Update README.md

README.md

@@ -6,12 +6,13 @@ base_model:
 
 
 Experimental ONNX conversion of kaloscope model.  
-These need a re-export because i didnt specify dynamic axes during export which probably locked the model behind batch size = 1; otherwise they seem to work perfectly fine
+~~These need a re-export because i didnt specify dynamic axes during export which probably locked the model behind batch size = 1; otherwise they seem to work perfectly fine~~  
+25th oct: replaced existing onnx files with new exports that use dynamo=False and `dynamic_axes={"input": {0: "batch_size"}, "output": {0: "batch_size"},}` - scores seems to be same as original pytorch model and dynamo=True export  
 
 [🤗 Space Demo](https://huggingface.co/spaces/DraconicDragon/Kaloscope-artist-style-classifier) for ONNX & PyTorch inference implementation (incl. timm+lsnet; OpenVINO accelerate CPU inference; no Triton required - refer to [ska.py](https://huggingface.co/spaces/DraconicDragon/Kaloscope-artist-style-classifier/blob/main/lsnet/ska.py) or [here](https://github.com/spawner1145/comfyui-lsnet/pull/2))  
 Barebones standalone ONNX inference script (no timm or lsnet; scores are a tiny bit different - probably different img preprocessing): [onnx_barebones_inference.py](https://huggingface.co/DraconicDragon/Kaloscope-onnx-ema/blob/main/onnx_barebones_inference.py)
 
-- `kaloscope_1-0.onnx`: Exported from `best_checkpoint.pth` original Kaloscope release | dynamo=True, dynamic_axes=None, opset_version=None (torch 2.8.0 used here defaults to 18 when None), optimization/constant folding enabled
+- `kaloscope_1-0.onnx`: Exported from `best_checkpoint.pth` original Kaloscope release | dynamo=False, dynamic_axes={"input": {0: "batch_size"}, "output": {0: "batch_size"},}, opset_version=None (torch 2.8.0 used here defaults to 18 when None), optimization/constant folding enabled
 - `kaloscope_1-1.onnx`: Exported from `224-85.65/best_checkpoint.pth` aka v1.1 | Same settings as v1.0
 
 Conversion/Export script can be found in convert-scripts folder or: