feat: add new Jupyter notebook for image transformation and dataset handling
This commit is contained in:
fada
53
03.ipynb
53
03.ipynb
@ -1,63 +1,30 @@
|
|||||||
{
|
{
|
||||||
"cells": [
|
"cells": [
|
||||||
{
|
{
|
||||||
|
"metadata": {},
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"id": "initial_id",
|
"outputs": [],
|
||||||
"metadata": {
|
"execution_count": null,
|
||||||
"collapsed": true,
|
|
||||||
"ExecuteTime": {
|
|
||||||
"end_time": "2025-06-11T07:39:14.997108Z",
|
|
||||||
"start_time": "2025-06-11T07:39:14.986047Z"
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"source": [
|
"source": [
|
||||||
"from PIL import Image\n",
|
"from PIL import Image\n",
|
||||||
"\n",
|
"\n",
|
||||||
"im = Image.open('./data/jk.jpg')\n",
|
"im = Image.open('data/images/jk.jpg')\n",
|
||||||
"im.size"
|
"im.size"
|
||||||
],
|
],
|
||||||
"outputs": [
|
"id": "306b84c8b2d7bc36"
|
||||||
{
|
|
||||||
"data": {
|
|
||||||
"text/plain": [
|
|
||||||
"(318, 116)"
|
|
||||||
]
|
|
||||||
},
|
},
|
||||||
"execution_count": 73,
|
{
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"output_type": "execute_result"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"execution_count": 73
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"metadata": {
|
|
||||||
"ExecuteTime": {
|
|
||||||
"end_time": "2025-06-11T07:39:22.279332Z",
|
|
||||||
"start_time": "2025-06-11T07:39:22.267501Z"
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
|
"outputs": [],
|
||||||
|
"execution_count": null,
|
||||||
"source": [
|
"source": [
|
||||||
"import numpy as np\n",
|
"import numpy as np\n",
|
||||||
"\n",
|
"\n",
|
||||||
"im_pillow = np.asarray(im)\n",
|
"im_pillow = np.asarray(im)\n",
|
||||||
"im_pillow.shape"
|
"im_pillow.shape"
|
||||||
],
|
],
|
||||||
"id": "e10b9e7640af00c9",
|
"id": "627463cc80a9eea4"
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"data": {
|
|
||||||
"text/plain": [
|
|
||||||
"(116, 318, 3)"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
"execution_count": 74,
|
|
||||||
"metadata": {},
|
|
||||||
"output_type": "execute_result"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"execution_count": 74
|
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"metadata": {
|
"metadata": {
|
||||||
@ -99,7 +66,7 @@
|
|||||||
"source": [
|
"source": [
|
||||||
"import cv2\n",
|
"import cv2\n",
|
||||||
"\n",
|
"\n",
|
||||||
"im_cv2 = cv2.imread('./data/jk.jpg')\n",
|
"im_cv2 = cv2.imread('./data/images/jk.jpg')\n",
|
||||||
"print(type(im_cv2))\n",
|
"print(type(im_cv2))\n",
|
||||||
"\n",
|
"\n",
|
||||||
"print(im_cv2.shape)"
|
"print(im_cv2.shape)"
|
||||||
|
|||||||
193
06.ipynb
193
06.ipynb
@ -16,8 +16,8 @@
|
|||||||
{
|
{
|
||||||
"metadata": {
|
"metadata": {
|
||||||
"ExecuteTime": {
|
"ExecuteTime": {
|
||||||
"end_time": "2025-06-12T12:58:38.694696Z",
|
"end_time": "2025-06-13T01:44:55.209362Z",
|
||||||
"start_time": "2025-06-12T12:58:38.690734Z"
|
"start_time": "2025-06-13T01:44:52.973675Z"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
@ -42,13 +42,13 @@
|
|||||||
],
|
],
|
||||||
"id": "1244f4325aad0ac5",
|
"id": "1244f4325aad0ac5",
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"execution_count": 64
|
"execution_count": 1
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"metadata": {
|
"metadata": {
|
||||||
"ExecuteTime": {
|
"ExecuteTime": {
|
||||||
"end_time": "2025-06-12T12:59:08.444392Z",
|
"end_time": "2025-06-13T01:44:55.286472Z",
|
||||||
"start_time": "2025-06-12T12:59:08.435084Z"
|
