diff --git a/part4/4.JetTaggingPointCloud.ipynb b/part4/4.JetTaggingPointCloud.ipynb new file mode 100644 index 0000000..e0227f2 --- /dev/null +++ b/part4/4.JetTaggingPointCloud.ipynb @@ -0,0 +1,729 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "colab_type": "text", + "id": "view-in-github" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "BsonEqBekjyy" + }, + "source": [ + "# Jet Tagging with Set Transformer\n", + "\n", + "In this notebook we will see an implementation of the Transformer architecture for sets applied to the jet tagging task. For *sets* it is meant here a point cloud, i.e. a set of nodes without edges. We will instead use Multi-Head Attention to learn which nodes (or particles) have strong pair-wise interaction.\n", + "\n", + "The architecture was introduced by [J. Lee at al. (ICML 2019)](https://arxiv.org/abs/1810.00825) -- specifically designed to model interactions among elements in the input set without pre-defined edges. The model consists of an encoder and a decoder, both of which rely on attention mechanisms, as in the original Transformer implementation [by Vaswani](https://arxiv.org/abs/1706.03762). The main difference is that positional encoding is removed plus some other low level adaptions.\n", + "\n", + "We will use tensorflow for this implementation.\n", + "\n", + "Before you start, choose GPU as a hardware accelerator for this notebook. To do this first go to Edit -> Notebook Settings -> Choose GPU as a hardware accelerator." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "A7OS3w5WRSCj" + }, + "outputs": [], + "source": [ + "import tensorflow as tf\n", + "from tensorflow import keras\n", + "from tensorflow.keras import layers\n", + "import h5py\n", + "import numpy as np\n", + "\n", + "print(\"Num GPUs Available: \", len(tf.config.list_physical_devices('GPU')))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "qwekVVRzneqU" + }, + "source": [ + "## Dataset exploration" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "BHQGiyC4Pr4R" + }, + "outputs": [], + "source": [ + "! curl https://cernbox.cern.ch/s/6Ec5pGFEpFWeH6S/download -o Data-MLtutorial.tar.gz\n", + "! tar -xvzf Data-MLtutorial.tar.gz \n", + "! ls Data-MLtutorial/JetDataset/\n", + "! rm Data-MLtutorial.tar.gz " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "J9ZLcoKpPteG" + }, + "outputs": [], + "source": [ + "# let's open the file\n", + "data_dir = 'Data-MLtutorial/JetDataset/'\n", + "fileIN = data_dir+'jetImage_7_100p_30000_40000.h5'\n", + "f = h5py.File(fileIN)\n", + "# and see what it contains\n", + "print(list(f.keys()))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Ktx1VjNoOu4c" + }, + "source": [ + "* 'jetImage' ,' jetImageECAL' and 'jetImageHCAL' contains the image representation of the jets . We will not use them today but build our point cloud from the other information.\n", + "* 'jetConstituentList' is the list of particles cointained in the jet. For each particle, a list of relevant quantities is stored. This is the dataset we will consider in this notebook.\n", + "* 'particleFeatureNames' is the list of the names corresponding to the quantities contained in 'jetConstituentList'\n", + "* 'jets' is the list of jets with the high-level jet features stored. We will only use jet ID from it, indecies [-6:-1]\n", + "* 'jetFeatureNames' is the list of the names corresponding to the quantities contained in 'jets'. These quantities are build using physics knowledge and correspond to high-level infromation and features per graph (as opposed to per node)\n", + "\n", + "The first 100 highest transverse momentum $p_T$ particles are considered for each jet.