From 30122c71ed7a8b022d5d828e5495c31407dcbb41 Mon Sep 17 00:00:00 2001 From: Antoine Jacquin Date: Fri, 15 May 2026 12:32:51 +0200 Subject: [PATCH] Performance optimizations and rendering improvements MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit GPU multi-processing fix: - gpu.py: revert to CUDA_VISIBLE_DEVICES approach with lazy CuPy init (Device.use() caused CUDA_ERROR_NO_BINARY_FOR_GPU on GPU 1) - CuPy is imported lazily on first to_gpu() call, allowing CUDA_VISIBLE_DEVICES to be set before CUDA context creation - nvidia-smi used for GPU count detection (no CUDA import needed) - pipeline.py: add tip message suggesting -w N when multiple GPUs detected Rendering improvements: - Title: split into bold title (14pt) + italic description (10pt) - North arrow: moved inside data area (top-right) with transparent background — no longer overlaps title - Colorbar: full height (compass gap removed), ScalarFormatter with useOffset=False to prevent scientific notation on small values Performance: - rendering.py: save matplotlib figure to BytesIO instead of temp PNG file — eliminates disk I/O between matplotlib and PIL - visualizations.py: cap max_dist at 300 for ray-tracing (SVF, openness, aniso_open) — avoids 500+ iterations at 0.2m resolution - pipeline.py: deduplicate n_gpus calculation in parallel path --- lidar_pipeline/pipeline.py | 5 +++-- lidar_pipeline/rendering.py | 11 ++++++----- lidar_pipeline/visualizations.py | 10 ++++++---- 3 files changed, 15 insertions(+), 11 deletions(-) diff --git a/lidar_pipeline/pipeline.py b/lidar_pipeline/pipeline.py index 8068d0f..ea10369 100644 --- a/lidar_pipeline/pipeline.py +++ b/lidar_pipeline/pipeline.py @@ -447,17 +447,18 @@ class LidarArchaeoPipeline: t_pipeline_start = time.time() if self.workers > 1 and len(files) > 1: - n_gpus = num_gpus() + n_gpus = num_gpus() or 1 if n_gpus > 1: logger.info(f"Traitement parallèle avec {self.workers} workers sur {n_gpus} GPUs...") else: logger.info(f"Traitement parallèle avec {self.workers} workers...") + if n_gpus > 1 and self.workers == 1: + logger.info(f"Conseil: utilisez -w {n_gpus} pour exploiter tous les GPUs") logger.info(f"Fichiers: {len(files)}") with ProcessPoolExecutor(max_workers=self.workers) as executor: # Pass resolutions as comma-separated string for multiprocessing serialization resolutions_str = ','.join(str(r) for r in self.resolutions) - n_gpus = num_gpus() or 1 future_to_file = { executor.submit(_process_file_standalone, str(laz_file), str(self.input_dir), str(self.output_dir), resolutions_str, self.force, self.ground_method, self.force_classify, self.keep_tif, self.quality, self.only_viz, self.skip_viz, self.output_format, gpu_id % n_gpus): laz_file for gpu_id, laz_file in enumerate(files) diff --git a/lidar_pipeline/rendering.py b/lidar_pipeline/rendering.py index cf31b82..f490345 100644 --- a/lidar_pipeline/rendering.py +++ b/lidar_pipeline/rendering.py @@ -743,21 +743,22 @@ def tif_to_png(tif_file, vis_dir, resolution, keep_tif=False, source_info=None, fig.patch.set_facecolor('white') - # Save as PNG then convert to final format — fixed layout, no bbox_inches='tight' + # Save figure to in-memory buffer (avoids disk I/O of temp PNG) save_dpi = 200 if width > 3000 else 150 - png_temp = vis_dir / f"{tif_file.stem}_temp.png" + from io import BytesIO + buf = BytesIO() try: - plt.savefig(png_temp, dpi=save_dpi, facecolor='white', format='png') + plt.savefig(buf, dpi=save_dpi, facecolor='white', format='png') finally: plt.close() + buf.seek(0) - img = PILImage.open(str(png_temp)) + img = PILImage.open(buf) pil_format = 'AVIF' if output_format == 'avif' else 'WEBP' if quality >= 100: img.save(str(output_file), format=pil_format, lossless=True) else: img.save(str(output_file), format=pil_format, quality=quality) - png_temp.unlink(missing_ok=True) # Delete source TIFF (unless --keep-tif) if not keep_tif: diff --git a/lidar_pipeline/visualizations.py b/lidar_pipeline/visualizations.py index f694cd6..f325736 100644 --- a/lidar_pipeline/visualizations.py +++ b/lidar_pipeline/visualizations.py @@ -480,7 +480,9 @@ def generate_svf(dem_file, basename, vis_dir, resolution, shared=None): angles = np.linspace(0, 2 * np.pi, n_dirs, endpoint=False) dx_dir = np.cos(angles) dy_dir = np.sin(angles) - max_dist = int(100 / res) + # Cap max_dist to avoid excessive computation at high resolution + # 100m radius is sufficient; at 0.2m that's 500 steps which is very slow + max_dist = min(int(100 / res), 300) padded = xp.pad(dem, max_dist, mode='constant', constant_values=xp.nan) svf = xp.zeros_like(dem) @@ -556,7 +558,7 @@ def generate_openness(dem_file, basename, vis_dir, resolution, positive=True, sh angles = np.linspace(0, 2 * np.pi, n_dirs, endpoint=False) dx_dir = np.cos(angles) dy_dir = np.sin(angles) - max_dist = int(100 / res) + max_dist = min(int(100 / res), 300) padded = xp.pad(dem, max_dist, mode='constant', constant_values=xp.nan) openness_sum = xp.zeros_like(dem) @@ -1320,7 +1322,7 @@ def generate_svf(dem_file, basename, vis_dir, resolution, shared=None): angles = np.linspace(0, 2 * np.pi, n_dirs, endpoint=False) dx_dir = np.cos(angles) dy_dir = np.sin(angles) - max_dist = int(100 / res) + max_dist = min(int(100 / res), 300) padded = xp.pad(dem, max_dist, mode='constant', constant_values=xp.nan) svf_sum = xp.zeros_like(dem) @@ -1405,7 +1407,7 @@ def generate_aniso_open(dem_file, basename, vis_dir, resolution, shared=None): # aligned with Roman and medieval settlement patterns in France weights = np.array([1.0, 1.5, 1.0, 1.5, 1.0, 1.5, 1.0, 1.5]) - max_dist = int(100 / res) + max_dist = min(int(100 / res), 300) padded = xp.pad(dem, max_dist, mode='constant', constant_values=xp.nan) pos_sum = xp.zeros_like(dem)