Downloads · 30 days
5
11% of all-time downloads
NICOPOI-9/segformer-b5-finetuned-ade20k-morphpadver1-hgo-coord-v9_mix_resample_40epochs_distortion_30_30
segformer-b5-finetuned-ade20k-morphpadver1-hgo-coord-v9_mix_resample_40epochs_distortion_30_30 is a image segmentation model from NICOPOI-9. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
5
11% of all-time downloads
All-time downloads
46
Public
Parameters
84.6M
339 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors339 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of nvidia/segformer-b5-finetuned-ade-640-640 on the NICOPOI-9/morphpad_coord_hgo_30_30_512_4class dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy 0-0 | Accuracy 0-90 | Accuracy 90-0 | Accuracy 90-90 | Iou 0-0 | Iou 0-90 | Iou 90-0 | Iou 90-90 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.0065 | 2.1053 | 4000 | 1.2810 | 0.1798 | 0.3411 | 0.3843 | 0.0650 | 0.8516 | 0.3933 | 0.0545 | 0.0616 | 0.3219 | 0.2854 | 0.0504 |
| 1.3353 | 4.2105 | 8000 | 1.1874 | 0.2561 | 0.4160 | 0.4499 | 0.2169 | 0.7132 | 0.5797 | 0.1543 | 0.1789 | 0.3478 | 0.3626 | 0.1351 |
| 1.2779 | 6.3158 | 12000 | 1.1353 | 0.3100 | 0.4771 | 0.5107 | 0.2577 | 0.7079 | 0.7136 | 0.2292 | 0.2252 | 0.4204 | 0.3885 | 0.2057 |
| 0.2697 | 8.4211 | 16000 | 1.1561 | 0.3406 | 0.5109 | 0.5473 | 0.2683 | 0.7132 | 0.8228 | 0.2393 | 0.2526 | 0.4669 | 0.4168 | 0.2261 |
| 0.2765 | 10.5263 | 20000 | 1.1780 | 0.3967 | 0.5647 | 0.5984 | 0.3409 | 0.8128 | 0.7818 | 0.3234 | 0.3178 | 0.4881 | 0.4813 | 0.2998 |
| 1.3424 | 12.6316 | 24000 | 0.8132 | 0.4701 | 0.6298 | 0.6548 | 0.4110 | 0.8028 | 0.8009 | 0.5046 | 0.3877 | 0.5546 | 0.4984 | 0.4398 |
| 1.4588 | 14.7368 | 28000 | 0.7890 | 0.5047 | 0.6576 | 0.6815 | 0.4513 | 0.8877 | 0.7459 | 0.5455 | 0.4218 | 0.5272 | 0.5854 | 0.4843 |
| 0.2028 | 16.8421 | 32000 | 0.6630 | 0.5607 | 0.7045 | 0.7242 | 0.5508 | 0.7816 | 0.9109 | 0.5747 | 0.5075 | 0.6565 | 0.5515 | 0.5272 |
| 1.1433 | 18.9474 | 36000 | 0.6946 | 0.5834 | 0.7249 | 0.7503 | 0.5823 | 0.9130 | 0.8885 | 0.5159 | 0.5514 | 0.6559 | 0.6303 | 0.4961 |
| 1.3294 | 21.0526 | 40000 | 0.4913 | 0.6707 | 0.7914 | 0.8083 | 0.6621 | 0.8995 | 0.9191 | 0.6848 | 0.6324 | 0.7335 | 0.6751 | 0.6420 |
| 1.0484 | 23.1579 | 44000 | 0.3873 | 0.7303 | 0.8368 | 0.8456 | 0.8293 | 0.8780 | 0.9249 | 0.7149 | 0.7450 | 0.7801 | 0.7104 | 0.6857 |
| 1.1695 | 25.2632 | 48000 | 0.3731 | 0.7416 | 0.8424 | 0.8546 | 0.7678 | 0.9254 | 0.9301 | 0.7463 | 0.7232 | 0.7865 | 0.7408 | 0.7161 |
| 0.3945 | 27.3684 | 52000 | 0.2975 | 0.7840 | 0.8736 | 0.8803 | 0.8641 | 0.9077 | 0.9374 | 0.7850 | 0.7872 | 0.8205 | 0.7741 | 0.7543 |
| 0.0882 | 29.4737 | 56000 | 0.2718 | 0.8072 | 0.8908 | 0.8942 | 0.8461 | 0.8937 | 0.9384 | 0.8849 | 0.7885 | 0.8318 | 0.8023 | 0.8063 |
| 0.1896 | 31.5789 | 60000 | 0.2483 | 0.8219 | 0.9003 | 0.9033 | 0.8563 | 0.9449 | 0.8920 | 0.9079 | 0.8020 | 0.8356 | 0.8287 | 0.8210 |
| 0.089 | 33.6842 | 64000 | 0.2537 | 0.8164 | 0.8954 | 0.9000 | 0.8684 | 0.9057 | 0.9530 | 0.8545 | 0.8009 | 0.8503 | 0.8080 | 0.8066 |
| 1.3302 | 35.7895 | 68000 | 0.2916 | 0.7907 | 0.8774 | 0.8855 | 0.8762 | 0.9122 | 0.9622 | 0.7590 | 0.7927 | 0.8438 | 0.7850 | 0.7413 |
| 0.0328 | 37.8947 | 72000 | 0.2191 | 0.8373 | 0.9086 | 0.9127 | 0.9070 | 0.9177 | 0.9603 | 0.8495 | 0.8280 | 0.8669 | 0.8356 | 0.8185 |
| 0.3443 | 40.0 | 76000 | 0.1967 | 0.8562 | 0.9213 | 0.9236 | 0.9249 | 0.9318 | 0.9446 | 0.8839 | 0.8436 | 0.8758 | 0.8619 | 0.8435 |