--- library_name: pytorch license: other tags: - foundation - android pipeline_tag: image-classification --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/web-assets/model_demo.png) # OpenAI-Clip: Optimized for Qualcomm Devices Contrastive Language-Image Pre-Training (CLIP) uses a ViT like transformer to get visual features and a causal language model to get the text features. Both the text and visual features can then be used for a variety of zero-shot learning tasks. This is based on the implementation of OpenAI-Clip found [here](https://github.com/openai/CLIP/). 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/blob/main/src/qai_hub_models/models/openai_clip) 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.com) 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 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.51.0/openai_clip-onnx-float.zip) | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.51.0/openai_clip-qnn_dlc-float.zip) | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.51.0/openai_clip-tflite-float.zip) For more device-specific assets and performance metrics, visit **[OpenAI-Clip on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/openai_clip)**. ### Option 2: Export with Custom Configurations Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/openai_clip) 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 [OpenAI-Clip on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/openai_clip) for usage instructions. ## Model Details **Model Type:** Model_use_case.image_classification **Model Stats:** - Model checkpoint: ViT-B/16 - Image input resolution: 224x224 - Text context length: 77 - Number of parameters: 150M - Model size (float): 571 MB ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | OpenAI-Clip | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.997 ms | 1 - 496 MB | NPU | OpenAI-Clip | ONNX | float | Snapdragon® X2 Elite | 7.194 ms | 291 - 291 MB | NPU | OpenAI-Clip | ONNX | float | Snapdragon® X Elite | 16.488 ms | 291 - 291 MB | NPU | OpenAI-Clip | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 11.216 ms | 1 - 563 MB | NPU | OpenAI-Clip | ONNX | float | Qualcomm® QCS8550 (Proxy) | 15.815 ms | 0 - 324 MB | NPU | OpenAI-Clip | ONNX | float | Qualcomm® QCS9075 | 20.535 ms | 0 - 4 MB | NPU | OpenAI-Clip | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 9.125 ms | 0 - 497 MB | NPU | OpenAI-Clip | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 9.0 ms | 0 - 417 MB | NPU | OpenAI-Clip | QNN_DLC | float | Snapdragon® X2 Elite | 9.853 ms | 1 - 1 MB | NPU | OpenAI-Clip | QNN_DLC | float | Snapdragon® X Elite | 21.261 ms | 1 - 1 MB | NPU | OpenAI-Clip | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 14.091 ms | 0 - 765 MB | NPU | OpenAI-Clip | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 59.715 ms | 1 - 570 MB | NPU | OpenAI-Clip | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 20.792 ms | 1 - 3 MB | NPU | OpenAI-Clip | QNN_DLC | float | Qualcomm® SA8775P | 23.145 ms | 1 - 566 MB | NPU | OpenAI-Clip | QNN_DLC | float | Qualcomm® QCS9075 | 23.793 ms | 1 - 3 MB | NPU | OpenAI-Clip | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 24.003 ms | 0 - 611 MB | NPU | OpenAI-Clip | QNN_DLC | float | Qualcomm® SA7255P | 59.715 ms | 1 - 570 MB | NPU | OpenAI-Clip | QNN_DLC | float | Qualcomm® SA8295P | 24.676 ms | 1 - 530 MB | NPU | OpenAI-Clip | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 11.686 ms | 1 - 586 MB | NPU | OpenAI-Clip | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 9.003 ms | 0 - 430 MB | NPU | OpenAI-Clip | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 14.171 ms | 0 - 773 MB | NPU | OpenAI-Clip | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 59.724 ms | 0 - 567 MB | NPU | OpenAI-Clip | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 20.522 ms | 0 - 3 MB | NPU | OpenAI-Clip | TFLITE | float | Qualcomm® SA8775P | 23.212 ms | 0 - 564 MB | NPU | OpenAI-Clip | TFLITE | float | Qualcomm® QCS9075 | 23.685 ms | 0 - 296 MB | NPU | OpenAI-Clip | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 24.376 ms | 0 - 617 MB | NPU | OpenAI-Clip | TFLITE | float | Qualcomm® SA7255P | 59.724 ms | 0 - 567 MB | NPU | OpenAI-Clip | TFLITE | float | Qualcomm® SA8295P | 24.793 ms | 0 - 532 MB | NPU | OpenAI-Clip | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 11.354 ms | 0 - 598 MB | NPU ## License * The license for the original implementation of OpenAI-Clip can be found [here](https://github.com/openai/CLIP/blob/main/LICENSE). ## References * [Learning Transferable Visual Models From Natural Language Supervision](https://arxiv.org/abs/2103.00020) * [Source Model Implementation](https://github.com/openai/CLIP/) ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).