Upload RT-DETRv2 voucher classifier

README.md

@@ -76,24 +76,24 @@ This model is a fine-tuned version of [PekingU/rtdetr_v2_r101vd](https://hugging
 
 
 **Overall Detection Performance:**
-- **mAP**: 0.0001
-- **mAP@50**: 0.0002
-- **mAP@75**: 0.0001
+- **mAP**: 0.0023
+- **mAP@50**: 0.0033
+- **mAP@75**: 0.0033
 
 **Per-Class Average Precision:**
 - **Digital invoices**: 0.0000 (needs improvement)
-- **Fisico receipts**: 0.0003 (needs improvement)
+- **Fisico receipts**: 0.0069 (needs improvement)
 - **Tesoreria receipts**: 0.0000 (needs improvement)
 
 **Model Confidence:**
-- **Digital invoices mean confidence**: 0.3055 (low)
-- **Fisico receipts mean confidence**: 0.1668 (low)
-- **Tesoreria receipts mean confidence**: 0.1538 (low)
+- **Digital invoices mean confidence**: 0.3061 (low)
+- **Fisico receipts mean confidence**: 0.1853 (low)
+- **Tesoreria receipts mean confidence**: 0.0000 (low)
 
 **Performance by Object Size:**
 - **Small objects**: -1.0000
 - **Medium objects**: 0.0000
-- **Large objects**: 0.0012
+- **Large objects**: 0.0024
 
 **Evaluation Dataset:**
 - **Digital invoices**: 157 samples (28.8%)
@@ -122,7 +122,7 @@ This model is a fine-tuned version of [PekingU/rtdetr_v2_r101vd](https://hugging
 
 ### MLflow Tracking
 
-- **MLflow Run ID**: a7833854ba314e9a9c9c2e9dc47a5e3f
+- **MLflow Run ID**: 6c2fc7f32c7946148d0d6799b183b9fa
 - **MLflow Experiment**: RT-DETRv2_Voucher_Classification
 
 

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:847ead33349897692345ec9554bc6530520e8a1bce7fd14cb758692e6141f486
+oid sha256:80bf7fd48da208b5c9febfabe9cb53bc40e3c63c95962c2699c23541196c5d37
 size 5841