_train, 10)\ny_test <- one_hot_encode(y_test, 10)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-11T06:04:56.845684Z","iopub.execute_input":"2026-03-11T06:04:56.847012Z","iopub.status.idle":"2026-03-11T06:04:56.870761Z","shell.execute_reply":"2026-03-11T06:04:56.869516Z"}},"outputs":[],"execution_count":5},{"cell_type":"code","source":"# Check dimensions and type of data\nstr(x_train)\nstr(y_train)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-11T06:05:10.648440Z","iopub.execute_input":"2026-03-11T06:05:10.649891Z","iopub.status.idle":"2026-03-11T06:05:10.667589Z","shell.execute_reply":"2026-03-11T06:05:10.666293Z"}},"outputs":[{"name":"stdout","text":" num [1:60000, 1:28, 1:28, 1] 0 0 0 0 0 0 0 0 0 0 ...\n num [1:60000, 1:10] 0 1 0 0 0 0 0 0 0 0 ...\n","output_type":"stream"}],"execution_count":6},{"cell_type":"code","source":"# Initialize the model\nmodel <- keras_model_sequential() \n\n# Add convolutional layers\nmodel %>%\n  layer_conv_2d(filters = 32, kernel_size = c(3, 3), activation = 'relu', \n                input_shape = c(28, 28, 1)) %>%\n  layer_max_pooling_2d(pool_size = c(2, 2)) %>%\n  layer_conv_2d(filters = 64, kernel_size = c(3, 3), activation = 'relu') %>%\n  layer_max_pooling_2d(pool_size = c(2, 2)) %>%\n  layer_conv_2d(filters = 128, kernel_size = c(3, 3), activation = 'relu') %>%\n  layer_max_pooling_2d(pool_size = c(2, 2)) %>%\n  \n  # Flatten the output from convolutional layers\n  layer_flatten() %>%\n  \n  # Add fully connected layers\n  layer_dense(units = 128, activation = 'relu') %>%\n  layer_dropout(rate = 0.5) %>%\n  layer_dense(units = 10, activation = 'softmax')  # Output layer for 10 classes","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-11T06:05:17.700008Z","iopub.execute_input":"2026-03-11T06:05:17.701382Z","iopub.status.idle":"2026-03-11T06:05:17.866220Z","shell.execute_reply":"2026-03-11T06:05:17.864824Z"}},"outputs":[],"execution_count":7},{"cell_type":"code","source":"model %>% compile(\n  optimizer = optimizer_adam(),\n  loss = 'categorical_crossentropy',\n  metrics = c('accuracy')\n)\n\nhistory <- model %>% fit(\n  x_train, y_train,\n  epochs = 10,\n  batch_size = 64,\n  validation_split = 0.2\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-11T06:05:25.800195Z","iopub.execute_input":"2026-03-11T06:05:25.801506Z","iopub.status.idle":"2026-03-11T06:06:08.949707Z","shell.execute_reply":"2026-03-11T06:06:08.948048Z"}},"outputs":[],"execution_count":8},{"cell_type":"code","source":"# score <- model %>% evaluate(x_test, y_test)\n# print(score)\n# # Print evaluation results\n# cat('Test loss:', score$loss, '\\n')\n# cat('Test accuracy:', score$accuracy, '\\n')\nscore <- model %>% evaluate(x_test, y_test)\n\nprint(score)\n\n# Print evaluation results\ncat(\"Test loss:\", score[\"loss\"], \"\\n\")\ncat(\"Test accuracy:\", score[\"accuracy\"], \"\\n\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-11T06:08:01.760868Z","iopub.execute_input":"2026-03-11T06:08:01.762166Z","iopub.status.idle":"2026-03-11T06:08:02.708223Z","shell.execute_reply":"2026-03-11T06:08:02.706785Z"}},"outputs":[{"name":"stdout","text":"      loss   accuracy \n0.05012181 0.98710001 \nTest loss: 0.05012181 \nTest accuracy: 0.9871 \n","output_type":"stream"}],"execution_count":11},{"cell_type":"code","source":"# Plot training & validation accuracy values\nplot(history$metrics$accuracy, type = 'l', col = 'blue', ylim = c(0, 1), xlab = 'Epoch', \n     ylab = 'Accuracy', main = 'Model Accuracy')\nlines(history$metrics$val_accuracy, type = 'l', col = 'red')\nlegend(\"bottomright\", legend = c(\"Training Accuracy\", \"Validation Accuracy\"), \n       col = c(\"blue\", \"red\"), lty = 1)\n\n# Plot training & validation loss values\nplot(history$metrics$loss, type = 'l', col = 'blue', \n     ylim = c(0, max(history$metrics$loss, history$metrics$val_loss)), xlab = 'Epoch', \n     ylab = 'Loss', main = 'Model Loss')\nlines(history$metrics$val_loss, type = 'l', col = 'red')\nlegend(\"topright\", legend = c(\"Training Loss\", \"Validation Loss\"), \n       col = c(\"blue\", \"red\"), lty = 1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-11T06:08:13.906222Z","iopub.execute_input":"2026-03-11T06:08:13.907782Z","iopub.status.idle":"2026-03-11T06:08:14.038977Z","shell.execute_reply":"2026-03-11T06:08:14.037239Z"}},"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAIAAAByhViMAAAABmJLR0QA/wD/AP+gvaeTAAAg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"},"metadata":{"image/png":{"width":420,"height":420}}},{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAIAAAByhViMAAAABmJLR0QA/wD/AP+gvaeTAAAg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\nOwAAAIsg2AEAAFjE/wPR2Iqu/8o+8wAAAABJRU5ErkJggg=="},"metadata":{"image/png":{"width":420,"height":420}}}],"execution_count":12},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}