Upload folder using huggingface_hub

README.md

@@ -1,12 +1,6 @@
 ---
-title: Texttoimg
-emoji: 📈
-colorFrom: green
-colorTo: indigo
+title: texttoimg
+app_file: 1_build_text_image_search_engine9.ipynb
 sdk: gradio
 sdk_version: 3.35.2
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,172 @@
+import pandas as pd
+import  time
+from zipfile import ZipFile
+
+with ZipFile('reverse_image_search.zip', 'r') as zip:
+    # printing all the contents of the zip file
+    # extracting all the files
+    print('Extracting all the files now...')
+    zip.extractall()
+    print('Done!')
+
+df = pd.read_csv('reverse_image_search.csv')
+df.head()
+
+import cv2
+from towhee.types.image import Image
+
+id_img = df.set_index('id')['path'].to_dict()
+def read_images(results):
+    imgs = []
+    for re in results:
+        path = id_img[re.id]
+        imgs.append(Image(cv2.imread(path), 'BGR'))
+    return imgs
+
+
+
+from milvus import default_server
+from pymilvus import connections, utility
+default_server.start()
+
+connections.connect(host='127.0.0.1', port=default_server.listen_port)
+
+default_server.listen_port
+
+time.sleep(20)
+print(utility.get_server_version())
+
+
+from pymilvus import connections, FieldSchema, CollectionSchema, DataType, Collection, utility
+
+def create_milvus_collection(collection_name, dim):
+    connections.connect(host='127.0.0.1', port='19530')
+    
+    if utility.has_collection(collection_name):
+        utility.drop_collection(collection_name)
+    
+    fields = [
+    FieldSchema(name='id', dtype=DataType.INT64, descrition='ids', is_primary=True, auto_id=False),
+    FieldSchema(name='embedding', dtype=DataType.FLOAT_VECTOR, descrition='embedding vectors', dim=dim)
+    ]
+    schema = CollectionSchema(fields=fields, description='text image search')
+    collection = Collection(name=collection_name, schema=schema)
+
+    # create IVF_FLAT index for collection.
+    index_params = {
+        'metric_type':'L2',
+        'index_type':"IVF_FLAT",
+        'params':{"nlist":512}
+    }
+    collection.create_index(field_name="embedding", index_params=index_params)
+    return collection
+
+collection = create_milvus_collection('text_image_search', 512)
+
+
+from towhee import ops, pipe, DataCollection
+import numpy as np
+
+###. This section needs to have the teddy.png in the folder. Else it will throw an error.
+p = (
+    pipe.input('path')
+    .map('path', 'img', ops.image_decode.cv2('rgb'))
+    .map('img', 'vec', ops.image_text_embedding.clip(model_name='clip_vit_base_patch16', modality='image'))
+    .map('vec', 'vec', lambda x: x / np.linalg.norm(x))
+    .output('img', 'vec')
+)
+
+DataCollection(p('./teddy.png')).show()
+
+p2 = (
+    pipe.input('text')
+    .map('text', 'vec', ops.image_text_embedding.clip(model_name='clip_vit_base_patch16', modality='text'))
+    .map('vec', 'vec', lambda x: x / np.linalg.norm(x))
+    .output('text', 'vec')
+)
+
+DataCollection(p2("A teddybear on a skateboard in Times Square.")).show()
+
+time.sleep(60)
+collection = create_milvus_collection('text_image_search', 512)
+
+def read_csv(csv_path, encoding='utf-8-sig'):
+    import csv
+    with open(csv_path, 'r', encoding=encoding) as f:
+        data = csv.DictReader(f)
+        for line in data:
+            yield int(line['id']), line['path']
+
+p3 = (
+    pipe.input('csv_file')
+    .flat_map('csv_file', ('id', 'path'), read_csv)
+    .map('path', 'img', ops.image_decode.cv2('rgb'))
+    .map('img', 'vec', ops.image_text_embedding.clip(model_name='clip_vit_base_patch16', modality='image'))
+    .map('vec', 'vec', lambda x: x / np.linalg.norm(x))
+    .map(('id', 'vec'), (), ops.ann_insert.milvus_client(host='127.0.0.1', port='19530', collection_name='text_image_search'))
+    .output()
+)
+
+ret = p3('reverse_image_search.csv')
+
+
+time.sleep(120)
+collection.load()
+
+
+time.sleep(120)
+print('Total number of inserted data is {}.'.format(collection.num_entities))
+
+
+import pandas as pd
+import cv2
+
+def read_image(image_ids):
+    df = pd.read_csv('reverse_image_search.csv')
+    id_img = df.set_index('id')['path'].to_dict()
+    imgs = []
+    decode = ops.image_decode.cv2('rgb')
+    for image_id in image_ids:
+        path = id_img[image_id]
+        imgs.append(decode(path))
+    return imgs
+
+
+p4 = (
+    pipe.input('text')
+    .map('text', 'vec', ops.image_text_embedding.clip(model_name='clip_vit_base_patch16', modality='text'))
+    .map('vec', 'vec', lambda x: x / np.linalg.norm(x))
+    .map('vec', 'result', ops.ann_search.milvus_client(host='127.0.0.1', port='19530', collection_name='text_image_search', limit=5))
+    .map('result', 'image_ids', lambda x: [item[0] for item in x])
+    .map('image_ids', 'images', read_image)
+    .output('text', 'images')
+)
+
+DataCollection(p4("A white dog")).show()
+DataCollection(p4("A black dog")).show()
+
+search_pipeline = (
+    pipe.input('text')
+    .map('text', 'vec', ops.image_text_embedding.clip(model_name='clip_vit_base_patch16', modality='text'))
+    .map('vec', 'vec', lambda x: x / np.linalg.norm(x))
+    .map('vec', 'result', ops.ann_search.milvus_client(host='127.0.0.1', port='19530', collection_name='text_image_search', limit=5))
+    .map('result', 'image_ids', lambda x: [item[0] for item in x])
+    .output('image_ids')
+)
+
+def search(text):
+    df = pd.read_csv('reverse_image_search.csv')
+    id_img = df.set_index('id')['path'].to_dict()
+    imgs = []
+    image_ids = search_pipeline(text).to_list()[0][0]
+    return [id_img[image_id] for image_id in image_ids]
+
+
+import gradio
+
+interface = gradio.Interface(search, 
+                             gradio.inputs.Textbox(lines=1),
+                             [gradio.outputs.Image(type="filepath", label=None) for _ in range(5)]
+                            )
+
+interface.launch(inline=True, share=True)

