{
  "slug": "avgpool2d-forward-step",
  "title": "手撕 2D 平均池化前向 (AvgPool2d Forward)",
  "difficulty": "Easy",
  "category": "DL",
  "tags": [
    "池化",
    "CNN",
    "AvgPool"
  ],
  "description_md": "### 题目描述\n实现二维平均池化操作。\n\n### 函数签名\n```python\ndef avgpool2d(\n    x: torch.Tensor,\n    kernel_size: int = 2,\n    stride: int = 2,\n) -> torch.Tensor:\n```\n\n### 示例\n```python\n# 输入\nx = [[[[1.0, 2.0], [3.0, 4.0]], [[-1.0, 0.5], [1.5, -0.5]]], [[[2.5, 0.0], [-1.5, 3.5]], [[1.0, 2.0], [3.0, 4.0]]]]\nkernel_size = 2\nstride = 2\n\n# 输出 (Tensor, shape=[2, 2, 1, 1], dtype=float32)\n[[[[2.5]], [[0.125]]], [[[1.125]], [[2.5]]]]\n```\n\n### 参数规格与约束\n- **`x`**：`torch.Tensor`，测试规格 `shape=[2, 3, 8, 8], dtype=float32`\n- **`kernel_size`**：`int`（默认 `2`）\n- **`stride`**：`int`（默认 `2`）\n- **返回值**：`torch.Tensor`，输出规格 `shape=[2, 3, 4, 4], dtype=float32`\n- **精度容差**：`atol=0.0001, rtol=0.0001`",
  "entry_point": "avgpool2d",
  "starter_code": "import torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport math\nfrom typing import Optional, List, Tuple\n\ndef avgpool2d(\n    x: torch.Tensor,\n    kernel_size: int = 2,\n    stride: int = 2,\n) -> torch.Tensor:\n    \"\"\"\n    手撕 2D 平均池化前向 (AvgPool2d Forward)\n    \"\"\"\n    # 请在此编写代码\n    pass\n",
  "reference_code": "import torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport math\nfrom typing import Optional, List, Tuple\n\ndef avgpool2d(x: torch.Tensor, kernel_size: int = 2, stride: int = 2) -> torch.Tensor:\n    return F.avg_pool2d(x, kernel_size=kernel_size, stride=stride)\n",
  "forbidden_modules": [
    "os",
    "sys",
    "subprocess",
    "shutil",
    "socket",
    "requests"
  ],
  "forbidden_calls": [],
  "time_limit": 3.0,
  "memory_limit_mb": 512,
  "atol": 0.0001,
  "rtol": 0.0001,
  "test_code": "import torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport math\n\ncases = [\n    ('平均池化', torch.randn(2, 3, 8, 8), 2, 2),\n    ('多批次扩展泛化验证', torch.randn(4, 3, 8, 8), 2, 2),\n    ('多维批次与参数泛化验证', torch.randn(2, 3, 8, 8), 3, 2),\n    ('边界极值与稳定性验证', torch.randn(2, 3, 8, 8), 4, 2),\n]\nfor idx, (name, *args) in enumerate(cases, 1):\n    t0 = time.time()\n    try:\n        exp = ref_obj(*args)\n        act = user_obj(*args)\n        match, err, max_diff = compare_outputs(act, exp, atol=atol, rtol=rtol)\n        passed, msg = match, err\n    except Exception as e:\n        passed, msg = False, f\"Runtime Exception: {str(e)}\"\n        act, exp, max_diff = None, None, None\n    cases_results.append({\n        \"case_id\": idx, \"case_name\": name, \"passed\": passed,\n        \"time_ms\": round((time.time() - t0) * 1000, 2), \"message\": msg,\n        \"user_output_summary\": summarize_obj(act) if act is not None else None,\n        \"expected_summary\": summarize_obj(exp) if exp is not None else None,\n        \"max_diff\": max_diff,\n    })\n",
  "is_featured": false,
