G
gabrielkasmi/deeppvmapper
Automated pipeline for large scale detection of solar arrays in France
无 SECURITY.md
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
远端端点（Claude Desktop / Cursor / Windsurf 共用 mcpServers）
{
"mcpServers": {
"gabrielkasmi-deeppvmapper": {
"url": "https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp"
}
}
}把这段粘进 Claude Desktop / Cursor 的 mcpServers 配置即可。端点来自公开证据，我们没有替你安装或托管它。 官方 Registry 记录：这个端点没有列出任何请求头。这不等于免密 —— 以项目文档为准。
VS Code（.vscode/mcp.json —— 键名是 servers，远程要 type: http）
{
"servers": {
"gabrielkasmi-deeppvmapper": {
"type": "http",
"url": "https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp"
}
}
}VS Code 的配置文件和另外三家不同：顶层键是 <code>servers</code>，远程端点还要写 <code>"type": "http"</code>。复制到 .vscode/mcp.json。
Claude Code（命令行）
claude mcp add --transport http gabrielkasmi-deeppvmapper https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp
Claude Code 不收 JSON 文件，用这条命令直接加。
取自该仓库的安装命令
pip install "GDAL
解析自我们于 2026-10-26 抓取的该仓库 README；我们未执行过。
这条是仓库自己写的安装方式，不是 MCP 客户端配置，所以不生成 JSON。
配置项的键名以你的客户端为准：客户端与 CLI
- ★ 数取值
- 39 ★ · gabrielkasmi/deeppvmapper · 取自 GitHub 搜索 API · （2026-11-13 20:00:50 核对）
- 来源明细
- 收录自 punkpeye/awesome-mcp-servers 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-10-23 · 最近见到 2026-11-14 · 共见到 26 次 · 被 23 个来源列出
- 评分构成
- 综合分 2,300 · 39 ★ · 23 个来源 · mcp
- 安装
pip install "GDAL
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
pip install "GDAL。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
仓库
gabrielkasmi/deeppvmapper；我们收录于 2026-10-23；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。# DeepPVMapper
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
Large-scale rooftop PV detection pipeline for France. Classifies IGN aerial tiles with InceptionV3, segments positive patches with FCN/DeepLab, and extracts panel characteristics (surface, tilt, azimuth, installed capacity) via pypvroof.
🗺️ Official project page
Work carried out by Gabriel Kasmi as part of his PhD at Mines Paris-PSL (2020–2024).
## MCP Server
DeepPVMapper's detection registry is also exposed as a public MCP (Model Context Protocol) server over Streamable HTTP, so any MCP-compatible client (Claude, etc.) can query the 1.14M+ rooftop-solar detections directly via natural language: search detections, aggregate installed capacity by department, explore an area, track yearly deployment, and check data-quality signals.
Live endpoint: https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp
Server source: supabase/functions/mcp
Registry listing: registry.modelcontextprotocol.io — io.github.gabrielkasmi/deeppvmapper
No install required — add the endpoint as a custom connector in any MCP client.
## Mapping data
Pre-computed detection results for French departments are available on Zenodo:
## Installation
GDAL must be installed system-wide first, then via pip to match the running Python version:
bash
# Ubuntu/Debian
apt-get install -y gdal-bin libgdal-dev libopenjp2-7
pip install "GDAL==$(gdal-config --version)"
pip install -r requirements.txt
GPU required. CUDA 11.8+, 8 GB VRAM minimum.
## Data and model weights
Download model weights and runtime data from Zenodo:
Model weights are also available on Hugging Face:
The training dataset (BDAPPV):
Fill in the source paths in config.yml before running:
| config key | what goes there |
| sourceimagesdir | IGN JP2 tiles + dalles.shp index shapefile |
| sourcetopodir | BDTOPO folder (BATIMENT.shp, ZONEDACTIVITEOUDINTERET.shp) |
| sourcecommunedir | folder containing communes-20210101.shp |
| modeldir | folder containing modelbdappvcls.pth and modelbdappvseg.pth |
## Usage
bash
python main.py --dpt 06
--count sets tiles per classification batch (default 16 — reduce if OOM):
bash
python main.py --dpt 06 --count 8
--config points to an alternative config file (useful for RunPod deployments):
bash
python main.py --dpt 06 --config /workspace/configrunpod.yml
To process a subset of tiles (local testing), set tileslist in config.yml:
yaml
tileslist:
01-2024-0850-6565-LA93-0M20-E080
01-2024-0850-6570-LA93-0M20-E080
Force a full rerun (wipe prior progress):
bash
python main.py --dpt 06 --clean
## Pipeline
Four steps run sequentially inside main.py:
| step | what happens |
| Init | Builds per-department auxiliary files (buildings, plants, communes) into temp/. Skipped if already present — safe to rerun after a crash. |
| Classification | Tiles loaded fully in memory. InceptionV3 classifies 299×299 patches; positives saved as GeoTIFFs to temp/segmentation/. |
| Segmentation | FCN/DeepLab segments each positive patch. LAMB93 polygons extracted, sorted by tile, merged into pseudo-arrays. |
| Aggregation | pypvroof extracts tilt/azimuth/kWp per polygon. Building filter applied. Results written to outputsdir. |
On success: temp/ is deleted automatically.
