| .. |
|
benchmark.bin
|
Added --benchmark option and disabled gaze tracking for models with negative IDs.
|
2020-09-26 23:49:54 +02:00 |
|
lm_model0_gpu.onnx
|
Add _gpu.onnx unoptimized models for CUDAExecutionProvider compatibility
|
2026-08-29 19:40:28 +07:00 |
|
lm_model0_opt.onnx
|
Reverted "Switched back to decoding face landmarks within the models."
|
2020-10-08 13:07:51 +02:00 |
|
lm_model1_gpu.onnx
|
Add _gpu.onnx unoptimized models for CUDAExecutionProvider compatibility
|
2026-08-29 19:40:28 +07:00 |
|
lm_model1_opt.onnx
|
Reverted "Switched back to decoding face landmarks within the models."
|
2020-10-08 13:07:51 +02:00 |
|
lm_model2_gpu.onnx
|
Add _gpu.onnx unoptimized models for CUDAExecutionProvider compatibility
|
2026-08-29 19:40:28 +07:00 |
|
lm_model2_opt.onnx
|
Reverted "Switched back to decoding face landmarks within the models."
|
2020-10-08 13:07:51 +02:00 |
|
lm_model3_gpu.onnx
|
Add _gpu.onnx unoptimized models for CUDAExecutionProvider compatibility
|
2026-08-29 19:40:28 +07:00 |
|
lm_model3_opt.onnx
|
Reverted "Switched back to decoding face landmarks within the models."
|
2020-10-08 13:07:51 +02:00 |
|
lm_model4_gpu.onnx
|
Add _gpu.onnx unoptimized models for CUDAExecutionProvider compatibility
|
2026-08-29 19:40:28 +07:00 |
|
lm_model4_opt.onnx
|
Added new wink tracking capable tracking model.
|
2021-01-22 16:55:06 +01:00 |
|
lm_modelT_gpu.onnx
|
Add _gpu.onnx unoptimized models for CUDAExecutionProvider compatibility
|
2026-08-29 19:40:28 +07:00 |
|
lm_modelT_opt.onnx
|
Reverted "Switched back to decoding face landmarks within the models."
|
2020-10-08 13:07:51 +02:00 |
|
lm_modelU_gpu.onnx
|
Add _gpu.onnx unoptimized models for CUDAExecutionProvider compatibility
|
2026-08-29 19:40:28 +07:00 |
|
lm_modelU_opt.onnx
|
Integrated two new tracking models.
|
2020-11-28 15:50:22 +01:00 |
|
lm_modelV_gpu.onnx
|
Add _gpu.onnx unoptimized models for CUDAExecutionProvider compatibility
|
2026-08-29 19:40:28 +07:00 |
|
lm_modelV_opt.onnx
|
Integrated two new tracking models.
|
2020-11-28 15:50:22 +01:00 |
|
mnv3_detection_gpu.onnx
|
Add _gpu.onnx unoptimized models for CUDAExecutionProvider compatibility
|
2026-08-29 19:40:28 +07:00 |
|
mnv3_detection_opt.onnx
|
Smaller, faster and better detection model.
|
2020-03-22 13:47:55 +01:00 |
|
mnv3_gaze32_split_gpu.onnx
|
Add _gpu.onnx unoptimized models for CUDAExecutionProvider compatibility
|
2026-08-29 19:40:28 +07:00 |
|
mnv3_gaze32_split_opt.onnx
|
The eye tracking model was switched out. This one seems to be more stable.
|
2020-02-24 21:51:54 +01:00 |
|
priorbox_640x640.json
|
This changes the points used for PnP solving and replaces the RetinaFace model with a higher resolution version.
|
2020-02-28 02:10:23 +01:00 |
|
retinaface_640x640_gpu.onnx
|
Add _gpu.onnx unoptimized models for CUDAExecutionProvider compatibility
|
2026-08-29 19:40:28 +07:00 |
|
retinaface_640x640_opt.onnx
|
This changes the points used for PnP solving and replaces the RetinaFace model with a higher resolution version.
|
2020-02-28 02:10:23 +01:00 |
