手写数字识别

2026-07-05 00:31:14 +08:00
parent 9d1968c020
commit 355e01a4a1
7 changed files with 98520 additions and 8 deletions
@@ -0,0 +1,216 @@
+{
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.12.13",
+   "mimetype": "text/x-python",
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "pygments_lexer": "ipython3",
+   "nbconvert_exporter": "python",
+   "file_extension": ".py"
+  }
+ },
+ "nbformat_minor": 4,
+ "nbformat": 4,
+ "cells": [
+  {
+   "cell_type": "code",
+   "source": "import matplotlib.pyplot as plt\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import Dataset, DataLoader\nimport pandas as pd",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-03T10:17:12.326817130Z",
+     "start_time": "2026-07-03T10:17:12.293250353Z"
+    },
+    "trusted": true,
+    "execution": {
+     "iopub.status.busy": "2026-07-04T16:16:09.940312Z",
+     "iopub.execute_input": "2026-07-04T16:16:09.940612Z",
+     "iopub.status.idle": "2026-07-04T16:16:12.856395Z",
+     "shell.execute_reply.started": "2026-07-04T16:16:09.940586Z",
+     "shell.execute_reply": "2026-07-04T16:16:12.855776Z"
+    }
+   },
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "source": "%cd /kaggle/working\ndevice = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\ntrain_df=pd.read_csv(\"/kaggle/input/competitions/digit-recognizer/train.csv\")\ntest_df=pd.read_csv(\"/kaggle/input/competitions/digit-recognizer/test.csv\")",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-03T10:17:15.014258006Z",
+     "start_time": "2026-07-03T10:17:12.346500913Z"
+    },
+    "trusted": true,
+    "execution": {
+     "iopub.status.busy": "2026-07-04T16:16:12.857730Z",
+     "iopub.execute_input": "2026-07-04T16:16:12.858065Z",
+     "iopub.status.idle": "2026-07-04T16:16:16.048768Z",
+     "shell.execute_reply.started": "2026-07-04T16:16:12.858040Z",
+     "shell.execute_reply": "2026-07-04T16:16:16.048163Z"
+    }
+   },
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "source": "fig, ax = plt.subplots(nrows=2, ncols=2, sharex='all', sharey='all')\nax = ax.flatten()\nfor i in range(4):\n    img = train_df.iloc[i][1:].to_numpy().reshape(28,28)\n    # ax[i].imshow(img,cmap='Greys')\n    ax[i].imshow(img)\n    ax[i].set_title(f'{train_df.iloc[i][0]}')",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-03T10:17:15.565961732Z",
+     "start_time": "2026-07-03T10:17:15.073738808Z"
+    },
+    "trusted": true,
+    "execution": {
+     "iopub.status.busy": "2026-07-04T16:16:16.049873Z",
+     "iopub.execute_input": "2026-07-04T16:16:16.050089Z",
+     "iopub.status.idle": "2026-07-04T16:16:16.369380Z",
+     "shell.execute_reply.started": "2026-07-04T16:16:16.050066Z",
+     "shell.execute_reply": "2026-07-04T16:16:16.368725Z"
+    }
+   },
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "source": "class DatasetMnist(Dataset):\n    def __init__(self,df):\n        self.df=df\n    def __len__(self):\n        return len(self.df)\n    def __getitem__(self, idx):\n        item= {\"Data\": torch.tensor(self.df.iloc[idx][1:].to_numpy().reshape(28, 28),dtype=torch.float), \"label\": torch.tensor(self.df.iloc[idx][0],dtype=torch.long)}\n        return item\nbatch_size =64\ntrain_dataset = DatasetMnist(train_df)\ntrain_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-03T10:17:15.669173315Z",
+     "start_time": "2026-07-03T10:17:15.616933550Z"
+    },
+    "trusted": true,
+    "execution": {
+     "iopub.status.busy": "2026-07-04T16:16:16.370253Z",
+     "iopub.execute_input": "2026-07-04T16:16:16.370426Z",
+     "iopub.status.idle": "2026-07-04T16:16:16.375630Z",
+     "shell.execute_reply.started": "2026-07-04T16:16:16.370409Z",
+     "shell.execute_reply": "2026-07-04T16:16:16.375171Z"
+    }
+   },
