256, 256, 256, 10] ▪ 390K parameters ▪ 1.6MB memory ▪ 80386 http://slazebni.cs.illinois.edu/spring17/lec01_cnn_architectures.pdf Receptive Field https://medium.freecodecamp.org/an-intuitive-gui com/exdb/publis/pdf/lecun-89e.pdf Convolution Operation Rethink Linear layer http://slazebni.cs.illinois.edu/spring17/lec01_cnn_architectures.pdf Why call Convolution? Convolution https://www.superdatascience.

时间序列表示 主讲人：龙良曲 Spatial Signals Temporal Signals? Sequence http://slazebni.cs.illinois.edu/spring17/lec02_rnn.pdf Sequence representation ▪ [seq_len, feature_len] [100, 1] [28, 28] [words, word_vec]

○ Most implementations of recent deep learning papers ○ ... References ● Machine Learning 2021 Spring Pytorch Tutorial ● Official Pytorch Tutorials ● https://numpy.org/ Any questions?

'T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat’, 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot’ ] train_images = train_images / 255.0 test_images = test_images / 255.0 plt.figure(figsize=(8

3: ” Dress ” , 4: ”Coat” , 5: ” Sandal ” , 6: ” Shirt ” , 7: ” Sneaker ” , 8: ”Bag” , 9: ”Ankle␣Boot” , } import matplotlib . pyplot as plt f i g u r e = plt . f i g u r e () # 抽 取 索 引 为 100 的 数

2 Pullover 套头衫 3 Dress 连衣裙 4 Coat 外套 5 Sandal 凉鞋 6 Shirt 衬衫 7 Sneaker 运动鞋 8 Bag 背包 9 Ankle boot 短靴 用法： from keras.datasets import fashion_mnist (x_train, y_train), (x_test, y_test) = fashion_mnist

T恤）、trouser（裤子）、pullover（套衫）、dress（连衣 裙）、coat（外套）、sandal（凉鞋）、shirt（衬衫）、sneaker（运动鞋）、bag（包）和ankle boot（短靴）。以 下函数用于在数字标签索引及其文本名称之间进行转换。 def get_fashion_mnist_labels(labels): #@save """返回Fashion-MNIST数据集的文本标签""" = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat', 'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot'] return [text_labels[int(i)] for i in labels] 我们现在可以创建一个函数来可视化这些样本。 def show_images(imgs, num_rows