diff --git a/README.md b/README.md index 5ecfae2..1e5fd2f 100644 --- a/README.md +++ b/README.md @@ -281,6 +281,7 @@ _Note: Below you can find the best lectures for popular Machine Learning Algorit - [CS131 Computer Vision: Foundations and Applications Fall 2019](http://vision.stanford.edu/teaching/cs131_fall1920/index.html) - [CS231A: Computer Vision, From 3D Reconstruction to Recognition Winter 2018](http://web.stanford.edu/class/cs231a/) +- [CS231n Convolutional Neural Networks for Visual Recognition](https://cs231n.github.io/) ### CNN diff --git a/autonomous_car/README.md b/autonomous_car/README.md index 845c805..aca1545 100644 --- a/autonomous_car/README.md +++ b/autonomous_car/README.md @@ -5,3 +5,7 @@ ## [waymo-open-dataset](https://github.com/waymo-research/waymo-open-dataset) Waymo Open Dataset https://www.waymo.com/open + +### MIT 6.S094: Deep Learning for Self-Driving Cars + +- [DeepTraffic](https://selfdrivingcars.mit.edu/deeptraffic/) diff --git a/gans/README.md b/gans/README.md index d9a5bec..d8ac645 100644 --- a/gans/README.md +++ b/gans/README.md @@ -36,6 +36,11 @@ Look at the papers I mentioned. Links in the link below - Papers - https://github.com/terryum/awesome-deep-learning-papers#new-papers - Ai blog - https://ai.googleblog.com/ +## Demo + +- [Image-to-Image Translation with Conditional Adversarial Nets](https://phillipi.github.io/pix2pix/) +- [Image-to-Image Demo](https://affinelayer.com/pixsrv/) _Interactive Image Translation with pix2pix-tensorflow_ + # Courses - [A to Z ML/DL](https://www.udemy.com/course/machinelearning/) diff --git a/webinars/computer_vision/Computer Vision Share.pdf b/webinars/computer_vision/Computer Vision Share.pdf new file mode 100644 index 0000000..dfe7aa1 Binary files /dev/null and b/webinars/computer_vision/Computer Vision Share.pdf differ diff --git a/webinars/decision_trees_and_random_forest/Ensemble_Methods.ipynb b/webinars/decision_trees_and_random_forest/Ensemble_Methods.ipynb new file mode 100644 index 0000000..61f3e67 --- /dev/null +++ b/webinars/decision_trees_and_random_forest/Ensemble_Methods.ipynb @@ -0,0 +1,195 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "Ensemble Methods.ipynb", + "provenance": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + } + }, + "cells": [ + { + "cell_type": "code", + "metadata": { + "id": "-mCmaGdYCtBc", + "colab_type": "code", + "colab": {} + }, + "source": [ + "# Load Library\n", + "from sklearn.datasets import make_moons\n", + "from sklearn.metrics import accuracy_score\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.tree import DecisionTreeClassifier\n", + "from sklearn.ensemble import RandomForestClassifier,AdaBoostClassifier,GradientBoostingClassifier" + ], + "execution_count": 0, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "4ja4yb4_CzlY", + "colab_type": "code", + "colab": {} + }, + "source": [ + "# Step1: Create data set\n", + "X, y = make_moons(n_samples=10000, noise=.5, random_state=0)" + ], + "execution_count": 0, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "WbIUBF8pdXUF", + "colab_type": "code", + "colab": {} + }, + "source": [ + "# Step2: Split the training test set\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)" + ], + "execution_count": 0, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "8vRma5CzC1id", + "colab_type": "code", + "outputId": "47d557ac-f8d7-4b3d-8fb8-94893afbc5fd", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 51 + } + }, + "source": [ + "# Step 3: Fit a Decision Tree model as comparison\n", + "clf = DecisionTreeClassifier()\n", + "clf.fit(X_train, y_train)\n", + "print(\" Train Accuracy\", accuracy_score(y_train, clf.predict(X_train)))\n", + "print(\" Test Accuracy\", accuracy_score(y_test, clf.predict(X_test)))" + ], + "execution_count": 15, + "outputs": [ + { + "output_type": "stream", + "text": [ + " Train Accuracy 1.0\n", + " Test Accuracy 0.751\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "LeoG6gvlC1oR", + "colab_type": "code", + "outputId": "42772dfc-410f-474d-c442-a940260ac783", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 51 + } + }, + "source": [ + "# Step 4: Fit a Random Forest model, \" compared to \"Decision Tree model, accuracy go up by 5%\n", + "clf = RandomForestClassifier(n_estimators=100, max_features=\"auto\",random_state=0)\n", + "clf.fit(X_train, y_train)\n", + "print(\" Train Accuracy\", accuracy_score(y_train, clf.predict(X_train)))\n", + "print(\" Test Accuracy\", accuracy_score(y_test, clf.predict(X_test)))" + ], + "execution_count": 16, + "outputs": [ + { + "output_type": "stream", + "text": [ + " Train Accuracy 1.0\n", + " Test Accuracy 0.7965\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "h_ntW2CiC1ll", + "colab_type": "code", + "outputId": "753a8327-e25f-4c2d-9d39-e3ee62c13192", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 51 + } + }, + "source": [ + "# Step 5: Fit a AdaBoost model, \" compared to \"Decision Tree model, accuracy go up by 10%\n", + "clf = AdaBoostClassifier(n_estimators=100)\n", + "clf.fit(X_train, y_train)\n", + "print(\" Train Accuracy\", accuracy_score(y_train, clf.predict(X_train)))\n", + "print(\" Test Accuracy\", accuracy_score(y_test, clf.predict(X_test)))" + ], + "execution_count": 17, + "outputs": [ + { + "output_type": "stream", + "text": [ + " Train Accuracy 0.825625\n", + " Test Accuracy 0.833\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "GXw2cMWuC92S", + "colab_type": "code", + "outputId": "ce935fdf-df0a-4405-e6d3-a41af02a7ae6", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 51 + } + }, + "source": [ + "# Step 6: Fit a Gradient Boosting model, \" compared to \"Decision Tree model, accuracy go up by 10%\n", + "clf = GradientBoostingClassifier(n_estimators=100)\n", + "clf.fit(X_train, y_train)\n", + "print(\" Train Accuracy\", accuracy_score(y_train, clf.predict(X_train)))\n", + "print(\" Test Accuracy\", accuracy_score(y_test, clf.predict(X_test)))" + ], + "execution_count": 18, + "outputs": [ + { + "output_type": "stream", + "text": [ + " Train Accuracy 0.829875\n", + " Test Accuracy 0.8335\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "QY37GWzl9CQD", + "colab_type": "code", + "colab": {} + }, + "source": [ + "" + ], + "execution_count": 0, + "outputs": [] + } + ] +} \ No newline at end of file