Update AUTODRI_baseline.ipynb

b7c93e4a · ashivani · 1c88ea9e · b7c93e4a
Commit b7c93e4a authored 4 years ago by ashivani
--- a/baselines/AUTODRI_baseline.ipynb
+++ b/baselines/AUTODRI_baseline.ipynb
@@ -97,9 +97,9 @@
        "!rm -rf data/\n",
        "!mkdir data/\n",
        "\n",
-        "!curl https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/train.zip\n",
+        "!wget https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/train.zip\n",
-        "!curl https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/test.zip\n",
+        "!wget https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/test.zip\n",
-        "!curl https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/val.zip\n",
+        "!wget https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/val.zip\n",
        "!unzip train.zip  \n",
        "!unzip test.zip \n",
        "!unzip val.zip\n",

 %% Cell type:markdown id: tags:
 ![AIcrowd-Logo](https://raw.githubusercontent.com/AIcrowd/AIcrowd/master/app/assets/images/misc/aicrowd-horizontal.png)
 %% Cell type:markdown id: tags:
 # Baseline for [AUTODRI Challenge](https://www.aicrowd.com/challenges/autodri) on AIcrowd
 #### Author : Ayush Shivani
 %% Cell type:markdown id: tags:
 ## Download Necessary Packages
 %% Cell type:code id: tags:
 ``` python
 import sys
 !pip install numpy
 !pip install pandas
 !pip install scikit-learn
 !pip install matplotlib tqdm
 ```
 %% Cell type:markdown id: tags:
 ## Download data
 The first step is to download the training data and the test data
 %% Cell type:code id: tags:
 ``` python
 # #Donwload the datasets
 !rm -rf data/
 !mkdir data/
-!curl https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/train.zip
+!wget https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/train.zip
-!curl https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/test.zip
+!wget https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/test.zip
-!curl https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/val.zip
+!wget https://datasets.aicrowd.com/default/aicrowd-practice-challenges/public/autodri/v0.1/val.zip
 !unzip train.zip
 !unzip test.zip
 !unzip val.zip
 !mv train data/train
 !mv test data/test
 !mv val data/val
 ```
 %% Cell type:code id: tags:
 ``` python
 ## Now the data is available at the following locations:
 TRAINING_IMAGES_FOLDER = "data/train/cameraFront"
 TRAINING_LABELS_PATH = "data/train/train.csv"
 TESTING_LABELS_PATH = "data/test/test.csv"
 TESTING_IMAGES_FOLDER = "data/test/cameraFront"
 # For this baseline, we will only be using the front camera angle of the car just for demonstration purpose. For actual one should try and see the best combination of all the angles
 ```
 %% Cell type:markdown id: tags:
 ## Import packages
 %% Cell type:code id: tags:
 ``` python
 import os
 import tqdm
 import pandas as pd
 import numpy as np
 from sklearn.model_selection import train_test_split
 from sklearn.neural_network import MLPRegressor
 from sklearn.metrics import mean_squared_error,mean_absolute_error
 import matplotlib.pyplot as plt
 %matplotlib inline
 from PIL import Image
 ```
 %% Cell type:markdown id: tags:
 ## Load Data
 We use PIL library to load our images. Here we are creating our array where our input features are the mean colours and output features are the rotations along the x axis.
 %% Cell type:code id: tags:
 ``` python
 training_labels_df = pd.read_csv(TRAINING_LABELS_PATH)
 def pre_process_data_X(image):
    """
    This file takes a loaded image and returns a particular
    representation of the data point
    NOTE: This current baseline implements a **very** silly approach
    of representing every image by the mean RGB values for every image.
    You are encourage to try to alternate representations of the data,
    or figure out how to learn the best representation from the data ;)
    """
    im_array = np.array(im)
    mean_rgb = im_array.mean(axis=(0, 1))
    return mean_rgb
 ALL_DATA = []
 for _idx, row in tqdm.tqdm(training_labels_df.iterrows(), total=training_labels_df.shape[0]):
    filepath = os.path.join(
        TRAINING_IMAGES_FOLDER,
        row.filename
    )
    im = Image.open(filepath)
    data_X = pre_process_data_X(im)
    data_Y = [row.canSteering]
    ALL_DATA.append((data_X, data_Y))
 ```
 %% Cell type:markdown id: tags:
 ## Exploratory Data Analysis
 We now see the kind of images the dataset contains to get a better idea.
 %% Cell type:code id: tags:
 ``` python
 plt.figure(figsize=(20,20))
 for i in range(16):
  filename,xRot = training_labels_df.iloc[i]
  filepath = os.path.join(
        TRAINING_IMAGES_FOLDER,
        filename
    )
  im = Image.open(filepath)
  plt.subplot(4,4,i+1)
  plt.axis('off')
  plt.title("canSteering: %.3f"%(xRot))
  plt.imshow(im)
 ```
 %% Cell type:markdown id: tags:
 ## Split Data into Train and Validation
 We split the dataset into Training data and Validation datasets to help us test the generalizability of our models, and to ensure that we are not overfitting on the training set.
