cs231_features

features 作业

features原理

1. 改变只将原图的像素作为特征表示，将原图的hog特征，作为该图的特征表示
2. 改变只将原图的像素作为特征表示，将原图的颜色直方图作为该图的特征表示

features.ipynb

1. 训练SVM on features

   # Use the validation set to tune the learning rate and regularization strength
   
   from cs231n.classifiers.linear_classifier import LinearSVM
   
   learning_rates = [1e-9, 1e-8, 1e-7]
   regularization_strengths = [5e4, 5e5, 5e6]
   
   results = {}
   best_val = -1
   best_svm = None
   
   pass
   ################################################################################
   # TODO:                                                                        #
   # Use the validation set to set the learning rate and regularization strength. #
   # This should be identical to the validation that you did for the SVM; save    #
   # the best trained classifer in best_svm. You might also want to play          #
   # with different numbers of bins in the color histogram. If you are careful    #
   # you should be able to get accuracy of near 0.44 on the validation set.       #
   ################################################################################
   for cur_lr in learning_rates:
       for cur_reg in regularization_strengths:
           svm = LinearSVM()
           svm.train(X_train_feats,y_train, learning_rate=cur_lr, reg=cur_reg,num_iters=1500,verbose=False)
           
           y_train_pred = svm.predict(X_train_feats)
           train_acc = np.mean(y_train==y_train_pred)
           
           y_val_pred = svm.predict(X_val_feats)
           val_acc = np.mean(y_val==y_val_pred)
           
           results[(cur_lr,cur_reg)] = (train_acc, val_acc)
           
           if val_acc > best_val:
               best_val = val_acc
               best_svm = svm
       
   ################################################################################
   #                              END OF YOUR CODE                                #
   ################################################################################
   
   # Print out results.
   for lr, reg in sorted(results):
       train_accuracy, val_accuracy = results[(lr, reg)]
       print('lr %e reg %e train accuracy: %f val accuracy: %f' % (
                   lr, reg, train_accuracy, val_accuracy))
       
   print('best validation accuracy achieved during cross-validation: %f' % best_val)
   

   最后结果为：

   [外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-98skmPKz-1618559810747)(C:\Users\vpmas\AppData\Roaming\Typora\typora-user-images\image-20210307202623873.png)]

   最终在test上的结果为

   [外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-StzLK0Kt-1618559810749)(C:\Users\vpmas\AppData\Roaming\Typora\typora-user-images\image-20210307202656367.png)]

   2. 利用特征的神经网络

      from cs231n.classifiers.neural_net import TwoLayerNet
      
      input_dim = X_train_feats.shape[1]
      hidden_dim = 200
      num_classes = 10
      
      
      best_net = None
      
      ################################################################################
      # TODO: Train a two-layer neural network on image features. You may want to    #
      # cross-validate various parameters as in previous sections. Store your best   #
      # model in the best_net variable.                                              #
      ################################################################################
      bestacc = 0
      for hidden_size in [hidden_dim]:
          for learning_rate in [1e-1,5e-1]:
              for learning_rate_decay in [0.999]:
                  for reg in [3e-4,1e-3,3e-3]:
                      net = TwoLayerNet(input_dim, hidden_dim, num_classes)
                      # Train the network
                      stats = net.train(X_train_feats, y_train, X_val_feats, y_val,
                                  num_iters=3000, batch_size=500,
                                  learning_rate=learning_rate, learning_rate_decay=learning_rate_decay,
                                  reg=reg, verbose=False)
      
                      # Predict on the validation set
                      val_acc = (net.predict(X_val_feats) == y_val).mean()
                      print('hidden_size = %d,learning_rate = %f,learning_rate_decay = %f,reg = %f,Validation accuracy =%f '%(hidden_size,learning_rate,learning_rate_decay,reg,val_acc))
                      if bestacc<val_acc:
                          bestacc = val_acc
                          best_net = net
      ################################################################################
      #                              END OF YOUR CODE                                #
      ################################################################################
      

      最终结果为：

      [外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-6lOGk5Nt-1618559810749)(C:\Users\vpmas\AppData\Roaming\Typora\typora-user-images\image-20210307202815449.png)]

questions

Inline question 1:

Describe the misclassification results that you see. Do they make sense?
错误的分类结果大部分与此类的可能出现的背景相似，因为这里是通过hog特征进行分类判断，即对应位置梯度接近的图像将被分为一类，因此具有相同hog特征的类将被分为一类，所以出现这类的情况比较合理。