xclele/yolov10
1
0
Fork 0
mirror of https://github.com/THU-MIG/yolov10.git synced 2025-05-23 21:44:22 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update H1 in Explorer API docs (#7813)

Browse Source
This commit is contained in:
Muhammad Rizwan Munawar 2024-01-25 13:10:49 +05:00 committed by GitHub
parent a2222b4283
commit c460ad28f8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 602 additions and 519 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/en/datasets/explorer/api.md
View File

@ -314,11 +314,11 @@ plt.show()
Start creating your own CV dataset exploration reports using the Explorer API. For inspiration, check out the Start creating your own CV dataset exploration reports using the Explorer API. For inspiration, check out the
# Apps Built Using Ultralytics Explorer ## Apps Built Using Ultralytics Explorer
Try our GUI Demo based on Explorer API Try our GUI Demo based on Explorer API
# Coming Soon ## Coming Soon
- [ ] Merge specific labels from datasets. Example - Import all `person` labels from COCO and `car` labels from Cityscapes - [ ] Merge specific labels from datasets. Example - Import all `person` labels from COCO and `car` labels from Cityscapes
- [ ] Remove images that have a higher similarity index than the given threshold - [ ] Remove images that have a higher similarity index than the given threshold

2
docs/en/datasets/explorer/dashboard.md
View File

@ -1,5 +1,5 @@
--- ---
comments: 5rue comments: true
description: Learn about Ultralytics Explorer GUI for semantic search, SQL queries, and AI-powered natural language search in CV datasets. description: Learn about Ultralytics Explorer GUI for semantic search, SQL queries, and AI-powered natural language search in CV datasets.
keywords: Ultralytics, Explorer GUI, semantic search, vector similarity search, AI queries, SQL queries, computer vision, dataset exploration, image search, OpenAI integration keywords: Ultralytics, Explorer GUI, semantic search, vector similarity search, AI queries, SQL queries, computer vision, dataset exploration, image search, OpenAI integration
--- ---

165
docs/en/datasets/explorer/explorer.ipynb
View File

@ -3,7 +3,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "aa923c26-81c8-4565-9277-1cb686e3702e", "id": "aa923c26-81c8-4565-9277-1cb686e3702e",
"metadata": {}, "metadata": {
"id": "aa923c26-81c8-4565-9277-1cb686e3702e"
},
"source": [ "source": [
"# VOC Exploration Example\n", "# VOC Exploration Example\n",
"<div align=\"center\">\n", "<div align=\"center\">\n",
@ -31,7 +33,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "2454d9ba-9db4-4b37-98e8-201ba285c92f", "id": "2454d9ba-9db4-4b37-98e8-201ba285c92f",
"metadata": {}, "metadata": {
"id": "2454d9ba-9db4-4b37-98e8-201ba285c92f"
},
"source": [ "source": [
"## Setup\n", "## Setup\n",
"Pip install `ultralytics` and [dependencies](https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml) and check software and hardware." "Pip install `ultralytics` and [dependencies](https://github.com/ultralytics/ultralytics/blob/main/pyproject.toml) and check software and hardware."
@ -41,7 +45,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "433f3a4d-a914-42cb-b0b6-be84a84e5e41", "id": "433f3a4d-a914-42cb-b0b6-be84a84e5e41",
"metadata": {}, "metadata": {
"id": "433f3a4d-a914-42cb-b0b6-be84a84e5e41"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"%pip install ultralytics[explorer] openai\n", "%pip install ultralytics[explorer] openai\n",
@ -53,7 +59,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "ae602549-3419-4909-9f82-35cba515483f", "id": "ae602549-3419-4909-9f82-35cba515483f",
"metadata": {}, "metadata": {
"id": "ae602549-3419-4909-9f82-35cba515483f"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"from ultralytics import Explorer" "from ultralytics import Explorer"
@ -62,9 +70,11 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "d8c06350-be8e-45cf-b3a6-b5017bbd943c", "id": "d8c06350-be8e-45cf-b3a6-b5017bbd943c",
"metadata": {}, "metadata": {
"id": "d8c06350-be8e-45cf-b3a6-b5017bbd943c"
},
"source": [ "source": [
"# Similarity search\n", "## Similarity search\n",