 %% Cell type:code id: tags:
 ``` python
 training_set, validation_set= train_test_split(ALL_DATA, test_size=0.2, random_state=42)
 ```
 %% Cell type:markdown id: tags:
 Here we have selected the size of the testing data to be 20% of the total data. You can change it and see what effect it has on the accuracies. To learn more about the train_test_split function [click here](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html).
 %% Cell type:markdown id: tags:
 Now, since we have our data splitted into train and validation sets, we need to get the label separated from the data.
 %% Cell type:code id: tags:
 ``` python
 X_train, y_train = zip(*training_set)
 X_val, y_val = zip(*validation_set)
 X_train = np.array(X_train)
 y_train = np.array(y_train)
 X_val = np.array(X_val)
 y_val = np.array(y_val)
 ```
 %% Cell type:markdown id: tags:
 ## Define the Classifier
 Now we finally come to the juicy part.
 Now that all the data is all loaded and available nice, we can finally get to training the classifier. Here we use sklearn [`MLPRegressor`](https://scikit-learn.org/stable/modules/generated/sklearn.neural_network.MLPRegressor.html) to train our network. We can tune the hyper parameters based on cross validation scores
 %% Cell type:code id: tags:
 ``` python
 model = MLPRegressor(hidden_layer_sizes=[10, 10], verbose=True)
 # NOTE : This is again silly hyper parameter instantiation of this problem,
 # and we encourage you to explore what works the best for you.
 ```
 %% Cell type:markdown id: tags:
 ## Train the classifier
 %% Cell type:code id: tags:
 ``` python
 model.fit(X_train, y_train)
 ```
 %% Cell type:markdown id: tags:
 ## Predict on Validation
 Now we predict our trained classifier on the validation set and evaluate our model
 %% Cell type:code id: tags:
 ``` python
 y_pred = model.predict(X_val)
 ```
 %% Cell type:markdown id: tags:
 ## Evaluate the Performance
 We use the same metrics as that will be used for the test set.
 [MAE](https://en.wikipedia.org/wiki/Mean_absolute_error) and [RMSE](https://www.statisticshowto.com/rmse/) are the metrics for this challenge
 %% Cell type:code id: tags:
 ``` python
 print('Mean Absolute Error:', mean_absolute_error(y_val, y_pred))
 print('Mean Squared Error:', mean_squared_error(y_val, y_pred))
 print('Root Mean Squared Error:', np.sqrt(mean_squared_error(y_val, y_pred)))
 ```
 %% Cell type:markdown id: tags:
 ## Load Test Set
 Load the test data now
 %% Cell type:code id: tags:
 ``` python
 import glob
 testing_labels_df = pd.read_csv(TESTING_LABELS_PATH)
 TEST_DATA = []
 TEST_FILENAMES = []
 for _idx, row in tqdm.tqdm(testing_labels_df.iterrows(), total=testing_labels_df.shape[0]):
    filepath = os.path.join(
        TESTING_IMAGES_FOLDER,
        row.filename
    )
    print(filepath)
    im = Image.open(filepath)
    data_X = pre_process_data_X(im)
    TEST_DATA.append(data_X)
    TEST_FILENAMES.append(row.filename)
 ```
 %% Cell type:markdown id: tags:
 ## Make predictions on the test set
 %% Cell type:code id: tags:
 ``` python
 test_predictions = model.predict(TEST_DATA)
 ```
 %% Cell type:code id: tags:
 ``` python
 test_predictions.shape
 ```
 %% Cell type:code id: tags:
 ``` python
 test_df = pd.DataFrame(test_predictions, columns=['canSteering'])
 test_df["filename"] = TEST_FILENAMES
 ```
 %% Cell type:code id: tags:
 ``` python
 test_df.shape
 ```
 %% Cell type:markdown id: tags:
 ## Save the prediction to csv
 %% Cell type:code id: tags:
 ``` python
 test_df.to_csv('submission.csv', index=False)
 ```
 %% Cell type:markdown id: tags:
 **Note**: Do take a look at the submission format.The submission file should contain the following header : `filename,xRot`.
 %% Cell type:markdown id: tags:
 ## To download the generated csv in Google Colab run the below command
 %% Cell type:code id: tags:
 ``` python
 from google.colab import files
 files.download('submission.csv')
 ```
 %% Cell type:markdown id: tags:
 ### Well Done! 👍 We are all set to make a submission and see your name on leaderborad. Lets navigate to [challenge page](https://www.aicrowd.com/challenges/autodri) and make one.
 %% Cell type:code id: tags:
 ``` python
 ```