Plot hidden layers in Keras

keras_plot.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using Theano backend.\n"
     ]
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "import os\n",
    "\n",
    "os.environ['KERAS_BACKEND'] = 'theano'\n",
    "#os.environ['KERAS_BACKEND'] = 'tensorflow'\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "\n",
    "import keras.backend as K\n",
    "from keras.datasets import mnist\n",
    "from keras.models import Sequential\n",
    "from keras.layers.core import Dense, Dropout, Activation\n",
    "from keras.optimizers import SGD, Adam, RMSprop\n",
    "from keras.utils import np_utils\n",
    "from keras.layers import Dense, Dropout, Activation, Flatten\n",
    "from keras.layers import Convolution2D, MaxPooling2D\n",
    "from keras.models import load_model\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X_train shape: (5000, 1, 28, 28)\n",
      "y_train shape: (5000,)\n"
     ]
    }
   ],
   "source": [
    "# Load dataset\n",
    "\n",
    "(X_train, y_train), (X_test, y_test) = mnist.load_data()\n",
    "\n",
    "# Only take a small part of the data to reduce computation time\n",
    "\n",
    "X_train = X_train[:5000]\n",
    "y_train = y_train[:5000]\n",
    "X_test = X_test[:5000]\n",
    "y_test = y_test[:5000]\n",
    "\n",
    "# Define some variables from the dataset\n",
    "\n",
    "nb_classes = np.unique(y_train).shape[0]\n",
    "img_rows, img_cols = X_train.shape[-2:]\n",
    "\n",
    "X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols).astype('float32')\n",
    "X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols).astype('float32')\n",
    "\n",
    "X_train /= 255\n",
    "X_test /= 255\n",
    "\n",
    "print('X_train shape:', X_train.shape)\n",
    "print('y_train shape:', y_train.shape)\n",
    "\n",
    "# Convert class vectors to binary class matrices\n",
    "\n",
    "Y_train = np_utils.to_categorical(y_train, nb_classes)\n",
    "Y_test = np_utils.to_categorical(y_test, nb_classes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "____________________________________________________________________________________________________\n",
      "Layer (type)                     Output Shape          Param #     Connected to                     \n",
      "====================================================================================================\n",
      "convolution2d_1 (Convolution2D)  (None, 32, 26, 26)    320         convolution2d_input_1[0][0]      \n",
      "____________________________________________________________________________________________________\n",
      "convolution2d_2 (Convolution2D)  (None, 32, 24, 24)    9248        convolution2d_1[0][0]            \n",
      "____________________________________________________________________________________________________\n",
      "maxpooling2d_1 (MaxPooling2D)    (None, 32, 12, 12)    0           convolution2d_2[0][0]            \n",
      "____________________________________________________________________________________________________\n",
      "dropout_1 (Dropout)              (None, 32, 12, 12)    0           maxpooling2d_1[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "flatten_1 (Flatten)              (None, 4608)          0           dropout_1[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "dense_1 (Dense)                  (None, 10)            46090       flatten_1[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "activation_1 (Activation)        (None, 10)            0           dense_1[0][0]                    \n",
      "====================================================================================================\n",
      "Total params: 55658\n",
      "____________________________________________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "# Model parameters\n",
    "\n",
    "nb_filters = 32\n",
    "nb_pool = 2\n",
    "kernel_size = (3, 3)\n",
    "\n",
    "# Create the model\n",
    "\n",
    "model = Sequential()\n",
    "\n",
    "model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],\n",
    "                        border_mode='valid', activation=\"relu\",\n",
    "                        input_shape=(1, img_rows, img_cols)))\n",
    "\n",
    "model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],\n",
    "                        border_mode='valid',activation=\"relu\"))\n",
    "\n",
    "model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))\n",
    "model.add(Dropout(0.25))\n",
    "\n",
    "model.add(Flatten())\n",
    "\n",
    "# model.add(Dense(128))\n",
    "# model.add(Activation('relu'))\n",
    "# model.add(Dropout(0.5))\n",
    "\n",
    "model.add(Dense(nb_classes))\n",
    "model.add(Activation('softmax'))\n",
    "\n",
    "model.summary()\n",
    "\n",
    "model.compile(loss='categorical_crossentropy',\n",
    "              optimizer=RMSprop(),\n",
    "              metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 5000 samples, validate on 5000 samples\n",
      "Epoch 1/5\n",
      "5000/5000 [==============================] - 14s - loss: 0.8267 - acc: 0.7676 - val_loss: 0.4986 - val_acc: 0.8492\n",
      "Epoch 2/5\n",
      "5000/5000 [==============================] - 17s - loss: 0.3438 - acc: 0.9004 - val_loss: 0.4225 - val_acc: 0.8712\n",
      "Epoch 3/5\n",
      "5000/5000 [==============================] - 15s - loss: 0.2499 - acc: 0.9272 - val_loss: 0.3238 - val_acc: 0.9028\n",
      "Epoch 4/5\n",
      "5000/5000 [==============================] - 16s - loss: 0.1887 - acc: 0.9464 - val_loss: 0.3644 - val_acc: 0.8820\n",
      "Epoch 5/5\n",
      "5000/5000 [==============================] - 19s - loss: 0.1471 - acc: 0.9590 - val_loss: 0.2306 - val_acc: 0.9284\n"
     ]
    }
   ],
   "source": [
    "batch_size = 128\n",
    "nb_epoch = 5\n",
    "\n",
    "history = model.fit(X_train, Y_train,\n",
    "                    batch_size=batch_size, nb_epoch=nb_epoch,\n",
    "                    verbose=1, validation_data=(X_test, Y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Plotting functions\n",
    "\n",
    "## make_mosaic(im, nrows, ncols, border=1)\n",
    "## Create a numpy mosaic from a list of matrix.\n",
    "\n",
    "## get_weights_mosaic(model, layer_id, n=64)\n",
    "## Get the weights of the layer of a model as a numpy mosaic.\n",
    "\n",
    "## plot_weights(model, layer_id, n=64, ax=None, **kwargs)\n",
    "## Plot the weights of a specific layer with matplotlib\n",
    "\n",
    "## plot_all_weights(model, n=64, **kwargs)\n",
    "## Plot all the possible 2D weights in the model\n",
    "\n",
    "## plot_feature_map(model, layer_id, X, n=256, ax=None, **kwargs)\n",
    "## Plot the feature maps of the layer of a model\n",
    "\n",
    "## plot_all_feature_maps(model, X, n=256, ax=None, **kwargs)\n",
    "## Plot all the feature maps of every possible layers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def make_mosaic(im, nrows, ncols, border=1):\n",
    "    \"\"\"From http://nbviewer.jupyter.org/github/julienr/ipynb_playground/blob/master/keras/convmnist/keras_cnn_mnist.ipynb\n",
    "    \"\"\"\n",
    "    import numpy.ma as ma\n",
    "\n",
    "    nimgs = len(im)\n",
    "    imshape = im[0].shape\n",
    "    \n",
    "    mosaic = ma.masked_all((nrows * imshape[0] + (nrows - 1) * border,\n",
    "                            ncols * imshape[1] + (ncols - 1) * border),\n",
    "                            dtype=np.float32)\n",
    "    \n",
    "    paddedh = imshape[0] + border\n",
    "    paddedw = imshape[1] + border\n",
    "    im\n",
    "    for i in range(nimgs):\n",
    "        \n",
    "        row = int(np.floor(i / ncols))\n",
    "        col = i % ncols\n",
    "        \n",
    "        mosaic[row * paddedh:row * paddedh + imshape[0],\n",
    "               col * paddedw:col * paddedw + imshape[1]] = im[i]\n",
    "        \n",
    "    return mosaic\n",
    "\n",
    "\n",
    "def get_weights_mosaic(model, layer_id, n=64):\n",
    "    \"\"\"\n",
    "    \"\"\"\n",
    "    \n",
    "    # Get Keras layer\n",
    "    layer = model.layers[layer_id]\n",
    "\n",
    "    # Check if this layer has weight values\n",
