2주차 과제

1_파이썬과_기계학습_기초_실습.ipynb

@@ -0,0 +1,190 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/poroblem/22-hub-kr-practice/blob/main/1_%ED%8C%8C%EC%9D%B4%EC%8D%AC%EA%B3%BC_%EA%B8%B0%EA%B3%84%ED%95%99%EC%8A%B5_%EA%B8%B0%EC%B4%88_%EC%8B%A4%EC%8A%B5.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "NCnlTCUlgQLb"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "import pandas as pd"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from sklearn.datasets import fetch_california_housing\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.linear_model import LinearRegression\n",
+        "from sklearn.metrics import r2_score"
+      ],
+      "metadata": {
+        "id": "GoR_tS6_g9sQ"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dataset = fetch_california_housing()\n",
+        "\n",
+        "print(dataset.DESCR)"
+      ],
+      "metadata": {
+        "id": "YkBBt3WVg_8_"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(dataset)"
+      ],
+      "metadata": {
+        "id": "VUaZDpz1yEEs"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "x_data = pd.DataFrame(dataset.data, columns=dataset.feature_names)\n",
+        "y_data = pd.DataFrame(dataset.target)\n",
+        "\n",
+        "print(x_data)\n",
+        "print(y_data)"
+      ],
+      "metadata": {
+        "id": "fhSBqGZ9iplE"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(x_data.shape)"
+      ],
+      "metadata": {
+        "id": "e2b9w7ddkns2"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(x_data.describe())"
+      ],
+      "metadata": {
+        "id": "kg_Pyot3kyAE"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "x_train, x_test, y_train, y_test = train_test_split(x_data, y_data, test_size=0.3)\n",
+        "\n",
+        "print(x_train)\n",
+        "print(y_train)"
+      ],
+      "metadata": {
+        "id": "KmU9_rezjTv8"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(x_test)\n",
+        "print(y_test)"
+      ],
+      "metadata": {
+        "id": "5akAx1xtveHQ"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "estimator = LinearRegression()"
+      ],
+      "metadata": {
+        "id": "IJ66-fbWj_OX"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "estimator.fit(x_train, y_train)"
+      ],
+      "metadata": {
+        "id": "TZH1Daf6kXps"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "y_predict = estimator.predict(x_train)\n",
+        "score = r2_score(y_train, y_predict)\n",
+        "print(score) #1.0"
+      ],
+      "metadata": {
+        "id": "A38LYJB_kY4d"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "y_predict = estimator.predict(x_test)\n",
+        "score = r2_score(y_test, y_predict)\n",
+        "print(score) #1.0"
+      ],
+      "metadata": {
+        "id": "B2-GKCfMkZyL"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

pytorch_vision_googlenet.md

@@ -27,11 +27,19 @@ All pre-trained models expect input images normalized in the same way,
 i.e. mini-batches of 3-channel RGB images of shape `(3 x H x W)`, where `H` and `W` are expected to be at least `224`.
 The images have to be loaded in to a range of `[0, 1]` and then normalized using `mean = [0.485, 0.456, 0.406]`
 and `std = [0.229, 0.224, 0.225]`.
+다시 학습받은 모든 모델은 이미지를 같은 방법으로 인풋 이미지를 정규화할려고 기대한다.
+즉 작은 집단의 3종류의 RGB이미지의 모양은 `(3 x H x W)'이고, `H` 와 `W` 적어도 '224' 가 되길 기대한다.
+그 이미지들은 `[0, 1]` 범위안에 실려야하고, 그리고  `mean = [0.485, 0.456, 0.406]`와 `std = [0.229, 0.224, 0.225]`을 보통으로 사용한다.
+@@
+
 
 Here's a sample execution.
+예시 예제가 있다
+
 
 ```python
 # Download an example image from the pytorch website
+# 파이토치 웹사이트에서 예시 그림을 다운받아라 
 import urllib
 url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
 try: urllib.URLopener().retrieve(url, filename)
@@ -40,6 +48,7 @@ except: urllib.request.urlretrieve(url, filename)
 
 ```python
 # sample execution (requires torchvision)
+# 실행 예제 ('torchvision'을 요구한다)
 from PIL import Image
 from torchvision import transforms
 input_image = Image.open(filename)
@@ -51,17 +60,20 @@ preprocess = transforms.Compose([
 ])
 input_tensor = preprocess(input_image)
 input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model
-
+                                        # 모델에서 요구되는 미니-배치를 생성하라
 # move the input and model to GPU for speed if available
+# 속도를 위해 가능하다면 'input'과 'model'을 'GPU'로 옮겨라
 if torch.cuda.is_available():
     input_batch = input_batch.to('cuda')
     model.to('cuda')
 
 with torch.no_grad():
     output = model(input_batch)
 # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
+# 'Imagenet'의 1000 classes 보다 높은 confidence scores와 함께 'Tensor'의 모양을 1000으로 하여라
 print(output[0])
 # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
+# 결과는 비정상적인 scores다. 개연성을 가질려면 softmax를 실행 할 수도 있다
 probabilities = torch.nn.functional.softmax(output[0], dim=0)
 print(probabilities)
 ```
@@ -86,6 +98,10 @@ for i in range(top5_prob.size(0)):
 
 GoogLeNet was based on a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014). The 1-crop error rates on the ImageNet dataset with a pretrained model are list below.
 
+### 모델 설명
+
+'GoogLeNet'은 "Inception"이라고 암호화된 이름으로 나선형의 심층 신경망의 아키텍쳐에 기반은 둔 새로운상태의 예술의 분류와 'ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014)'의 발견에 책임이있다
+
 | Model structure | Top-1 error | Top-5 error |
 | --------------- | ----------- | ----------- |
 |  googlenet       | 30.22       | 10.47       |
@@ -95,3 +111,6 @@ GoogLeNet was based on a deep convolutional neural network architecture codename
 ### References
 
  - [Going Deeper with Convolutions](https://arxiv.org/abs/1409.4842)
+### 참조
+
+ - [Going Deeper with Convolutions](https://arxiv.org/abs/1409.4842)