On crash: temp/ is kept. Rerun the same command to resume from where it stopped.
🗺️ Official project page
Work carried out by Gabriel Kasmi as part of his PhD at Mines Paris-PSL (2020–2024).
## MCP Server
DeepPVMapper's detection registry is also exposed as a public MCP (Model Context Protocol) server over Streamable HTTP, so any MCP-compatible client (Claude, etc.) can query the 1.14M+ rooftop-solar detections directly via natural language: search detections, aggregate installed capacity by department, explore an area, track yearly deployment, and check data-quality signals.
Live endpoint: https://zelhliylrlktnasircwp.supabase.co/functions/v1/mcp/mcp
Server source: supabase/functions/mcp
Registry listing: registry.modelcontextprotocol.io — io.github.gabrielkasmi/deeppvmapper
No install required — add the endpoint as a custom connector in any MCP client.
## Mapping data
Pre-computed detection results for French departments are available on Zenodo:
## Installation
GDAL must be installed system-wide first, then via pip to match the running Python version:
bash
# Ubuntu/Debian
apt-get install -y gdal-bin libgdal-dev libopenjp2-7
pip install "GDAL==$(gdal-config --version)"
pip install -r requirements.txt
GPU required. CUDA 11.8+, 8 GB VRAM minimum.
## Data and model weights
Download model weights and runtime data from Zenodo:
Model weights are also available on Hugging Face:
The training dataset (BDAPPV):
Fill in the source paths in config.yml before running:
| config key | what goes there |
| sourceimagesdir | IGN JP2 tiles + dalles.shp index shapefile |
| sourcetopodir | BDTOPO folder (BATIMENT.shp, ZONEDACTIVITEOUDINTERET.shp) |
| sourcecommunedir | folder containing communes-20210101.shp |
| modeldir | folder containing modelbdappvcls.pth and modelbdappvseg.pth |
## Usage
bash
python main.py --dpt 06
--count sets tiles per classification batch (default 16 — reduce if OOM):
bash
python main.py --dpt 06 --count 8
--config points to an alternative config file (useful for RunPod deployments):
bash
python main.py --dpt 06 --config /workspace/configrunpod.yml
To process a subset of tiles (local testing), set tileslist in config.yml:
yaml
tileslist:
01-2024-0850-6565-LA93-0M20-E080
01-2024-0850-6570-LA93-0M20-E080
Force a full rerun (wipe prior progress):
bash
python main.py --dpt 06 --clean
## Pipeline
Four steps run sequentially inside main.py:
| step | what happens |
| Init | Builds per-department auxiliary files (buildings, plants, communes) into temp/. Skipped if already present — safe to rerun after a crash. |
| Classification | Tiles loaded fully in memory. InceptionV3 classifies 299×299 patches; positives saved as GeoTIFFs to temp/segmentation/. |
| Segmentation | FCN/DeepLab segments each positive patch. LAMB93 polygons extracted, sorted by tile, merged into pseudo-arrays. |
| Aggregation | pypvroof extracts tilt/azimuth/kWp per polygon. Building filter applied. Results written to outputsdir. |
On success: temp/ is deleted automatically.
On crash: temp/ is kept. Rerun the same command to resume from where it stopped.
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/gabrielkasmi-deeppvmapper/)
- 来源
- awesome · https://github.com/gabrielkasmi/deeppvmapper
- 按领域浏览
- MCP 服务
- Traction
- 39 ★
- 收录来源
- 23 个独立来源
- 收录于
- 今天
- 安全策略
- 我们没在该仓库根目录找到
SECURITY.md（这不代表不安全）
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。