    "    if not hasattr(layer, \"W\"):\n",
    "        raise Exception(\"The layer {} of type {} does not have weights.\".format(layer.name,\n",
    "                                                           layer.__class__.__name__))\n",
    "        \n",
    "    weights = layer.W.get_value()\n",
    "    \n",
    "    # For now we only handle Conv layer like with 4 dimensions\n",
    "    if weights.ndim != 4:\n",
    "        raise Exception(\"The layer {} has {} dimensions which is not supported.\".format(layer.name, weights.ndim))\n",
    "    \n",
    "    # n define the maximum number of weights to display\n",
    "    if weights.shape[0] < n:\n",
    "        n = weights.shape[0]\n",
    "        \n",
    "    # Create the mosaic of weights\n",
    "    nrows = int(np.round(np.sqrt(n)))\n",
    "    ncols = int(nrows)\n",
    "\n",
    "    if nrows ** 2 < n:\n",
    "        ncols +=1\n",
    "\n",
    "    mosaic = make_mosaic(weights[:n, 0], nrows, ncols, border=1)\n",
    "    \n",
    "    return mosaic\n",
    "\n",
    "\n",
    "def plot_weights(model, layer_id, n=64, ax=None, **kwargs):\n",
    "    \"\"\"Plot the weights of a specific layer. ndim must be 4.\n",
    "    \"\"\"\n",
    "    import matplotlib.pyplot as plt\n",
    "    \n",
    "    # Set default matplotlib parameters\n",
    "    if not 'interpolation' in kwargs.keys():\n",
    "        kwargs['interpolation'] = \"none\"\n",
    "        \n",
    "    if not 'cmap' in kwargs.keys():\n",
    "        kwargs['cmap'] = \"gray\"\n",
    "    \n",
    "    layer = model.layers[layer_id]\n",
    "    \n",
    "    mosaic = get_weights_mosaic(model, layer_id, n=64)\n",
    "    \n",
    "    # Plot the mosaic\n",
    "    if not ax:\n",
    "        fig = plt.figure()\n",
    "        ax = plt.subplot()\n",
    "    \n",
    "    im = ax.imshow(mosaic, **kwargs)\n",
    "    ax.set_title(\"Layer #{} called '{}' of type {}\".format(layer_id, layer.name, layer.__class__.__name__))\n",
    "    \n",
    "    plt.colorbar(im, ax=ax)\n",
    "    \n",
    "    return ax\n",
    "\n",
    "\n",
    "def plot_all_weights(model, n=64, **kwargs):\n",
    "    \"\"\"\n",
    "    \"\"\"\n",
    "    import matplotlib.pyplot as plt\n",
    "    from mpl_toolkits.axes_grid1 import make_axes_locatable\n",
    "    \n",
    "    # Set default matplotlib parameters\n",
    "    if not 'interpolation' in kwargs.keys():\n",
    "        kwargs['interpolation'] = \"none\"\n",
    "\n",
    "    if not 'cmap' in kwargs.keys():\n",
    "        kwargs['cmap'] = \"gray\"\n",
    "\n",
    "    layers_to_show = []\n",
    "\n",
    "    for i, layer in enumerate(model.layers):\n",
    "        if hasattr(layer, \"W\"):\n",
    "            weights = layer.W.get_value()\n",
    "            if weights.ndim == 4:\n",
    "                layers_to_show.append((i, layer))\n",
    "\n",
    "\n",
    "    fig = plt.figure(figsize=(15, 15))\n",
    "    \n",
    "    n_mosaic = len(layers_to_show)\n",
    "    nrows = int(np.round(np.sqrt(n_mosaic)))\n",
    "    ncols = int(nrows)\n",
    "\n",
    "    if nrows ** 2 < n_mosaic:\n",
    "        ncols +=1\n",
    "\n",
    "    for i, (layer_id, layer) in enumerate(layers_to_show):\n",
    "\n",
    "        mosaic = get_weights_mosaic(model, layer_id=layer_id, n=n)\n",
    "\n",
    "        ax = fig.add_subplot(nrows, ncols, i+1)\n",
    "        \n",
    "        im = ax.imshow(mosaic, **kwargs)\n",
    "        ax.set_title(\"Layer #{} called '{}' of type {}\".format(layer_id, layer.name, layer.__class__.__name__))\n",
    "\n",
    "        divider = make_axes_locatable(ax)\n",
    "        cax = divider.append_axes(\"right\", size=\"5%\", pad=0.1)\n",
    "        plt.colorbar(im, cax=cax)\n",
    "        \n",
    "    fig.tight_layout()\n",
    "    return fig\n",
    "\n",
    "\n",
    "def plot_feature_map(model, layer_id, X, n=256, ax=None, **kwargs):\n",
    "    \"\"\"\n",
    "    \"\"\"\n",
    "    import keras.backend as K\n",
    "    import matplotlib.pyplot as plt\n",
    "    from mpl_toolkits.axes_grid1 import make_axes_locatable\n",