"Utilize the power of vector similarity search to find the similar data points in your dataset along with their distance in the embedding space. Simply create an embeddings table for the given dataset-model pair. It is only needed once and it is reused automatically.\n" "Utilize the power of vector similarity search to find the similar data points in your dataset along with their distance in the embedding space. Simply create an embeddings table for the given dataset-model pair. It is only needed once and it is reused automatically.\n"
] ]
}, },
@ -72,7 +82,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "334619da-6deb-4b32-9fe0-74e0a79cee20", "id": "334619da-6deb-4b32-9fe0-74e0a79cee20",
"metadata": {}, "metadata": {
"id": "334619da-6deb-4b32-9fe0-74e0a79cee20"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"exp = Explorer(\"VOC.yaml\", model=\"yolov8n.pt\")\n", "exp = Explorer(\"VOC.yaml\", model=\"yolov8n.pt\")\n",
@ -82,7 +94,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "b6c5e42d-bc7e-4b4c-bde0-643072a2165d", "id": "b6c5e42d-bc7e-4b4c-bde0-643072a2165d",
"metadata": {}, "metadata": {
"id": "b6c5e42d-bc7e-4b4c-bde0-643072a2165d"
},
"source": [ "source": [
"One the embeddings table is built, you can get run semantic search in any of the following ways:\n", "One the embeddings table is built, you can get run semantic search in any of the following ways:\n",
"- On a given index / list of indices in the dataset like - `exp.get_similar(idx=[1,10], limit=10)`\n", "- On a given index / list of indices in the dataset like - `exp.get_similar(idx=[1,10], limit=10)`\n",
@ -97,7 +111,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "b485f05b-d92d-42bc-8da7-5e361667b341", "id": "b485f05b-d92d-42bc-8da7-5e361667b341",
"metadata": {}, "metadata": {
"id": "b485f05b-d92d-42bc-8da7-5e361667b341"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"similar = exp.get_similar(idx=1, limit=10)\n", "similar = exp.get_similar(idx=1, limit=10)\n",
@ -107,7 +123,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "acf4b489-2161-4176-a1fe-d1d067d8083d", "id": "acf4b489-2161-4176-a1fe-d1d067d8083d",
"metadata": {}, "metadata": {
"id": "acf4b489-2161-4176-a1fe-d1d067d8083d"
},
"source": [ "source": [
"You can use the also plot the similar samples directly using the `plot_similar` util\n", "You can use the also plot the similar samples directly using the `plot_similar` util\n",
"<p>\n", "<p>\n",
@ -120,7 +138,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "9dbfe7d0-8613-4529-adb6-6e0632d7cce7", "id": "9dbfe7d0-8613-4529-adb6-6e0632d7cce7",
"metadata": {}, "metadata": {
"id": "9dbfe7d0-8613-4529-adb6-6e0632d7cce7"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"exp.plot_similar(idx=6500, limit=20)\n", "exp.plot_similar(idx=6500, limit=20)\n",
@ -131,7 +151,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "260e09bf-4960-4089-a676-cb0e76ff3c0d", "id": "260e09bf-4960-4089-a676-cb0e76ff3c0d",
"metadata": {}, "metadata": {
"id": "260e09bf-4960-4089-a676-cb0e76ff3c0d"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"exp.plot_similar(img=\"https://ultralytics.com/images/bus.jpg\", limit=10, labels=False) # Can also pass any external images\n" "exp.plot_similar(img=\"https://ultralytics.com/images/bus.jpg\", limit=10, labels=False) # Can also pass any external images\n"
@ -140,7 +162,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "faa0b7a7-6318-40e4-b0f4-45a8113bdc3a", "id": "faa0b7a7-6318-40e4-b0f4-45a8113bdc3a",
"metadata": {}, "metadata": {
"id": "faa0b7a7-6318-40e4-b0f4-45a8113bdc3a"
},
"source": [ "source": [
"<p>\n", "<p>\n",
"<img src=\"https://github.com/AyushExel/assets/assets/15766192/8e011195-b0da-43ef-b3cd-5fb6f383037e\">\n", "<img src=\"https://github.com/AyushExel/assets/assets/15766192/8e011195-b0da-43ef-b3cd-5fb6f383037e\">\n",
@ -151,7 +175,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "0cea63f1-71f1-46da-af2b-b1b7d8f73553", "id": "0cea63f1-71f1-46da-af2b-b1b7d8f73553",
"metadata": {}, "metadata": {
"id": "0cea63f1-71f1-46da-af2b-b1b7d8f73553"
},
"source": [ "source": [
"## 2. Ask AI: Search or filter with Natural Language\n", "## 2. Ask AI: Search or filter with Natural Language\n",
"You can prompt the Explorer object with the kind of data points you want to see and it'll try to return a dataframe with those. Because it is powered by LLMs, it doesn't always get it right. In that case, it'll return None.\n", "You can prompt the Explorer object with the kind of data points you want to see and it'll try to return a dataframe with those. Because it is powered by LLMs, it doesn't always get it right. In that case, it'll return None.\n",