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "source": "class MnistModule(nn.Module):\n    def __init__(self):\n        super(MnistModule, self).__init__()\n        self.fc1 = nn.Linear(28*28, 512)\n        self.relu = nn.ReLU()\n        self.fc2 = nn.Linear(512, 256)\n        self.fc3 = nn.Linear(256, 128)\n        self.fc4 = nn.Linear(128,10)\n    def forward(self,X):\n        return self.fc4(self.relu(self.fc3(self.relu(self.fc2(self.relu(self.fc1(X.view(-1,28*28))))))))",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-03T10:17:15.729366448Z",
+     "start_time": "2026-07-03T10:17:15.670668930Z"
+    },
+    "trusted": true,
+    "execution": {
+     "iopub.status.busy": "2026-07-04T16:16:16.376258Z",
+     "iopub.execute_input": "2026-07-04T16:16:16.376401Z",
+     "iopub.status.idle": "2026-07-04T16:16:16.389616Z",
+     "shell.execute_reply.started": "2026-07-04T16:16:16.376386Z",
+     "shell.execute_reply": "2026-07-04T16:16:16.388703Z"
+    }
+   },
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "source": "model = MnistModule()\nmodel=model.to(device)\nloss_func = nn.CrossEntropyLoss()\noptimizer = torch.optim.AdamW(model.parameters(), lr=2e-4)\nscheduler=torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10)\n",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-03T10:17:15.792463697Z",
+     "start_time": "2026-07-03T10:17:15.730536380Z"
+    },
+    "trusted": true,
+    "execution": {
+     "iopub.status.busy": "2026-07-04T16:16:16.390304Z",
+     "iopub.execute_input": "2026-07-04T16:16:16.390504Z",
+     "iopub.status.idle": "2026-07-04T16:16:18.580638Z",
+     "shell.execute_reply.started": "2026-07-04T16:16:16.390482Z",
+     "shell.execute_reply": "2026-07-04T16:16:18.580038Z"
+    }
+   },
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "source": "epochs = 30\nfor epoch in range(epochs):\n    model.train()\n    training_loss=0\n    for batch in train_loader:\n        optimizer.zero_grad()\n        X = batch['Data']\n        labels=batch['label']\n        X=X.to(device)\n        labels=labels.to(device)\n        #print(model(X),'\\n',labels)\n        loss = loss_func(model(X),labels)\n        loss.backward()\n        optimizer.step()\n        training_loss+=loss.item()\n    scheduler.step()\n    print(f\"train_loss: {training_loss/len(train_loader)}\")",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-03T10:18:55.758148762Z",
+     "start_time": "2026-07-03T10:17:31.736342843Z"
+    },
+    "trusted": true,
+    "execution": {
+     "iopub.status.busy": "2026-07-04T16:16:18.582512Z",
+     "iopub.execute_input": "2026-07-04T16:16:18.582874Z",
+     "iopub.status.idle": "2026-07-04T16:18:53.082304Z",
+     "shell.execute_reply.started": "2026-07-04T16:16:18.582856Z",
+     "shell.execute_reply": "2026-07-04T16:18:53.081057Z"
+    }
+   },
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "class DatasetMnistTest(Dataset):\n",
+    "    def __init__(self,df):\n",
+    "        self.df=df\n",
+    "    def __len__(self):\n",
+    "        return len(self.df)\n",
+    "    def __getitem__(self, idx):\n",
+    "        item= {\"Data\": torch.tensor(self.df.iloc[idx].to_numpy().reshape(28, 28),dtype=torch.float)}\n",
+    "        return item\n",
+    "test_dataset = DatasetMnistTest(test_df)\n",
+    "test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)\n",
+    "all_preds = []\n",
+    "with torch.no_grad():\n",
+    "    for batch in test_loader:\n",
+    "        input_ids = batch['Data'].to(device)\n",
+    "        outputs = model(input_ids)\n",
+    "        preds = torch.argmax(outputs, dim=1)\n",
+    "        all_preds.extend(preds.cpu().numpy())\n",
+    "idd = range(1,len(all_preds)+1)\n",
+    "submission = pd.DataFrame({\n",
+    "    'ImageId':idd,\n",
+    "    'Label': all_preds\n",
+    "})\n",
+    "print(submission)\n",