"start_time": "2025-06-13T01:44:55.230898Z"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
@ -66,27 +66,27 @@
|
|||||||
"name": "stdout",
|
"name": "stdout",
|
||||||
"output_type": "stream",
|
"output_type": "stream",
|
||||||
"text": [
|
"text": [
|
||||||
"tensor([[-1.1016, 0.8803, 1.3645],\n",
|
"tensor([[ 1.5479, 0.1374, 1.6763],\n",
|
||||||
" [ 0.6674, 0.4500, 0.0367],\n",
|
" [-0.5671, -0.0821, -1.8523],\n",
|
||||||
" [ 1.3528, 0.2438, 0.4721],\n",
|
" [-0.4039, -0.5871, -0.3510],\n",
|
||||||
" [-1.3651, -1.1315, 0.0299],\n",
|
" [-0.2339, 0.2773, -0.0820],\n",
|
||||||
" [ 1.4538, 1.3622, -0.5165],\n",
|
" [-0.3131, 0.5911, 0.2030],\n",
|
||||||
" [ 0.7515, 0.6168, -0.9036],\n",
|
" [-0.7087, -0.2614, -0.2661],\n",
|
||||||
" [ 1.3542, -0.3779, -1.2439],\n",
|
" [ 0.3220, -0.0340, -1.2429],\n",
|
||||||
" [-0.4588, -0.2233, -0.3531],\n",
|
" [-0.1282, -0.2188, -0.7576],\n",
|
||||||
" [-0.0515, 0.8951, 0.3544],\n",
|
" [ 1.1233, -0.2452, 0.4664],\n",
|
||||||
" [ 0.0181, 0.4075, -2.0888]])\n",
|
" [ 1.2570, 0.3728, 0.9745]])\n",
|
||||||
"tensor([0, 0, 1, 0, 0, 1, 1, 1, 1, 0])\n"
|
"tensor([0, 1, 1, 1, 0, 0, 0, 0, 0, 0])\n"
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
"execution_count": 66
|
"execution_count": 2
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"metadata": {
|
"metadata": {
|
||||||
"ExecuteTime": {
|
"ExecuteTime": {
|
||||||
"end_time": "2025-06-12T12:59:25.092189Z",
|
"end_time": "2025-06-13T01:44:55.610922Z",
|
||||||
"start_time": "2025-06-12T12:59:25.085985Z"
|
"start_time": "2025-06-13T01:44:55.606365Z"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
@ -95,7 +95,7 @@
|
|||||||
"my_dataset = MyDataset(data_tensor, target_tensor)\n",
|
"my_dataset = MyDataset(data_tensor, target_tensor)\n",
|
||||||
"\n",
|
"\n",
|
||||||
"# 查看数据集大小\n",
|
"# 查看数据集大小\n",
|
||||||
"print(\"dataset size：\",len(my_dataset))\n",
|
"print(\"dataset size：\", len(my_dataset))\n",
|
||||||
"\n",
|
"\n",
|
||||||
"# 使用索引获取数据\n",
|
"# 使用索引获取数据\n",
|
||||||
"print(\"data:\", my_dataset[0]) # 获取第一个数据"
|
"print(\"data:\", my_dataset[0]) # 获取第一个数据"
|
||||||
@ -107,11 +107,160 @@
|
|||||||
"output_type": "stream",
|
"output_type": "stream",
|
||||||
"text": [
|
"text": [
|
||||||
"dataset size： 10\n",
|
"dataset size： 10\n",
|
||||||
"data: (tensor([-1.1016, 0.8803, 1.3645]), tensor(0))\n"
|
"data: (tensor([1.5479, 0.1374, 1.6763]), tensor(0))\n"
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
"execution_count": 67
|
"execution_count": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"ExecuteTime": {
|
||||||
|
"end_time": "2025-06-13T01:48:47.876220Z",
|
||||||
|
"start_time": "2025-06-13T01:48:47.866170Z"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"cell_type": "code",
|
||||||
|
"source": [
|
||||||
|
"from torch.utils.data import DataLoader\n",
|
||||||
|
"\n",
|
||||||
|
"tensor_loader = DataLoader(dataset=my_dataset, batch_size=2, shuffle=True, num_workers=0)\n",
|
||||||
|
"\n",
|
||||||
|
"# 以循环的方式获取数据\n",
|
||||||
|
"for data, target in tensor_loader:\n",
|
||||||
|
" print(\"data:\", data)\n",
|
||||||
|
" print(\"target:\", target)\n",
|
||||||
|
"\n",
|
||||||
|
"print(\"one batch tensor data:\", next(iter(tensor_loader)))"
|
||||||
|
],
|
||||||
|
"id": "d78ddf04e79df9ae",
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"data: tensor([[ 0.3220, -0.0340, -1.2429],\n",
|
||||||
|
" [-0.2339, 0.2773, -0.0820]])\n",
|
||||||
|
"target: tensor([0, 1])\n",
|
||||||
|
"data: tensor([[-0.5671, -0.0821, -1.8523],\n",
|
||||||
|
" [-0.3131, 0.5911, 0.2030]])\n",
|
||||||
|
"target: tensor([1, 0])\n",
|
||||||
|
"data: tensor([[-0.1282, -0.2188, -0.7576],\n",
|
||||||
|
" [-0.4039, -0.5871, -0.3510]])\n",
|
||||||
|
"target: tensor([0, 1])\n",
|
||||||
|
"data: tensor([[-0.7087, -0.2614, -0.2661],\n",
|
||||||
|
" [ 1.2570, 0.3728, 0.9745]])\n",
|
||||||
|
"target: tensor([0, 0])\n",
|
||||||
|
"data: tensor([[ 1.5479, 0.1374, 1.6763],\n",
|
||||||
|
" [ 1.1233, -0.2452, 0.4664]])\n",
|
||||||
|
"target: tensor([0, 0])\n",
|
||||||
|
"one batch tensor data: [tensor([[ 0.3220, -0.0340, -1.2429],\n",
|
||||||
|
" [ 1.1233, -0.2452, 0.4664]]), tensor([0, 0])]\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"execution_count": 9
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"ExecuteTime": {
|
||||||
|
"end_time": "2025-06-13T01:53:08.605768Z",
|
||||||
|
"start_time": "2025-06-13T01:53:07.616662Z"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"cell_type": "code",
|
||||||
|
"source": "!pip install torchvision pillow",
|
||||||
|
"id": "b6845476dfd81659",
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"Requirement already satisfied: torchvision in /opt/conda/lib/python3.10/site-packages (0.17.1)\r\n",
|
||||||
|
"Requirement already satisfied: pillow in /opt/conda/lib/python3.10/site-packages (10.2.0)\r\n",
|
||||||
|
"Requirement already satisfied: numpy in /opt/conda/lib/python3.10/site-packages (from torchvision) (1.26.3)\r\n",
|
||||||
|
"Requirement already satisfied: torch in /opt/conda/lib/python3.10/site-packages (from torchvision) (2.2.1)\r\n",
|
||||||
|
"Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from torch->torchvision) (3.13.1)\r\n",
|
||||||
|
"Requirement already satisfied: typing-extensions>=4.8.0 in /opt/conda/lib/python3.10/site-packages (from torch->torchvision) (4.9.0)\r\n",
|
||||||
|
"Requirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from torch->torchvision) (1.12)\r\n",
|
||||||
|
"Requirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch->torchvision) (3.1)\r\n",
|
||||||
|
"Requirement already satisfied: jinja2 in /opt/conda/lib/python3.10/site-packages (from torch->torchvision) (3.1.3)\r\n",
|
||||||
|
"Requirement already satisfied: fsspec in /opt/conda/lib/python3.10/site-packages (from torch->torchvision) (2024.2.0)\r\n",
|
||||||
|
"Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.10/site-packages (from jinja2->torch->torchvision) (2.1.3)\r\n",
|
||||||
|
"Requirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->torch->torchvision) (1.3.0)\r\n",
|
||||||
|
"\u001B[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.\u001B[0m\u001B[33m\r\n",
|
||||||
|
"\u001B[0m"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"execution_count": 11
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"ExecuteTime": {
|
||||||
|
"end_time": "2025-06-13T02:12:21.816805Z",
|
||||||
|
"start_time": "2025-06-13T02:12:21.421202Z"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"cell_type": "code",
|
||||||
|
"source": [
|
||||||
|
"# 以MNIST数据集为例\n",
|
||||||
|
"import torchvision\n",
|
||||||
|
"\n",
|
||||||
|
"mnist_dataset = torchvision.datasets.MNIST(root=\"./data\", train=True, transform=None, target_transform=None,\n",
|
||||||
|
" download=True)"
|
||||||
|
],
|
||||||
|
"id": "f8112ef53ed2d0ce",
|
||||||
|
"outputs": [],
|
||||||
|
"execution_count": 13
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"ExecuteTime": {
|
||||||
|
"end_time": "2025-06-13T02:17:29.130555Z",
|
||||||
|
"start_time": "2025-06-13T02:17:28.225901Z"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"cell_type": "code",
