nnicolosi/Raptor
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

temp commit: i will soft-reset and recommit after next changes

Browse Source
This commit is contained in:
NiccoloN
2026-08-02 11:37:22 +02:00
parent f4a3b012cc
commit 893e90feac
43 changed files with 2159 additions and 2048 deletions
Download Patch File Download Diff File Expand all files Collapse all files
validation/operations/README.md
+6 -3
View File
@@ -43,7 +43,7 @@ and writes the same rows to `validation_results.csv`.
## Complete inventory
The suite contains 165 models. Tensor shapes, attributes, and constants are
The suite contains 168 models. Tensor shapes, attributes, and constants are
defined in `gen_tests.py` and in the checked-in ONNX models.
### Add (5)
@@ -64,7 +64,7 @@ defined in `gen_tests.py` and in the checked-in ONNX models.
| `negative_axis` | Concatenates tensors using a negative axis. |
| `three_inputs_channel_axis` | Concatenates three runtime NCHW tensors along the channel axis. |
### Conv (32)
### Conv (34)
| Case | Description |
|---|---|
@@ -99,6 +99,8 @@ defined in `gen_tests.py` and in the checked-in ONNX models.
| `with_bias_3x3` | Multi-channel 3x3 Conv with bias. |
| `with_constant` | Hand-authored SAME_UPPER Conv with constant weight and bias. |
| `without_kernel_shape_attr` | Conv whose kernel shape is inferred from its weight tensor. |
| `yolo11n_depthwise_head` | YOLO11n pointwise-to-depthwise head boundary at `80x80`, preserving row fragments. |
| `yolo11n_heavy` | Two largest standard YOLO11n Conv-SiLU blocks by MAC count at `64x80x80`. |
| `yolo11n_stem` | First two YOLO11n `Conv-SiLU` blocks at `640x640`, including the distributed activation boundary. |
### Div (6)
@@ -158,7 +160,7 @@ defined in `gen_tests.py` and in the checked-in ONNX models.
| `with_homogeneous_constant` | Adds a constant bias matching the output shape. |
| `with_scalar_constant` | Adds a scalar broadcast bias. |
### MatMul (11)
### MatMul (12)
| Case | Description |
|---|---|
@@ -173,6 +175,7 @@ defined in `gen_tests.py` and in the checked-in ONNX models.
| `left_constant` | Direct 2D MatMul with constant left-hand matrix. |
| `matrix_vector` | Matrix-vector multiplication producing a 1D output. |
| `vector_matrix` | Vector-matrix multiplication producing a 1D output. |
| `yolo_attention` | YOLO11n rank-4 dynamic MatMul-scale-transpose-MatMul attention chain. |
### Mul (5)