\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Re7oXWWmPxz9" + }, + "outputs": [], + "source": [ + "target_onehot = np.array([])\n", + "jetList = np.array([])\n", + "jetImages = np.array([])\n", + "features_names = dict()\n", + "datafiles = ['jetImage_7_100p_0_10000.h5',\n", + " 'jetImage_7_100p_10000_20000.h5',\n", + " 'jetImage_7_100p_30000_40000.h5',\n", + " 'jetImage_7_100p_40000_50000.h5',\n", + " 'jetImage_7_100p_50000_60000.h5'\n", + " ]\n", + "for i_f,fileIN in enumerate(datafiles):\n", + " print(\"Appending %s\" %fileIN)\n", + " f = h5py.File(data_dir + fileIN)\n", + " jetList_file = np.array(f.get(\"jetConstituentList\"))\n", + " target_file = np.array(f.get('jets')[0:,-6:-1])\n", + " jetImages_file = np.array(f.get('jetImage'))\n", + " jetList = np.concatenate([jetList, jetList_file], axis=0) if jetList.size else jetList_file\n", + " target_onehot = np.concatenate([target_onehot, target_file], axis=0) if target_onehot.size else target_file\n", + " jetImages = np.concatenate([jetImages, jetImages_file], axis=0) if jetImages.size else jetImages_file\n", + " del jetList_file, target_file, jetImages_file\n", + " #save particles/nodes features names and their indecies in a dictionary\n", + " if i_f==0:\n", + " for feat_idx,feat_name in enumerate(list(f['particleFeatureNames'])[:-1]):\n", + " features_names[feat_name.decode(\"utf-8\").replace('j1_','')] = feat_idx\n", + " f.close()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "7kQnL9vkP4rK" + }, + "source": [ + "The ground truth is incorporated in the ['j_g', 'j_q', 'j_w', 'j_z', 'j_t] vector of boolean, taking the form\n", + "* [1, 0, 0, 0, 0] for gluons\n", + "* [0, 1, 0, 0, 0] for quarks\n", + "* [0, 0, 1, 0, 0] for W\n", + "* [0, 0, 0, 1, 0] for Z \n", + "* [0, 0, 0, 0, 1] for top quarks\n", + "\n", + "This is what is called 'one-hot' encoding of a descrete label (typical of ground truth for classification problems). These labels are the 'target' for our classification tasks. Let's convert it back to single-column encoding :\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "84NSj2W7P477" + }, + "outputs": [], + "source": [ + "print(\"Labels for the first five entries in the dataset, one-hot encoded:\")\n", + "for i in range(5):\n", + " print(target_onehot[i])\n", + "print(target_onehot.shape)\n", + "target = np.argmax(target_onehot, axis=1)\n", + "print(target.shape)\n", + "print(\"Labels for the first five entries in the dataset, single column encoded:\")\n", + "for i in range(0,5):\n", + " print(target[i])" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "mqsd_aP__RIi" + }, + "source": [ + "Now our lables correspond to :\n", + "* 0 for gluons\n", + "* 1 for quarks\n", + "* 2 for W\n", + "* 3 for Z \n", + "* 4 for top quarks\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "hyP15oxhP5ek" + }, + "outputs": [], + "source": [ + "num_classes = len(np.unique(target))\n", + "label_names= [\"gluon\", \"quark\", \"W\", \"Z\", \"top\"]" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Ik-6OX0LMJW7" + }, + "source": [ + "Now let's inspect our data. Each jet is a point cloud/graph with 100 particles/nodes, each of which has 16 features. We have a double-index dataset: (jet index, particle index). The list is cut at 100 constituents per jet. If less constituents are present in the jet/point cloud, the dataset is completed filling it with 0s (zero padding). Note : zero-padding is not using during the training, it is only used to store the ragged dataset.\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "YfHRopq0P8tW" + }, + "outputs": [], + "source": [ + "print('Jets shape : ',jetList.shape)\n", + "print('Target/Labels shape : ',target.shape)\n", + "print('Particles/Nodes features : ',list(features_names.keys()))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "VBYwH4t8MhHm" + }, + "source": [ + "We are not interested in all features for now. For now we will only consider the same node features as were considered in the ParticleNet paper: ![Screenshot 2022-09-26 at 16.28.34.png](data:image/png;base64,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)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "QWtB3vTWP_QY" + }, + "outputs": [], + "source": [ + "features_to_consider = 'etarel,phirel,pt,e,ptrel,erel,deltaR'.split(',')\n", + "features_idx = [features_names[name] for name in features_to_consider]\n", + "jetList = jetList[:,:,features_idx]\n", + "print(jetList.shape)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "-M8uvPR4mfI7" + }, + "source": [ + "Let's define basics hyperparamters:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "2mHCuVm6ZJaY" + }, + "outputs": [], + "source": [ + "batch_size=128\n", + "learning_rate=0.0001\n", + "epochs=20" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "unpVhZNfmotI" + }, + "source": [ + "In the original paper, multi-head attention is also applied in the decoder step to obtain a smarter pooling operation. For this excercise we will simplify the model and use instead a `Lambda` layer to apply a custom pooling function to the input tensor. In this case, the `Lambda` layer is being used to sum over the first dimension, i.e. over the elements in the output set of the previous layer, which has shape `(batch_size, n_elements, features)`. By summing over the first dimension (`axis=1`), we obtain a tensor of shape `(batch_size, features)` that represents an aggregation of each feature over the elements in the set.\n", + "\n", + "Here is the full model:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "O7rzMn7wRcrP" + }, + "outputs": [], + "source": [ + "inputs = keras.Input(shape=(100,7), name='input')\n", + "x = layers.TimeDistributed(layers.Dense(64))(inputs)\n", + "x = layers.TimeDistributed(layers.LeakyReLU())(x)\n", + "x = layers.TimeDistributed(layers.Dense(64))(x)\n", + "x = layers.TimeDistributed(layers.LeakyReLU())(x)\n", + "x = layers.TimeDistributed(layers.Dense(64))(x)\n", + "x = layers.TimeDistributed(layers.LeakyReLU())(x)\n", + "x = layers.TimeDistributed(layers.Dense(64))(x)\n", + "x = layers.TimeDistributed(layers.LeakyReLU())(x)\n", + "x = layers.Lambda(lambda y: tf.reduce_sum(y, axis=1))(x)\n", + "x = layers.BatchNormalization()(x)\n", + "x = layers.Dense(64)(x)\n", + "x = layers.LeakyReLU()(x)\n", + "x = layers.Dense(64)(x)\n", + "x = layers.LeakyReLU()(x)\n", + "x = layers.Dense(16)(x)\n", + "x = layers.LeakyReLU()(x)\n", + "output = layers.Dense(5, dtype='float32')(x)\n", + "model = keras.models.Model(inputs=inputs, outputs=output)\n", + "model.summary()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "G8NI-_bYdSAq" + }, + "outputs": [], + "source": [ + "model.compile(\n", + " loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n", + " optimizer=keras.optimizers.Adam(learning_rate=learning_rate),\n", + " metrics=[keras.metrics.SparseCategoricalAccuracy()],\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "DhAKhgMMcrwa" + }, + "outputs": [], + "source": [ + "from sklearn.model_selection import train_test_split\n", + "X_train, X_val, y_train, y_val, y_train_onehot, y_val_onehot = train_test_split(jetList, target, target_onehot, test_size=0.1, shuffle=True)\n", + "print(X_train.shape, X_val.shape, y_train.shape, y_val.shape)\n", + "del jetList, target, target_onehot" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "lz7rfyeCdNF0" + }, + "outputs": [], + "source": [ + "history = model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Egcr8vMhp-2v" + }, + "source": [ + "We can now plot the validation and training loss evolution over the epochs:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "sjTOMuzAqGEr" + }, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt\n", + "fig,axes = plt.subplots(2)\n", + "\n", + "axes[0].plot(history.history[\"sparse_categorical_accuracy\"])\n", + "axes[0].plot(history.history[\"val_sparse_categorical_accuracy\"])\n", + "axes[0].set_title(\"Accuracy\")\n", + "axes[0].legend([\"Training\", \"Validation\"])\n", + "\n", + "axes[1].plot(history.history[\"loss\"])\n", + "axes[1].plot(history.history[\"val_loss\"])\n", + "axes[1].legend([\"Training\", \"Validation\"])\n", + "axes[1].set_title(\"Loss\")\n", + "\n", + "fig.show()\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "CwrPPStDrS4J" + }, + "source": [ + "Now we finally evaluate the performance by plotting the ROC curves for the different classes:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "JKM0yYFfecJh" + }, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "%matplotlib inline\n", + "from sklearn.metrics import roc_curve, auc\n", + "predict_val = tf.nn.softmax(model.predict(X_val))\n", + "df = pd.DataFrame()\n", + "fpr = {}\n", + "tpr = {}\n", + "auc1 = {}\n", + "\n", + "plt.figure()\n", + "for i, label in enumerate(label_names):\n", + "\n", + " df[label] = y_val_onehot[:,i]\n", + " df[label + '_pred'] = predict_val[:,i]\n", + "\n", + " fpr[label], tpr[label], threshold = roc_curve(df[label],df[label+'_pred'])\n", + "\n", + " auc1[label] = auc(fpr[label], tpr[label])\n", + "\n", + " plt.plot(tpr[label],fpr[label],label='%s tagger, auc = %.1f%%'%(label,auc1[label]*100.))\n", + "plt.semilogy()\n", + "plt.xlabel(\"sig. efficiency\")\n", + "plt.ylabel(\"bkg. mistag rate\")\n", + "plt.ylim(0.000001,1)\n", + "plt.grid(True)\n", + "plt.legend(loc='lower right')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "IzxPDanrrYZB" + }, + "source": [ + "As you can see the performance are not as good for other models we have trained on the same dataset. As mentioned at the beginning of the notebook training a transformer might be tricky. You can try the optional excercise below to improve the performance and surpass the other models." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Multi Head Attention recap\n", + "\n", + "Assume we have $n$ query vectors (corresponding to the $n$ elements in the set) each with dimension $d_q : Q \\in \\mathbb{R}^{n\\times d_q}$. In the jet tagging dataset $n=100$ and $d_q=7$.\n", + "\n", + "An attention function $\\mathrm{Att}(Q,K,V)$ is a function that maps queries $Q$ to outputs using $n_v$ key-value pairs $K \\in \\mathbb{R}^{n_v \\times d_q}, V \\in \\mathbb{R}^{n_v\\times d_v}$:\n", + "\n", + "$$\n", + "\\mathrm{Att}(Q,K,V;\\omega) = \\omega(QK^{T})V.\n", + "$$\n", + "\n", + "The pairwise dot product $QT^\\mathrm{T} \\in \\mathbb{R}^{n\\times n_v}$ measures how similar each pair of query and key vectors is, with weights computed with an activation function $\\omega$. The output $\\omega(QK^{T})V$ is a weighted sum of $V$ where a value gets more weight if its corresponding key has larger dot product with the query.\n", + "\n", + "Instead of computing a single attention function, the **multi-head attention** method first projects $Q, K, V$ onto $h$ different $d^M_q,d^M_q,d^M_v$-dimensional vectors, respectively. An attention function $\\mathrm{Att}(\\cdot; \\omega_j)$ is applied to each of these $h$ projections. The output is a linear transformation of the concatenation of all attention outputs:\n", + "\n", + "$$\n", + "\\mathrm{Multihead}(Q, K, V ; \\lambda, \\omega) = \\mathrm{concat}(O_1,..., O_h)W^O\n", + "$$\n", + "\n", + "$$\n", + "O_j = \\mathrm{Att}(QW^Q_j, KW^K_j, VW^V_j ; \\omega_j )\n", + "$$\n", + "\n", + "In other words, the model tells you what is the score of a particle in the set knowing its interaction with the other particles in the set given all features but in a way that the features are attended separately.\n", + "\n", + "Note that $\\mathrm{Multihead}(\\cdot, \\cdot, \\cdot; \\lambda)$ has learnable parameters $\\lambda =$ {$W^Q_j, W^K_j, W^V_j$}$_{j=1,...,h}$ where $W^Q_j, W^K_j \\in \\mathbb{R}^{d_q\\times d^M_q}, W^V_j \\in \\mathbb{R}^{d_v\\times d^M_v}, W^O \\in \\mathbb{R}^{hd^M_v\\times d}$. A typical choice for the dimension hyperparameters is $d^M_q = d_q /h, d^M_v = d_v /h, d = d_q$. For the Set Transformer we set $d_q = d_v = d$ and $d^M_q = d^M_v = d/h$. A scaled softmax $\\omega_j (\\cdot) = \\mathrm{softmax}(\\cdot/\\sqrt{d})$ is used.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Building the Set Transformer\n", + "\n", + "We will implement a simplified version of the [original Set Transformer architecture](https://arxiv.org/abs/1810.00825). The reason is because Transformers are typically computationally and data hungry. As an optional excercise at the end of the notebook you can try to implement the full model and test it on a simpler problem like the MNIST dataset classification (or on a larger jet class dataset).