@ -166,7 +192,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "92fb92ac-7f76-465a-a9ba-ea7492498d9c", "id": "92fb92ac-7f76-465a-a9ba-ea7492498d9c",
"metadata": {}, "metadata": {
"id": "92fb92ac-7f76-465a-a9ba-ea7492498d9c"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"df = exp.ask_ai(\"show me images containing more than 10 objects with at least 2 persons\")\n", "df = exp.ask_ai(\"show me images containing more than 10 objects with at least 2 persons\")\n",
@ -176,7 +204,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "f2a7d26e-0ce5-4578-ad1a-b1253805280f", "id": "f2a7d26e-0ce5-4578-ad1a-b1253805280f",
"metadata": {}, "metadata": {
"id": "f2a7d26e-0ce5-4578-ad1a-b1253805280f"
},
"source": [ "source": [
"for plotting these results you can use `plot_query_result` util\n", "for plotting these results you can use `plot_query_result` util\n",
"Example:\n", "Example:\n",
@ -194,7 +224,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "b1cfab84-9835-4da0-8e9a-42b30cf84511", "id": "b1cfab84-9835-4da0-8e9a-42b30cf84511",
"metadata": {}, "metadata": {
"id": "b1cfab84-9835-4da0-8e9a-42b30cf84511"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"# plot\n", "# plot\n",
@ -208,7 +240,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "35315ae6-d827-40e4-8813-279f97a83b34", "id": "35315ae6-d827-40e4-8813-279f97a83b34",
"metadata": {}, "metadata": {
"id": "35315ae6-d827-40e4-8813-279f97a83b34"
},
"source": [ "source": [
"## 3. Run SQL queries on your Dataset!\n", "## 3. Run SQL queries on your Dataset!\n",
"Sometimes you might want to investigate a certain type of entries in your dataset. For this Explorer allows you to execute SQL queries.\n", "Sometimes you might want to investigate a certain type of entries in your dataset. For this Explorer allows you to execute SQL queries.\n",
@ -227,7 +261,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "8cd1072f-3100-4331-a0e3-4e2f6b1005bf", "id": "8cd1072f-3100-4331-a0e3-4e2f6b1005bf",
"metadata": {}, "metadata": {
"id": "8cd1072f-3100-4331-a0e3-4e2f6b1005bf"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"table = exp.sql_query(\"WHERE labels LIKE '%person, person%' AND labels LIKE '%dog%' LIMIT 10\")\n", "table = exp.sql_query(\"WHERE labels LIKE '%person, person%' AND labels LIKE '%dog%' LIMIT 10\")\n",
@ -237,7 +273,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "debf8a00-c9f6-448b-bd3b-454cf62f39ab", "id": "debf8a00-c9f6-448b-bd3b-454cf62f39ab",
"metadata": {}, "metadata": {
"id": "debf8a00-c9f6-448b-bd3b-454cf62f39ab"
},
"source": [ "source": [
"Just like similarity search, you also get a util to directly plot the sql queries using `exp.plot_sql_query`\n", "Just like similarity search, you also get a util to directly plot the sql queries using `exp.plot_sql_query`\n",
"<img src=\"https://github.com/AyushExel/assets/assets/15766192/f8b66629-8dd0-419e-8f44-9837969ba678\">\n" "<img src=\"https://github.com/AyushExel/assets/assets/15766192/f8b66629-8dd0-419e-8f44-9837969ba678\">\n"
@ -247,7 +285,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "18b977e7-d048-4b22-b8c4-084a03b04f23", "id": "18b977e7-d048-4b22-b8c4-084a03b04f23",
"metadata": {}, "metadata": {
"id": "18b977e7-d048-4b22-b8c4-084a03b04f23"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"exp.plot_sql_query(\"WHERE labels LIKE '%person, person%' AND labels LIKE '%dog%' LIMIT 10\", labels=True)" "exp.plot_sql_query(\"WHERE labels LIKE '%person, person%' AND labels LIKE '%dog%' LIMIT 10\", labels=True)"
@ -256,7 +296,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "f26804c5-840b-4fd1-987f-e362f29e3e06", "id": "f26804c5-840b-4fd1-987f-e362f29e3e06",
"metadata": {}, "metadata": {
"id": "f26804c5-840b-4fd1-987f-e362f29e3e06"
},
"source": [ "source": [
"## 3. Working with embeddings Table (Advanced)\n", "## 3. Working with embeddings Table (Advanced)\n",
"Explorer works on [LanceDB](https://lancedb.github.io/lancedb/) tables internally. You can access this table directly, using `Explorer.table` object and run raw queries, push down pre and post filters, etc." "Explorer works on [LanceDB](https://lancedb.github.io/lancedb/) tables internally. You can access this table directly, using `Explorer.table` object and run raw queries, push down pre and post filters, etc."