requirements.txt

@@ -0,0 +1,127 @@
+aiofiles==23.1.0
+aiohttp==3.8.4
+aiosignal==1.3.1
+altair==5.0.1
+annotated-types==0.5.0
+anyio==3.7.0
+appnope==0.1.3
+asttokens==2.2.1
+async-timeout==4.0.2
+attrs==23.1.0
+backcall==0.2.0
+bleach==6.0.0
+certifi==2023.5.7
+charset-normalizer==3.1.0
+click==8.1.3
+comm==0.1.3
+contourpy==1.1.0
+cycler==0.11.0
+debugpy==1.6.7
+decorator==5.1.1
+docutils==0.20.1
+environs==9.5.0
+executing==1.2.0
+fastapi==0.99.1
+ffmpy==0.3.0
+filelock==3.12.2
+fonttools==4.40.0
+frozenlist==1.3.3
+fsspec==2023.6.0
+gradio==3.35.2
+gradio_client==0.2.7
+grpcio==1.53.0
+h11==0.14.0
+httpcore==0.17.2
+httpx==0.24.1
+huggingface-hub==0.15.1
+idna==3.4
+importlib-metadata==6.7.0
+ipykernel==6.24.0
+ipython==8.14.0
+jaraco.classes==3.2.3
+jedi==0.18.2
+Jinja2==3.1.2
+jsonschema==4.17.3
+jupyter_client==8.3.0
+jupyter_core==5.3.1
+keyring==24.2.0
+kiwisolver==1.4.4
+linkify-it-py==2.0.2
+markdown-it-py==2.2.0
+MarkupSafe==2.1.3
+marshmallow==3.19.0
+matplotlib==3.7.1
+matplotlib-inline==0.1.6
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+milvus==2.2.10
+more-itertools==9.1.0
+mpmath==1.3.0
+multidict==6.0.4
+nest-asyncio==1.5.6
+networkx==3.1
+numpy==1.25.0
+opencv-python==4.8.0.74
+orjson==3.9.1
+packaging==23.1
+pandas==2.0.3
+parso==0.8.3
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==10.0.0
+pkginfo==1.9.6
+platformdirs==3.8.0
+prompt-toolkit==3.0.38
+protobuf==4.23.3
+psutil==5.9.5
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pydantic==1.10.10
+pydantic_core==2.0.1
+pydub==0.25.1
+Pygments==2.15.1
+pymilvus==2.2.11
+pyparsing==3.1.0
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+python-multipart==0.0.6
+pytz==2023.3
+PyYAML==6.0
+pyzmq==25.1.0
+readme-renderer==40.0
+regex==2023.6.3
+requests==2.31.0
+requests-toolbelt==1.0.0
+rfc3986==2.0.0
+rich==13.4.2
+safetensors==0.3.1
+semantic-version==2.10.0
+six==1.16.0
+sniffio==1.3.0
+stack-data==0.6.2
+starlette==0.27.0
+sympy==1.12
+tabulate==0.9.0
+tenacity==8.2.2
+tokenizers==0.13.3
+toolz==0.12.0
+torch==2.0.1
+torchvision==0.15.2
+tornado==6.3.2
+towhee==1.1.0
+tqdm==4.65.0
+traitlets==5.9.0
+transformers==4.30.2
+twine==4.0.2
+typing_extensions==4.7.1
+tzdata==2023.3
+uc-micro-py==1.0.2
+ujson==5.8.0
+urllib3==2.0.3
+uvicorn==0.22.0
+wcwidth==0.2.6
+webencodings==0.5.1
+websockets==11.0.3
+yarl==1.9.2
+zipp==3.15.0

reverse_image_search.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:736813a3307070aae31c41fee6fad93fd4a86b2dcee012754f2c4b7cdb8b9464
+size 125643445