[2026-07-15 11:06:15] input=/home/mahbod/uni/MP_raw/BACH/tiles patches=19200 repo=AdapterGNN [2026-07-15 11:06:15] ===== STEP 01 cell segmentation (CPU) ===== 2026-07-15 11:06:15.720721: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-07-15 11:06:15.751065: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX_VNNI AVX_VNNI_INT8 AVX_NE_CONVERT FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-07-15 11:06:16.331592: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-07-15 11:06:17.537295: E external/local_xla/xla/stream_executor/cuda/cuda_platform.cc:51] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected 2026-07-15 11:06:17.537331: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:160] env: CUDA_VISIBLE_DEVICES="" 2026-07-15 11:06:17.537334: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:163] CUDA_VISIBLE_DEVICES is set to an empty string - this hides all GPUs from CUDA 2026-07-15 11:06:17.537336: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:171] verbose logging is disabled. Rerun with verbose logging (usually --v=1 or --vmodule=cuda_diagnostics=1) to get more diagnostic output from this module 2026-07-15 11:06:17.537339: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:176] retrieving CUDA diagnostic information for host: Qolam 2026-07-15 11:06:17.537341: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:183] hostname: Qolam 2026-07-15 11:06:17.537393: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:190] libcuda reported version is: 580.159.3 2026-07-15 11:06:17.537406: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:194] kernel reported version is: 580.159.3 2026-07-15 11:06:17.537407: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:284] kernel version seems to match DSO: 580.159.3 Found model '2D_versatile_he' for 'StarDist2D'. Loading network weights from 'weights_best.h5'. Loading thresholds from 'thresholds.json'. Using default values: prob_thresh=0.692478, nms_thresh=0.3. Processing 400 patient folders Processing patient folders: 0%| | 0/400 [00:00