@ -266,7 +308,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "ea69260a-3407-40c9-9f42-8b34a6e6af7a", "id": "ea69260a-3407-40c9-9f42-8b34a6e6af7a",
"metadata": {}, "metadata": {
"id": "ea69260a-3407-40c9-9f42-8b34a6e6af7a"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"table = exp.table\n", "table = exp.table\n",
@ -276,7 +320,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "238db292-8610-40b3-9af7-dfd6be174892", "id": "238db292-8610-40b3-9af7-dfd6be174892",
"metadata": {}, "metadata": {
"id": "238db292-8610-40b3-9af7-dfd6be174892"
},
"source": [ "source": [
"### Run raw queries\n", "### Run raw queries\n",
"Vector Search finds the nearest vectors from the database. In a recommendation system or search engine, you can find similar products from the one you searched. In LLM and other AI applications, each data point can be presented by the embeddings generated from some models, it returns the most relevant features.\n", "Vector Search finds the nearest vectors from the database. In a recommendation system or search engine, you can find similar products from the one you searched. In LLM and other AI applications, each data point can be presented by the embeddings generated from some models, it returns the most relevant features.\n",
@ -297,7 +343,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "d74430fe-5aee-45a1-8863-3f2c31338792", "id": "d74430fe-5aee-45a1-8863-3f2c31338792",
"metadata": {}, "metadata": {
"id": "d74430fe-5aee-45a1-8863-3f2c31338792"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"dummy_img_embedding = [i for i in range(256)]\n", "dummy_img_embedding = [i for i in range(256)]\n",
@ -307,7 +355,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "587486b4-0d19-4214-b994-f032fb2e8eb5", "id": "587486b4-0d19-4214-b994-f032fb2e8eb5",
"metadata": {}, "metadata": {
"id": "587486b4-0d19-4214-b994-f032fb2e8eb5"
},
"source": [ "source": [
"### Inter-conversion to popular data formats" "### Inter-conversion to popular data formats"
] ]
@ -316,7 +366,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "bb2876ea-999b-4eba-96bc-c196ba02c41c", "id": "bb2876ea-999b-4eba-96bc-c196ba02c41c",
"metadata": {}, "metadata": {
"id": "bb2876ea-999b-4eba-96bc-c196ba02c41c"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"df = table.to_pandas()\n", "df = table.to_pandas()\n",
@ -326,7 +378,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "42659d63-ad76-49d6-8dfc-78d77278db72", "id": "42659d63-ad76-49d6-8dfc-78d77278db72",
"metadata": {}, "metadata": {
"id": "42659d63-ad76-49d6-8dfc-78d77278db72"
},
"source": [ "source": [
"### Work with Embeddings\n", "### Work with Embeddings\n",
"You can access the raw embedding from lancedb Table and analyse it. The image embeddings are stored in column `vector`" "You can access the raw embedding from lancedb Table and analyse it. The image embeddings are stored in column `vector`"
@ -336,7 +390,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "66d69e9b-046e-41c8-80d7-c0ee40be3bca", "id": "66d69e9b-046e-41c8-80d7-c0ee40be3bca",
"metadata": {}, "metadata": {
"id": "66d69e9b-046e-41c8-80d7-c0ee40be3bca"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"import numpy as np\n", "import numpy as np\n",
@ -348,7 +404,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "e8df0a49-9596-4399-954b-b8ae1fd7a602", "id": "e8df0a49-9596-4399-954b-b8ae1fd7a602",
"metadata": {}, "metadata": {
"id": "e8df0a49-9596-4399-954b-b8ae1fd7a602"
},
"source": [ "source": [
"### Scatterplot\n", "### Scatterplot\n",
"One of the preliminary steps in analysing embeddings is by plotting them in 2D space via dimensionality reduction. Let's try an example\n", "One of the preliminary steps in analysing embeddings is by plotting them in 2D space via dimensionality reduction. Let's try an example\n",
@ -360,7 +418,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "d9a150e8-8092-41b3-82f8-2247f8187fc8", "id": "d9a150e8-8092-41b3-82f8-2247f8187fc8",
"metadata": {}, "metadata": {
"id": "d9a150e8-8092-41b3-82f8-2247f8187fc8"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"!pip install scikit-learn --q" "!pip install scikit-learn --q"
