kvasir_seg_rtdetrv2_r18_test_fps

goodcasper/kvasir_seg_rtdetrv2_r18_test_fps

kvasir_seg_rtdetrv2_r18_test_fps is a object detection model from goodcasper. Use it when you need objects located in an image. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

8% of all-time downloads

All-time downloads

130

Public

Parameters

20.1M

805 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors80.5 MB · 100%

At a glance

Task: Object Detection
Library: transformers
License: apache-2.0
Model type: rt_detr_v2
Access: Public
Created: Jun 22, 2025
Updated: Jun 22, 2025
SHA: f933aae3

Base models

PekingU/rtdetr_v2_r18vd

Model card

From the Hugging Face model README

kvasir_seg_rtdetrv2_r18_test_fps

This model is a fine-tuned version of PekingU/rtdetr_v2_r18vd on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 5.7736
Map: 0.6786
Map 50: 0.865
Map 75: 0.7285
Map Small: 0.0
Map Medium: 0.5729
Map Large: 0.6933
Mar 1: 0.6607
Mar 10: 0.8706
Mar 100: 0.9114
Mar Small: 0.0
Mar Medium: 0.79
Mar Large: 0.922
Map Polyp: 0.6786
Mar 100 Polyp: 0.9114

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 1
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 300
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Map	Map 50	Map 75	Map Medium	Map Large	Mar 1	Mar 10	Mar 100	Mar Medium	Mar Large	Map Polyp	Mar 100 Polyp
222.0855	1.0	100	27.8979	0.2324	0.3276	0.2381	0.0033	0.2491	0.4327	0.6583	0.7569	0.47	0.775	0.2324	0.7569
21.4558	2.0	200	8.5908	0.4453	0.6029	0.4705	0.2753	0.4596	0.6161	0.7815	0.872	0.71	0.8845	0.4453	0.872
11.9198	3.0	300	7.3897	0.559	0.7445	0.5928	0.3981	0.5748	0.6156	0.8218	0.8806	0.74	0.892	0.559	0.8806
10.1107	4.0	400	6.7691	0.5087	0.691	0.5261	0.258	0.53	0.6185	0.8047	0.8744	0.61	0.892	0.5087	0.8744
8.9974	5.0	500	6.1887	0.6247	0.7927	0.6818	0.51	0.6464	0.6682	0.8346	0.8872	0.69	0.9015	0.6247	0.8872
8.4837	6.0	600	6.0117	0.6313	0.82	0.6738	0.4952	0.6465	0.627	0.8502	0.9028	0.74	0.9155	0.6313	0.9028
7.9083	7.0	700	6.0504	0.6328	0.8234	0.6877	0.5697	0.6459	0.6412	0.8545	0.891	0.77	0.9015	0.6328	0.891
7.4364	8.0	800	5.9616	0.6493	0.8454	0.6945	0.6155	0.6611	0.6445	0.8635	0.9033	0.78	0.914	0.6493	0.9033
7.2255	9.0	900	5.7790	0.6767	0.8628	0.7297	0.5687	0.6914	0.663	0.8739	0.9047	0.79	0.915	0.6767	0.9047
6.9854	10.0	1000	5.7736	0.6786	0.865	0.7285	0.5729	0.6933	0.6607	0.8706	0.9114	0.79	0.922	0.6786	0.9114

Framework versions

Transformers 4.53.0.dev0
Pytorch 2.7.1+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Task: Object Detection
Library: transformers
Type: rt_detr_v2
License: apache-2.0
Created: Jun 22, 2025
Updated: Jun 22, 2025