--- title: Conditional-DETR-ResNet50 canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/Conditional-DETR-ResNet50" md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/Conditional-DETR-ResNet50.md" repository: Qualcomm-AI-Hub/Conditional-DETR-ResNet50 last_updated: 2026-10-16 license: apache-2.0 downloads: 0 stars: 0 tags: - android --- # Conditional-DETR-ResNet50 > Conditional-DETR-ResNet50 - Qualcomm-AI-Hub 在 ModelScope 开源的模型。Conditional-DETR-ResNet50: Optimized for Qualcomm Devices Qualcomm-AI-Hub/Conditional-DETR-ResNet50 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。 - **Repository**: Qualcomm-AI-Hub/Conditional-DETR-ResNet50 - **License**: apache-2.0 - **Tags**: android - **Downloads**: 0 - **Stars**: 0 - **Last updated**: 2026-10-16 Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/Conditional-DETR-ResNet50 --- ![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/conditional_detr_resnet50/web-assets/model_demo.png) # Conditional-DETR-ResNet50: Optimized for Qualcomm Devices DETR is a machine learning model that can detect objects (trained on COCO dataset). This is based on the implementation of Conditional-DETR-ResNet50 found [here](https://github.com/huggingface/transformers/tree/main/src/transformers/models/conditional_detr). This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/conditional_detr_resnet50) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary). Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.cn) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device. ## Getting Started There are two ways to deploy this model on your device: ### Option 1: Download Pre-Exported Models Below are pre-exported model assets ready for deployment. | Runtime | Precision | Chipset | SDK Versions | Download | |---|---|---|---|---| | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/conditional_detr_resnet50/releases/v0.62.1/conditional_detr_resnet50-onnx-float.zip) | ONNX | w8a16_mixed_fp16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/conditional_detr_resnet50/releases/v0.62.1/conditional_detr_resnet50-onnx-w8a16_mixed_fp16.zip) | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/conditional_detr_resnet50/releases/v0.62.1/conditional_detr_resnet50-qnn_dlc-float.zip) | QNN_DLC | w8a16_mixed_fp16 | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/conditional_detr_resnet50/releases/v0.62.1/conditional_detr_resnet50-qnn_dlc-w8a16_mixed_fp16.zip) | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/conditional_detr_resnet50/releases/v0.62.1/conditional_detr_resnet50-tflite-float.zip) For more device-specific assets and performance metrics, visit **[Conditional-DETR-ResNet50 on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/conditional_detr_resnet50)**. ### Option 2: Export with Custom Configurations Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/conditional_detr_resnet50) Python library to compile and export the model with your own: - Custom weights (e.g., fine-tuned checkpoints) - Custom input shapes - Target device and runtime configurations This option is ideal if you need to customize the model beyond the default configuration provided here. See our repository for [Conditional-DETR-ResNet50 on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/conditional_detr_resnet50) for usage instructions. ## Model Details **Model Type:** Model_use_case.object_detection **Model Stats:** - Input resolution: 480x480 - Model checkpoint: ResNet50 - Model size (float): 166 MB - Number of parameters: 43.6M ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | Conditional-DETR-ResNet50 | ONNX | float | Snapdragon® X2 Elite | 9.299 ms | 5 - 5 MB | NPU | Conditional-DETR-ResNet50 | ONNX | float | Snapdragon® X Elite | 20.278 ms | 82 - 82 MB | NPU | Conditional-DETR-ResNet50 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 15.019 ms | 2 - 455 MB | NPU | Conditional-DETR-ResNet50 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 40.115 ms | 1 - 368 MB | NPU | Conditional-DETR-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 31.368 ms | 5 - 13 MB | NPU | Conditional-DETR-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 20.31 ms | 0 - 94 MB | NPU | Conditional-DETR-ResNet50 | ONNX | float | Qualcomm® QCS8450 | 40.115 ms | 1 - 368 MB | NPU | Conditional-DETR-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 29.674 ms | 5 - 12 MB | NPU | Conditional-DETR-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 20.278 ms | 82 - 82 MB | NPU | Conditional-DETR-ResNet50 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 11.163 ms | 0 - 317 MB | NPU | Conditional-DETR-ResNet50 | ONNX | float | Snapdragon® 8 Elite Mobile | 11.163 ms | 0 - 317 MB | NPU | Conditional-DETR-ResNet50 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 8.307 ms | 3 - 326 MB | NPU | Conditional-DETR-ResNet50 | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 54.232 ms | 20 - 408 MB | NPU | Conditional-DETR-ResNet50 | ONNX | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ Q-8750 | 45.367 ms | 24 - 298 MB | NPU | Conditional-DETR-ResNet50 | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Mobile | 45.367 ms | 24 - 298 MB | NPU | Conditional-DETR-ResNet50 | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 Mobile | 39.07 ms | 22 - 311 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 9.972 ms | 5 - 5 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Snapdragon® X Elite | 23.439 ms | 5 - 5 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 17.1 ms | 0 - 400 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 45.055 ms | 5 - 351 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 33.334 ms | 5 - 12 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 23.12 ms | 5 - 7 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA8775P | 32.229 ms | 1 - 306 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA8650P | 32.229 ms | 1 - 306 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA8255P | 32.229 ms | 1 - 306 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Qualcomm® QCS8450 | 45.055 ms | 5 - 351 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 32.961 ms | 5 - 11 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 23.439 ms | 5 - 5 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 11.581 ms | 5 - 322 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA7255P | 98.233 ms | 1 - 308 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 34.076 ms | 2 - 263 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 11.581 ms | 5 - 322 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 8.94 ms | 5 - 336 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® X2 Elite | 16.441 ms | 2 - 2 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® X Elite | 30.322 ms | 2 - 2 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 22.199 ms | 2 - 474 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-8275 | 35.72 ms | 2 - 7 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 30.542 ms | 3 - 350 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA8775P | 35.951 ms | 1 - 370 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA8650P | 35.951 ms | 1 - 370 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA8255P | 35.951 ms | 1 - 370 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-9075 | 36.067 ms | 2 - 6 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-X7181 | 30.322 ms | 2 - 2 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ Q-8750 | 17.011 ms | 0 - 371 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA7255P | 90.234 ms | 2 - 371 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Elite Mobile | 17.011 ms | 0 - 371 MB | NPU | Conditional-DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 Mobile | 15.071 ms | 2 - 394 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 16.076 ms | 0 - 437 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 45.236 ms | 0 - 374 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 31.263 ms | 0 - 94 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 22.313 ms | 0 - 2 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Qualcomm® SA8775P | 30.255 ms | 0 - 366 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Qualcomm® SA8650P | 30.255 ms | 0 - 366 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Qualcomm® SA8255P | 30.255 ms | 0 - 366 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Qualcomm® QCS8450 | 45.236 ms | 0 - 374 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 30.834 ms | 0 - 93 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 12.266 ms | 0 - 343 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Qualcomm® SA7255P | 94.001 ms | 0 - 334 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Qualcomm® SA8295P | 35.171 ms | 0 - 289 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Elite Mobile | 12.266 ms | 0 - 343 MB | NPU | Conditional-DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 9.558 ms | 0 - 356 MB | NPU ## License * The license for the original implementation of Conditional-DETR-ResNet50 can be found [here](https://github.com/huggingface/transformers/blob/main/LICENSE). ## References * [Conditional {DETR} for Fast Training Convergence](https://arxiv.org/abs/2108.06152) * [Source Model Implementation](https://github.com/huggingface/transformers/tree/main/src/transformers/models/conditional_detr) ## Community * For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).