  "editorial_md": "#### 💡 核心算法原理与数学推导\n**手撕 2D 平均池化前向 (AvgPool2d Forward)**（`avgpool2d`）聚焦于 **DL** 中的关键计算逻辑：\n\n实现二维平均池化操作。\n\n在实现中，函数接收参数 `x` (`torch.Tensor`)、`kernel_size` (`int`)、`stride` (`int`)，目标是计算出类型与形状严格符合 `torch.Tensor` 契约的结果。\n\n#### 📐 输入输出张量变换与步骤拆解\n- **输入基准规格**：`x` 规格为 `torch.Tensor(shape=[2, 3, 8, 8], dtype=float32)`，`kernel_size` 规格为 `int` (示例值: `2`)，`stride` 规格为 `int` (示例值: `2`)。\n- **期望输出规格**：`torch.Tensor(shape=[2, 3, 4, 4], dtype=float32)`。\n\n**具体推导与计算步骤如下：**\n1. 返回最终结果：输出 `F.avg_pool2d(x, kernel_size=kernel_size, stride=stride)`，严格对齐函数签名要求的返回类型与维度。\n\n#### 📊 复杂度分析\n- **时间复杂度**：$O(B \\cdot C \\cdot H_{out} \\cdot W_{out} \\cdot K_h \\cdot K_w)$（或对应动态规划网格规模 $O(T_1 \\cdot T_2)$），取决于滑动窗口或递推网格遍历次数。\n- **空间复杂度**：$O(B \\cdot C \\cdot H_{out} \\cdot W_{out})$，用于存储输出特征图或递推状态表。\n\n#### ⚠️ 关键实现细节与易错点\n- **输入输出类型与形状契约**：请严格按照函数签名返回对应类型（`torch.Tensor`、`Tuple` 或标量数值），避免遗漏批次维度或改变张量的数据类型（`dtype`）。\n- **边界输入鲁棒性**：注意单样本（`Batch=1`）、单步序列（`Seq=1`）、零值输入或极端超参数下的计算行为，不要在代码中硬编码特定测试用例的维度常数。\n- **纯向量化算子优先**：尽量使用 PyTorch 原生向量化张量算子替代低效的 Python 逐元素循环，以兼顾代码简洁性与执行性能。\n\n#### 💻 官方标准参考实现\n```python\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport math\nfrom typing import Optional, List, Tuple\n\ndef avgpool2d(x: torch.Tensor, kernel_size: int = 2, stride: int = 2) -> torch.Tensor:\n    return F.avg_pool2d(x, kernel_size=kernel_size, stride=stride)\n```",
  "difficulty_breakdown": {
    "concept": 1,
    "implementation": 1,
    "math_derivation": 2,
    "boundary_complexity": 1
  },
  "test_cases": [
    {
      "name": "平均池化",
      "input_desc": "真实参数契约用例 (x, kernel_size, stride)",
      "params": [
        {
          "name": "x",
          "type": "torch.Tensor",
          "value": "torch.tensor([[[[1.0, 2.0], [3.0, 4.0]], [[-1.0, 0.5], [1.5, -0.5]]], [[[2.5, 0.0], [-1.5, 3.5]], [[1.0, 2.0], [3.0, 4.0]]]], dtype=torch.float32)"
        },
        {
          "name": "kernel_size",
          "type": "int",
          "value": "2"
        },
        {
          "name": "stride",
          "type": "int",
          "value": "2"
        }
      ],
      "raw_inputs": {
        "x": "torch.tensor([[[[1.0, 2.0], [3.0, 4.0]], [[-1.0, 0.5], [1.5, -0.5]]], [[[2.5, 0.0], [-1.5, 3.5]], [[1.0, 2.0], [3.0, 4.0]]]], dtype=torch.float32)",
        "kernel_size": "2",
        "stride": "2"
      }
    },
    {
      "name": "多批次扩展泛化验证",
      "input_desc": "真实参数契约用例 (x, kernel_size, stride)",
      "params": [
        {
          "name": "x",
          "type": "torch.Tensor",
          "value": "torch.randn(4, 3, 8, 8)"
        },
        {
          "name": "kernel_size",
          "type": "int",
          "value": "2"
        },
        {
          "name": "stride",
          "type": "int",
          "value": "2"
        }
      ],
      "raw_inputs": {
        "x": "torch.randn(4, 3, 8, 8)",
        "kernel_size": "2",
        "stride": "2"
      }
    },
    {
      "name": "多维批次与参数泛化验证",
      "input_desc": "真实参数契约用例 (x, kernel_size, stride)",
      "params": [
        {
          "name": "x",
          "type": "torch.Tensor",
          "value": "torch.randn(2, 3, 8, 8)"
        },
        {
          "name": "kernel_size",
          "type": "int",
          "value": "3"
        },
        {
          "name": "stride",
          "type": "int",
          "value": "2"
        }
      ],
      "raw_inputs": {
        "x": "torch.randn(2, 3, 8, 8)",
        "kernel_size": "3",
        "stride": "2"
      }
    }
  ]
}