| _BASE_: oneformer_R50_bs16_50ep.yaml | |
| MODEL: | |
| BACKBONE: | |
| NAME: "D2DiNAT" | |
| DiNAT: | |
| EMBED_DIM: 192 | |
| MLP_RATIO: 2.0 | |
| DEPTHS: [3, 4, 18, 5] | |
| NUM_HEADS: [6, 12, 24, 48] | |
| KERNEL_SIZE: 11 | |
| DROP_PATH_RATE: 0.3 | |
| DILATIONS: [[1, 20, 1], [1, 5, 1, 10], [1, 2, 1, 3, 1, 4, 1, 5, 1, 2, 1, 3, 1, 4, 1, 5, 1, 5], [1, 2, 1, 2, 1]] | |
| WEIGHTS: "dinat_large_in22k_in1k_384_11x11.pkl" | |
| PIXEL_MEAN: [123.675, 116.280, 103.530] | |
| PIXEL_STD: [58.395, 57.120, 57.375] | |
| ONE_FORMER: | |
| NUM_OBJECT_QUERIES: 150 | |
| SOLVER: | |
| STEPS: (655556, 710184) | |
| MAX_ITER: 737500 | |
| TEST: | |
| DETECTIONS_PER_IMAGE: 150 |