{ "cells": [ { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "import clip.clip as clip\n", "import os\n", "import torch\n", "from collections import OrderedDict" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "path = 'your_model_path/clip_visual_encoder'" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "model, _ = clip.load(\"ViT-B/16\", device='cpu')\n", "new_state_dict = OrderedDict()\n", "for k, v in model.state_dict().items():\n", " if 'visual.' in k:\n", " new_state_dict[k[7:]] = v\n", "torch.save(new_state_dict, os.path.join(path, 'vit_b16.pth'))" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "model, _ = clip.load(\"ViT-L/14\", device='cpu')\n", "new_state_dict = OrderedDict()\n", "for k, v in model.state_dict().items():\n", " if 'visual.' in k:\n", " new_state_dict[k[7:]] = v\n", "torch.save(new_state_dict, os.path.join(path, 'vit_l14.pth'))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "model, _ = clip.load(\"ViT-L/14@336px\", device='cpu')\n", "new_state_dict = OrderedDict()\n", "for k, v in model.state_dict().items():\n", " if 'visual.' in k:\n", " new_state_dict[k[7:]] = v\n", "torch.save(new_state_dict, os.path.join(path, 'vit_l14_336.pth'))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3.7.13 ('torch1.9')", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.13" }, "orig_nbformat": 4, "vscode": { "interpreter": { "hash": "c30e0be9d1dabfc31a056b9daab5ce1d15284c0e9e5af7f56f8931344ec84c24" } } }, "nbformat": 4, "nbformat_minor": 2 }