+    "submission.to_csv('submission.csv', index=False)\n",
+    "print(\"Submission saved!\")"
+   ],
+   "metadata": {
+    "trusted": true,
+    "execution": {
+     "iopub.status.busy": "2026-07-04T16:19:40.600448Z",
+     "iopub.execute_input": "2026-07-04T16:19:40.601006Z",
+     "iopub.status.idle": "2026-07-04T16:19:41.910494Z",
+     "shell.execute_reply.started": "2026-07-04T16:19:40.600982Z",
+     "shell.execute_reply": "2026-07-04T16:19:41.909862Z"
+    }
+   },
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "source": "",
+   "metadata": {
+    "trusted": true
+   },
+   "outputs": [],
+   "execution_count": null
+  }
+ ]
+}
@@ -0,0 +1,94 @@
+# %%
+import matplotlib.pyplot as plt
+import torch
+import torch.nn as nn
+from torch.utils.data import Dataset, DataLoader
+import pandas as pd
+# %%
+# %cd /kaggle/working
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+train_df=pd.read_csv("/kaggle/input/competitions/digit-recognizer/train.csv")
+test_df=pd.read_csv("/kaggle/input/competitions/digit-recognizer/test.csv")
+# %%
+fig, ax = plt.subplots(nrows=2, ncols=2, sharex='all', sharey='all')
+ax = ax.flatten()
+for i in range(4):
+    img = train_df.iloc[i][1:].to_numpy().reshape(28,28)
+    # ax[i].imshow(img,cmap='Greys')
+    ax[i].imshow(img)
+    ax[i].set_title(f'{train_df.iloc[i][0]}')
+# %%
+class DatasetMnist(Dataset):
+    def __init__(self,df):
+        self.df=df
+    def __len__(self):
+        return len(self.df)
+    def __getitem__(self, idx):
+        item= {"Data": torch.tensor(self.df.iloc[idx][1:].to_numpy().reshape(28, 28),dtype=torch.float), "label": torch.tensor(self.df.iloc[idx][0],dtype=torch.long)}
+        return item
+batch_size =64
+train_dataset = DatasetMnist(train_df)
+train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
+# %%
+class MnistModule(nn.Module):
+    def __init__(self):
+        super(MnistModule, self).__init__()
+        self.fc1 = nn.Linear(28*28, 512)
+        self.relu = nn.ReLU()
+        self.fc2 = nn.Linear(512, 256)
+        self.fc3 = nn.Linear(256, 128)
+        self.fc4 = nn.Linear(128,10)
+    def forward(self,X):
+        return self.fc4(self.relu(self.fc3(self.relu(self.fc2(self.relu(self.fc1(X.view(-1,28*28))))))))
+# %%
+model = MnistModule()
+model=model.to(device)
+loss_func = nn.CrossEntropyLoss()
+optimizer = torch.optim.AdamW(model.parameters(), lr=2e-4)
+scheduler=torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10)
+
+# %%
+epochs = 30
+for epoch in range(epochs):
+    model.train()
+    training_loss=0
+    for batch in train_loader:
+        optimizer.zero_grad()
+        X = batch['Data']
+        labels=batch['label']
+        X=X.to(device)
+        labels=labels.to(device)
+        #print(model(X),'\n',labels)
+        loss = loss_func(model(X),labels)
+        loss.backward()
+        optimizer.step()
+        training_loss+=loss.item()
+    scheduler.step()
+    print(f"train_loss: {training_loss/len(train_loader)}")
+# %%
+class DatasetMnistTest(Dataset):
+    def __init__(self,df):
+        self.df=df
+    def __len__(self):
+        return len(self.df)
+    def __getitem__(self, idx):
+        item= {"Data": torch.tensor(self.df.iloc[idx].to_numpy().reshape(28, 28),dtype=torch.float)}
+        return item
+test_dataset = DatasetMnistTest(test_df)
+test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)
+all_preds = []
+with torch.no_grad():
+    for batch in test_loader:
+        input_ids = batch['Data'].to(device)
+        outputs = model(input_ids)
+        preds = torch.argmax(outputs, dim=1)
+        all_preds.extend(preds.cpu().numpy())
+idd = range(1,len(all_preds)+1)
+submission = pd.DataFrame({
+    'ImageId':idd,
+    'Label': all_preds
+})
+print(submission)
+submission.to_csv('submission.csv', index=False)
+print("Submission saved!")
+# %%