|
||||||
|
"source": [
|
||||||
|
"mnist_dataset_list = list(mnist_dataset)\n",
|
||||||
|
"\n",
|
||||||
|
"display(mnist_dataset_list[0][0])\n",
|
||||||
|
"print(\"Image label is:\", mnist_dataset_list[0][1])"
|
||||||
|
],
|
||||||
|
"id": "9b9c1d2993b37bcd",
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"<PIL.Image.Image image mode=L size=28x28>"
|
||||||
|
],
|
||||||
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAABwAAAAcCAAAAABXZoBIAAAA90lEQVR4AWNgGMyAWUhIqK5jvdSy/9/rQe5kgTlWjs3KRiAYxHsyKfDzxYMgFiOIAALDvfwQBsO/pK8Mz97fhPLAlNDtvyBwbNv3j8jCUHbAnOy/f89yM2jPwiLJwMc4628UqgQTnPvp/0eGFAQXLg5lcO/764YuhuArf3y4IAfmfoQwlBX44e/fckkMYaiA7q6/f6dJ45IViP3zdzcuSQaGn39/OkBl4WEL4euFmLIwXDuETav6lKfAIPy1DYucRNFdUPCe9MOUE3e6CpI6FogZSEKrwbFyOIATQ5v5mkcgXV9auVGlwK4NDGRguL75b88HVDla8QBFF16ADQA8sQAAAABJRU5ErkJggg==",
|
||||||
|
"image/jpeg": "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"
|
||||||
|
},
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "display_data"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"Image label is: 5\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"ename": "AttributeError",
|
||||||
|
"evalue": "'list' object has no attribute 'size'",
|
||||||
|
"output_type": "error",
|
||||||
|
"traceback": [
|
||||||
|
"\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
|
||||||
|
"\u001B[0;31mAttributeError\u001B[0m Traceback (most recent call last)",
|
||||||
|
"Cell \u001B[0;32mIn[23], line 6\u001B[0m\n\u001B[1;32m 3\u001B[0m display(mnist_dataset_list[\u001B[38;5;241m0\u001B[39m][\u001B[38;5;241m0\u001B[39m])\n\u001B[1;32m 4\u001B[0m \u001B[38;5;28mprint\u001B[39m(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mImage label is:\u001B[39m\u001B[38;5;124m\"\u001B[39m, mnist_dataset_list[\u001B[38;5;241m0\u001B[39m][\u001B[38;5;241m1\u001B[39m])\n\u001B[0;32m----> 6\u001B[0m \u001B[38;5;28mprint\u001B[39m(\u001B[38;5;28;43mlist\u001B[39;49m\u001B[43m(\u001B[49m\u001B[43mmnist_dataset_list\u001B[49m\u001B[43m)\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43msize\u001B[49m)\n",
|
||||||
|
"\u001B[0;31mAttributeError\u001B[0m: 'list' object has no attribute 'size'"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"execution_count": 23
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
"metadata": {
|
"metadata": {
|
||||||
|
|||||||
BIN
data/MNIST/raw/t10k-images-idx3-ubyte
Normal file
BIN
data/MNIST/raw/t10k-images-idx3-ubyte
Normal file
Binary file not shown.
BIN
data/MNIST/raw/t10k-images-idx3-ubyte.gz
Normal file
BIN
data/MNIST/raw/t10k-images-idx3-ubyte.gz
Normal file
Binary file not shown.
BIN
data/MNIST/raw/t10k-labels-idx1-ubyte
Normal file
BIN
data/MNIST/raw/t10k-labels-idx1-ubyte
Normal file
Binary file not shown.
BIN
data/MNIST/raw/t10k-labels-idx1-ubyte.gz
Normal file
BIN
data/MNIST/raw/t10k-labels-idx1-ubyte.gz
Normal file
Binary file not shown.
BIN
data/MNIST/raw/train-images-idx3-ubyte
Normal file
BIN
data/MNIST/raw/train-images-idx3-ubyte
Normal file
Binary file not shown.
BIN
data/MNIST/raw/train-images-idx3-ubyte.gz
Normal file
BIN
data/MNIST/raw/train-images-idx3-ubyte.gz
Normal file
Binary file not shown.
BIN
data/MNIST/raw/train-labels-idx1-ubyte
Normal file
BIN
data/MNIST/raw/train-labels-idx1-ubyte
Normal file
Binary file not shown.
BIN
data/MNIST/raw/train-labels-idx1-ubyte.gz
Normal file
BIN
data/MNIST/raw/train-labels-idx1-ubyte.gz
Normal file
Binary file not shown.
|
Before Width: | Height: | Size: 7.2 KiB After Width: | Height: | Size: 7.2 KiB |
Reference in New Issue
Block a user