All models were compiled using Hailo Dataflow Compiler v2.18.0.
| Key / Icon | Description |
|---|---|
| ⭐ | Networks used by Hailo-apps. |
| S | Source – Link to the model's open-source repository. |
| PT | Pretrained – Download the pretrained model file (ZIP format). |
| HEF, NV12, RGBX | Compiled Models – Links to models in various formats: - HEF: RGB format - NV12: NV12 format - RGBX: RGBX format |
| PR | Profiler Report – Download the model's performance profiling report. |
| Network Name | float Retrieval@10 | Hardware Retrieval@10 | FPS (Batch Size=1) | FPS (Batch Size=8) | Links | Input Resolution (HxWxC) | Params (M) | OPS (G) |
|---|---|---|---|---|---|---|---|---|
| clip_resnet_50_text_encoder | 88.8 | 83.9 | 32.3 | 114 | 1x77x512 | 37.8 | 6.0 | |
| clip_resnet_50x4_text_encoder | 91.2 | 89.9 | 21.4 | 79.0 | 1x77x640 | 59.1 | 9.3 | |
| clip_vit_b_16_text_encoder | 90.9 | 89.8 | 33.6 | 129 | 1x77x512 | 37.8 | 6.0 | |
| clip_vit_b_32_text_encoder⭐ | 90.6 | 89.3 | 32.4 | 137 | 1x77x512 | 37.8 | 6.0 | |
| siglip2_b_32_256_text_encoder | 96.1 | 96.2 | 16.6 | 81.9 | 8x8x768 | 85.6 | 11.0 | |
| siglip_b_16_text_encoder | 96.2 | 96.0 | 16.5 | 81.9 | 8x8x768 | 85.6 | 11.1 | |
| tinyclip_vit_39m_16_text_19m_yfcc15m_text_encoder | 94.0 | 94.0 | 68.3 | 247 | 1x77x512 | 19 | 3 | |
| tinyclip_vit_40m_32_text_19m_laion400m_text_encoder | 91.1 | 90.0 | 68.9 | 229 | 1x77x512 | 19 | 3 | |
| tinyclip_vit_61m_32_text_29m_laion400m_text_encoder | 93.8 | 90.0 | 44.7 | 178 | 1x77x512 | 29 | 4.5 | |
| tinyclip_vit_8m_16_text_3m_yfcc15m_text_encoder | 84.4 | 84.2 | 358 | 1665 | 1x77x512 | 3 | 382 |