v1.0

CLIP/setup.py

+import os
+
+import pkg_resources
+from setuptools import setup, find_packages
+
+setup(
+    name="clip",
+    py_modules=["clip"],
+    version="1.0",
+    description="",
+    author="OpenAI",
+    packages=find_packages(exclude=["tests*"]),
+    install_requires=[
+        str(r)
+        for r in pkg_resources.parse_requirements(
+            open(os.path.join(os.path.dirname(__file__), "requirements.txt"))
+        )
+    ],
+    include_package_data=True,
+    extras_require={'dev': ['pytest']},
+)

CLIP/tests/test_consistency.py

+import numpy as np
+import pytest
+import torch
+from PIL import Image
+
+import clip
+
+
+@pytest.mark.parametrize('model_name', clip.available_models())
+def test_consistency(model_name):
+    device = "cpu"
+    jit_model, transform = clip.load(model_name, device=device, jit=True)
+    py_model, _ = clip.load(model_name, device=device, jit=False)
+
+    image = transform(Image.open("CLIP.png")).unsqueeze(0).to(device)
+    text = clip.tokenize(["a diagram", "a dog", "a cat"]).to(device)
+
+    with torch.no_grad():
+        logits_per_image, _ = jit_model(image, text)
+        jit_probs = logits_per_image.softmax(dim=-1).cpu().numpy()
+
+        logits_per_image, _ = py_model(image, text)
+        py_probs = logits_per_image.softmax(dim=-1).cpu().numpy()
+
+    assert np.allclose(jit_probs, py_probs, atol=0.01, rtol=0.1)

LICENSE

+MIT License
+
+Copyright (c) 2024 gpt-omni
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

__init__.py

+import sys
+import os
+
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))

docker/Dockerfile

+FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.3.0-ubuntu22.04-dtk24.04.2-py3.10
+ENV DEBIAN_FRONTEND=noninteractive
+# RUN yum update && yum install -y git cmake wget build-essential
+# RUN source /opt/dtk-24.04.2/env.sh
+# # 安装pip相关依赖
+COPY requirements.txt requirements.txt
+RUN pip3 install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
+

docker/requirements.txt

+#torch==2.3.1
+#torchvision==0.18.1
+#torchaudio==2.3.1
+litgpt==0.4.3
+snac==1.2.0
+soundfile==0.12.1
+openai-whisper
+streamlit==1.37.1
+# PyAudio==0.2.14
+pydub==0.25.1
+onnxruntime==1.19.0
+# numpy==1.26.3
+gradio==4.42.0
+librosa==0.10.2.post1
+#flask==3.0.3
+fire
+transformers==4.45.2
+tokenizers==0.20.1
+#git+https://github.com/mini-omni/CLIP.git

docker_start.sh

+docker run -it --shm-size=64G -v $PWD/mini-omni2:/home/mini-omni2 -v /public/DL_DATA/AI:/home/AI -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=//dev/dri/ --group-add video --name omni2 83714c19d308 bash                                                                                                                                                                                       
+# python -m torch.utils.collect_env