diff options
Diffstat (limited to 'training/export_cnn_v2_weights.py')
| -rwxr-xr-x | training/export_cnn_v2_weights.py | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/training/export_cnn_v2_weights.py b/training/export_cnn_v2_weights.py index e3d1724..723f572 100755 --- a/training/export_cnn_v2_weights.py +++ b/training/export_cnn_v2_weights.py @@ -94,6 +94,8 @@ def export_weights_binary(checkpoint_path, output_path): weight_offset += len(layer2_flat) # Convert to f16 + # TODO: Use 8-bit quantization for 2× size reduction + # Requires quantization-aware training (QAT) to maintain accuracy all_weights_f16 = np.array(all_weights, dtype=np.float16) # Pack f16 pairs into u32 for storage buffer |