@ -370,7 +430,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "196079c3-45a9-4325-81ab-af79a881e37a", "id": "196079c3-45a9-4325-81ab-af79a881e37a",
"metadata": {}, "metadata": {
"id": "196079c3-45a9-4325-81ab-af79a881e37a"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"%matplotlib inline\n", "%matplotlib inline\n",
@ -400,7 +462,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "1c843c23-e3f2-490e-8d6c-212fa038a149", "id": "1c843c23-e3f2-490e-8d6c-212fa038a149",
"metadata": {}, "metadata": {
"id": "1c843c23-e3f2-490e-8d6c-212fa038a149"
},
"source": [ "source": [
"## 4. Similarity Index\n", "## 4. Similarity Index\n",
"Here's a simple example of an operation powered by the embeddings table. Explorer comes with a `similarity_index` operation-\n", "Here's a simple example of an operation powered by the embeddings table. Explorer comes with a `similarity_index` operation-\n",
@ -417,7 +481,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "953c2a5f-1b61-4acf-a8e4-ed08547dbafc", "id": "953c2a5f-1b61-4acf-a8e4-ed08547dbafc",
"metadata": {}, "metadata": {
"id": "953c2a5f-1b61-4acf-a8e4-ed08547dbafc"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"exp.plot_similarity_index(max_dist=0.2, top_k=0.01)" "exp.plot_similarity_index(max_dist=0.2, top_k=0.01)"
@ -426,7 +492,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "28228a9a-b727-45b5-8ca7-8db662c0b937", "id": "28228a9a-b727-45b5-8ca7-8db662c0b937",
"metadata": {}, "metadata": {
"id": "28228a9a-b727-45b5-8ca7-8db662c0b937"
},
"source": [ "source": [
"Now let's look at the output of the operation" "Now let's look at the output of the operation"
] ]
@ -435,7 +503,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "f4161aaa-20e6-4df0-8e87-d2293ee0530a", "id": "f4161aaa-20e6-4df0-8e87-d2293ee0530a",
"metadata": {}, "metadata": {
"id": "f4161aaa-20e6-4df0-8e87-d2293ee0530a"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"import numpy as np\n", "import numpy as np\n",
@ -447,7 +517,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "b01d5b1a-9adb-4c3c-a873-217c71527c8d", "id": "b01d5b1a-9adb-4c3c-a873-217c71527c8d",
"metadata": {}, "metadata": {
"id": "b01d5b1a-9adb-4c3c-a873-217c71527c8d"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"sim_idx" "sim_idx"
@ -456,7 +528,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "22b28e54-4fbb-400e-ad8c-7068cbba11c4", "id": "22b28e54-4fbb-400e-ad8c-7068cbba11c4",
"metadata": {}, "metadata": {
"id": "22b28e54-4fbb-400e-ad8c-7068cbba11c4"
},
"source": [ "source": [
"Let's create a query to see what data points have similarity count of more than 30 and plot images similar to them." "Let's create a query to see what data points have similarity count of more than 30 and plot images similar to them."
] ]
@ -465,7 +539,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "58d2557b-d401-43cf-937d-4f554c7bc808", "id": "58d2557b-d401-43cf-937d-4f554c7bc808",
"metadata": {}, "metadata": {
"id": "58d2557b-d401-43cf-937d-4f554c7bc808"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"import numpy as np\n", "import numpy as np\n",
@ -477,7 +553,9 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "a5ec8d76-271a-41ab-ac74-cf8c0084ba5e", "id": "a5ec8d76-271a-41ab-ac74-cf8c0084ba5e",
"metadata": {}, "metadata": {
"id": "a5ec8d76-271a-41ab-ac74-cf8c0084ba5e"
},
"source": [ "source": [
"You should see something like this\n", "You should see something like this\n",
"<img src=\"https://github.com/AyushExel/assets/assets/15766192/649bc366-ca2d-46ea-bfd9-3097cf575584\">\n" "<img src=\"https://github.com/AyushExel/assets/assets/15766192/649bc366-ca2d-46ea-bfd9-3097cf575584\">\n"
@ -487,7 +565,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "3a7b2ee3-9f35-48a2-9c38-38379516f4d2", "id": "3a7b2ee3-9f35-48a2-9c38-38379516f4d2",
"metadata": {}, "metadata": {
"id": "3a7b2ee3-9f35-48a2-9c38-38379516f4d2"
},
"outputs": [], "outputs": [],
"source": [ "source": [
"exp.plot_similar(idx=[7146, 14035]) # Using avg embeddings of 2 images" "exp.plot_similar(idx=[7146, 14035]) # Using avg embeddings of 2 images"
@ -511,6 +591,9 @@
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.9.6" "version": "3.9.6"
},
"colab": {
"provenance": []
} }
}, },
"nbformat": 4, "nbformat": 4,