pre torch.compile -chkpoint made

This commit is contained in:
2026-06-16 10:40:38 -05:00
parent 34855eff55
commit 6650d3c5ea
19 changed files with 2519 additions and 0 deletions

16
launch-training.sh Executable file
View File

@@ -0,0 +1,16 @@
#!/bin/bash
# Launch hierarchical training — Stage A (species classifier)
# Batch 1536 to utilize the 78GB free memory
cd /home/mike/Plant-Health-ID
source .venv/bin/activate
mkdir -p logs checkpoints
nohup python3 scripts/train_hierarchical.py \
--stage species \
--batch-size 512 \
--no-wandb \
>logs/species_training.log 2>&1 &
echo "Training launched (PID: $!)"
echo "Monitor with: tail -f logs/species_training.log"