    "\n",
    "    layer = model.layers[layer_id]\n",
    "    \n",
    "    try:\n",
    "        get_activations = K.function([model.layers[0].input, K.learning_phase()], [layer.output,])\n",
    "        activations = get_activations([X, 0])[0]\n",
    "    except:\n",
    "        # Ugly catch, a cleaner logic is welcome here.\n",
    "        raise Exception(\"This layer cannot be plotted.\")\n",
    "        \n",
    "    # For now we only handle feature map with 4 dimensions\n",
    "    if activations.ndim != 4:\n",
    "        raise Exception(\"Feature map of '{}' has {} dimensions which is not supported.\".format(layer.name,\n",
    "                                                                                             activations.ndim))\n",
    "        \n",
    "    # Set default matplotlib parameters\n",
    "    if not 'interpolation' in kwargs.keys():\n",
    "        kwargs['interpolation'] = \"none\"\n",
    "\n",
    "    if not 'cmap' in kwargs.keys():\n",
    "        kwargs['cmap'] = \"gray\"\n",
    "        \n",
    "    fig = plt.figure(figsize=(15, 15))\n",
    "    \n",
    "    # Compute nrows and ncols for images\n",
    "    n_mosaic = len(activations)\n",
    "    nrows = int(np.round(np.sqrt(n_mosaic)))\n",
    "    ncols = int(nrows)\n",
    "    if (nrows ** 2) < n_mosaic:\n",
    "        ncols +=1\n",
    "        \n",
    "    # Compute nrows and ncols for mosaics\n",
    "    if activations[0].shape[0] < n:\n",
    "        n = activations[0].shape[0]\n",
    "        \n",
    "    nrows_inside_mosaic = int(np.round(np.sqrt(n)))\n",
    "    ncols_inside_mosaic = int(nrows_inside_mosaic)\n",
    "\n",
    "    if nrows_inside_mosaic ** 2 < n:\n",
    "        ncols_inside_mosaic += 1\n",
    "\n",
    "    for i, feature_map in enumerate(activations):\n",
    "\n",
    "        mosaic = make_mosaic(feature_map[:n], nrows_inside_mosaic, ncols_inside_mosaic, border=1)\n",
    "\n",
    "        ax = fig.add_subplot(nrows, ncols, i+1)\n",
    "        \n",
    "        im = ax.imshow(mosaic, **kwargs)\n",
    "        ax.set_title(\"Feature map #{} \\nof layer#{} \\ncalled '{}' \\nof type {} \".format(i, layer_id,\n",
    "                                                                                  layer.name,\n",
    "                                                                                  layer.__class__.__name__))\n",
    "\n",
    "        divider = make_axes_locatable(ax)\n",
    "        cax = divider.append_axes(\"right\", size=\"5%\", pad=0.1)\n",
    "        plt.colorbar(im, cax=cax)\n",
    "            \n",
    "    fig.tight_layout()\n",
    "    return fig\n",
    "\n",
    "\n",
    "def plot_all_feature_maps(model, X, n=256, ax=None, **kwargs):\n",
    "    \"\"\"\n",
    "    \"\"\"\n",
    "    \n",
    "    figs = []\n",
    "    \n",
    "    for i, layer in enumerate(model.layers):\n",
    "        \n",
    "        try:\n",
    "            fig = plot_feature_map(model, i, X, n=n, ax=ax, **kwargs)\n",
    "        except:\n",
    "            pass\n",
    "        else:\n",
    "            figs.append(fig)\n",
    "            \n",
    "    return figs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABDAAAAHmCAYAAACFy36DAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/weSj8Z9igLR0QAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fba4c640400>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot all the weights when possible of the model\n",
    "# The maximum number of filters per layer is n=256\n",
    "_ = plot_all_weights(model, n=256)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABDAAAAPVCAYAAACQuhqpAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7fba496c3898>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot all the feature maps of the layer 2\n",
    "# The maximum number of filters per feature maps is n=9\n",
    "\n",
    "_ = plot_feature_map(model, 2, X_test[:12], n=9)\n",
    "#_ = plot_all_feature_maps(model, X_test[:9], n=9)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}