\n", + "\n", + "The architecture is based on the block called `MAB` (= Multihead Attention Block) which implements the following:\n", + "\n", + "$$\n", + "\\mathrm{MAB}(X, Y) = \\mathrm{LayerNorm}(H + \\mathrm{rFF}(H))\n", + "$$\n", + "\n", + "$$\n", + "H = \\mathrm{LayerNorm}(X + \\mathrm{Multihead}(X, X, X ; ω))\n", + "$$\n", + "\n", + "where $X \\in \\mathbb{R}^{n\\times d}$ is the input set and $\\mathrm{rFF}$ is any feedforward layer. Since $Q=K=V=X$, the MAB takes a set and performs *self-attention* between the elements in the set, resulting in a set of equal size. Since the output of MAB contains information about pairwise interactions among the elements in the input set $X$, we can stack multiple MABs to encode higher order interactions. This stack is the *encoder* part of the transformer. \n", + "\n", + "The `LayerNorm` normalizes the activations of a layer across the last dimension (feature dimension) of the input tensor. Specifically, it centers and scales each feature dimension independently by subtracting the mean and dividing by the standard deviation, which are computed over the corresponding feature dimension of the input tensor. As for `BatchNormalization` it has learnable $\\gamma$ (scaling) and $\\beta$ (shifting) parameters. The difference with respect to `BatchNormalization` is that the normalization is performed indipendently per each instance in the batch. `LayerNorm` leads to improved stability when you expect instances of different sizes (or different zero padding degree as in the jet tagging case)." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "RORSIHwVRPx4" + }, + "outputs": [], + "source": [ + "class SABTransformerBlock(tf.keras.layers.Layer):\n", + " def __init__(self, num_heads, hidden_units, mlp_hidden_units=128, dropout_rate=0.1, **kwargs):\n", + " super(SABTransformerBlock, self).__init__(**kwargs)\n", + " self.num_heads = num_heads\n", + " self.hidden_units = hidden_units\n", + " self.mlp_hidden_units = mlp_hidden_units\n", + " self.dropout_rate = dropout_rate\n", + "\n", + " def build(self, input_shape):\n", + " self.attention = tf.keras.layers.MultiHeadAttention(num_heads=self.num_heads, \n", + " key_dim=self.hidden_units//self.num_heads)\n", + " self.feedforward = tf.keras.Sequential([\n", + " Dense(units=self.mlp_hidden_units, activation=\"relu\"),\n", + " # Dropout(rate=self.dropout_rate),\n", + " Dense(units=input_shape[-1])\n", + " ])\n", + " self.layer_norm1 = LayerNormalization(epsilon=1e-6)\n", + " self.layer_norm2 = LayerNormalization(epsilon=1e-6)\n", + " self.dropout1 = Dropout(rate=self.dropout_rate)\n", + " self.dropout2 = Dropout(rate=self.dropout_rate)\n", + " super(SABTransformerBlock, self).build(input_shape)\n", + " \n", + " def call(self, inputs, mask=None):\n", + " attention_output = self.attention(inputs, inputs, attention_mask=mask)[0]\n", + " # attention_output = self.dropout1(attention_output)\n", + " attention_output = self.layer_norm1(inputs + attention_output)\n", + " feedforward_output = self.feedforward(attention_output)\n", + " # feedforward_output = self.dropout2(feedforward_output)\n", + " block_output = self.layer_norm2(attention_output + feedforward_output)\n", + " return block_output\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "inputs = keras.Input(shape=(100,7), name='input')\n", + "x = layers.TimeDistributed(layers.Dense(64))(inputs)\n", + "x = SABTransformerBlock(num_heads=8, hidden_units=64)(x)\n", + "x = SABTransformerBlock(num_heads=8, hidden_units=64)(x)\n", + "x = SABTransformerBlock(num_heads=8, hidden_units=64)(x)\n", + "x = layers.Lambda(lambda y: tf.reduce_sum(y, axis=1))(x)\n", + "x = layers.BatchNormalization()(x)\n", + "x = layers.Dense(64)(x)\n", + "x = layers.LeakyReLU()(x)\n", + "x = layers.Dense(64)(x)\n", + "x = layers.LeakyReLU()(x)\n", + "x = layers.Dense(16)(x)\n", + "x = layers.LeakyReLU()(x)\n", + "output = layers.Dense(5, dtype='float32')(x)\n", + "model_st = keras.models.Model(inputs=inputs, outputs=output)\n", + "model.summary()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "model.compile(\n", + " loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n", + " optimizer=keras.optimizers.Adam(learning_rate=learning_rate),\n", + " metrics=[keras.metrics.SparseCategoricalAccuracy()],\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "history = model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt\n", + "fig,axes = plt.subplots(2)\n", + "\n", + "axes[0].plot(history.history[\"sparse_categorical_accuracy\"])\n", + "axes[0].plot(history.history[\"val_sparse_categorical_accuracy\"])\n", + "axes[0].set_title(\"Accuracy\")\n", + "axes[0].legend([\"Training\", \"Validation\"])\n", + "\n", + "axes[1].plot(history.history[\"loss\"])\n", + "axes[1].plot(history.history[\"val_loss\"])\n", + "axes[1].legend([\"Training\", \"Validation\"])\n", + "axes[1].set_title(\"Loss\")\n", + "\n", + "fig.show()\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Now we finally evaluate the performance by plotting the ROC curves for the different classes:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "%matplotlib inline\n", + "from sklearn.metrics import roc_curve, auc\n", + "predict_val = tf.nn.softmax(model.predict(X_val))\n", + "df = pd.DataFrame()\n", + "fpr = {}\n", + "tpr = {}\n", + "auc1 = {}\n", + "\n", + "plt.figure()\n", + "for i, label in enumerate(label_names):\n", + "\n", + " df[label] = y_val_onehot[:,i]\n", + " df[label + '_pred'] = predict_val[:,i]\n", + "\n", + " fpr[label], tpr[label], threshold = roc_curve(df[label],df[label+'_pred'])\n", + "\n", + " auc1[label] = auc(fpr[label], tpr[label])\n", + "\n", + " plt.plot(tpr[label],fpr[label],label='%s tagger, auc = %.1f%%'%(label,auc1[label]*100.))\n", + "plt.semilogy()\n", + "plt.xlabel(\"sig. efficiency\")\n", + "plt.ylabel(\"bkg. mistag rate\")\n", + "plt.ylim(0.000001,1)\n", + "plt.grid(True)\n", + "plt.legend(loc='lower right')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Optional Excercise\n", + "\n", + "The original paper also use MH mechanism in the decoder step (while we used a simple sum over the latent space nodes). If you would like to try it out the `Lambda` layer should be replaced with the `PoolingByMultiHeadAttention` block below.\n", + "\n", + "Consider also the fact that it might be hard to train a Transformer architecture of this kind over the rather small dataset used here. Check out [this other dataset](https://events.mcs.cmu.edu/us-cms-2023/) for increased statistics or [this notebook](https://github.com/DLii-Research/tf-settransformer/blob/master/examples/mnist_pointcloud.ipynb) for a simpler task.\n", + "\n", + "Below is the starting point for a smarter decoder:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "9qHj1_Y7ZU-R" + }, + "outputs": [], + "source": [ + "class PoolingByMultiHeadAttention(tf.keras.layers.Layer):\n", + " def __init__(self, num_heads, hidden_units, mlp_hidden_units=128, num_seeds=1, **kwargs):\n", + " super(PoolingByMultiHeadAttention, self).__init__(**kwargs)\n", + " self.num_heads = num_heads\n", + " self.hidden_units = hidden_units\n", + " self.mlp_hidden_units = mlp_hidden_units\n", + " self.num_seeds = num_seeds\n", + " \n", + " def build(self, input_shape):\n", + " \n", + " self.attention = tf.keras.layers.MultiHeadAttention(num_heads=self.num_heads, \n", + " key_dim=self.hidden_units)\n", + " \n", + " self.seed_vectors = self.add_weight(\n", + " shape=(1, self.num_seeds, self.hidden_units),\n", + " initializer=\"random_normal\",\n", + " trainable=True,\n", + " name=\"Seeds\")\n", + "\n", + " self.feedforward = tf.keras.Sequential([\n", + " layers.Dense(units=self.mlp_hidden_units, activation=\"relu\"),\n", + " layers.Dense(units=self.hidden_units)\n", + " ])\n", + " self.layer_norm1 = layers.LayerNormalization(epsilon=1e-6)\n", + " self.layer_norm2 = layers.LayerNormalization(epsilon=1e-6)\n", + " super(PoolingByMultiHeadAttention, self).build(input_shape)\n", + "\n", + " def call(self, inputs, training=None):\n", + " a = tf.expand_dims(self.seed_vectors, axis=0)\n", + " seeds = tf.tile(self.seed_vectors, [tf.shape(inputs)[0], 1, 1])\n", + " attention_output = self.attention(seeds, inputs)[0]\n", + " attention_output = self.layer_norm1(seeds + attention_output)\n", + " feedforward_output = self.feedforward(attention_output)\n", + " block_output = self.layer_norm2(attention_output + feedforward_output)\n", + " return block_output" + ] + } + ], + "metadata": { + "accelerator": "GPU", + "colab": { + "authorship_tag": "ABX9TyPn4xtio5MeIQMG/e23naQt", + "include_colab_link": true, + "provenance": [] + }, + "gpuClass": "standard", + "kernelspec": { + "display_name": "Python 3", + "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": "3.9.16" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +}