ultralytics 8.3.10__py3-none-any.whl → 8.3.12__py3-none-any.whl

ultralytics/data/explorer/gui/dash.py

@@ -1,269 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-
-import sys
-import time
-from threading import Thread
-
-from ultralytics import Explorer
-from ultralytics.utils import ROOT, SETTINGS
-from ultralytics.utils.checks import check_requirements
-
-check_requirements(("streamlit>=1.29.0", "streamlit-select>=0.3"))
-
-import streamlit as st
-from streamlit_select import image_select
-
-
-def _get_explorer():
-    """Initializes and returns an instance of the Explorer class."""
-    exp = Explorer(data=st.session_state.get("dataset"), model=st.session_state.get("model"))
-    thread = Thread(
-        target=exp.create_embeddings_table,
-        kwargs={"force": st.session_state.get("force_recreate_embeddings"), "split": st.session_state.get("split")},
-    )
-    thread.start()
-    progress_bar = st.progress(0, text="Creating embeddings table...")
-    while exp.progress < 1:
-        time.sleep(0.1)
-        progress_bar.progress(exp.progress, text=f"Progress: {exp.progress * 100}%")
-    thread.join()
-    st.session_state["explorer"] = exp
-    progress_bar.empty()
-
-
-def init_explorer_form(data=None, model=None):
-    """Initializes an Explorer instance and creates embeddings table with progress tracking."""
-    if data is None:
-        datasets = ROOT / "cfg" / "datasets"
-        ds = [d.name for d in datasets.glob("*.yaml")]
-    else:
-        ds = [data]
-
-    prefixes = ["yolov8", "yolo11"]
-    sizes = ["n", "s", "m", "l", "x"]
-    tasks = ["", "-seg", "-pose"]
-    if model is None:
-        models = [f"{p}{s}{t}" for p in prefixes for s in sizes for t in tasks]
-    else:
-        models = [model]
-
-    splits = ["train", "val", "test"]
-
-    with st.form(key="explorer_init_form"):
-        col1, col2, col3 = st.columns(3)
-        with col1:
-            st.selectbox("Select dataset", ds, key="dataset")
-        with col2:
-            st.selectbox("Select model", models, key="model")
-        with col3:
-            st.selectbox("Select split", splits, key="split")
-        st.checkbox("Force recreate embeddings", key="force_recreate_embeddings")
-
-        st.form_submit_button("Explore", on_click=_get_explorer)
-
-
-def query_form():
-    """Sets up a form in Streamlit to initialize Explorer with dataset and model selection."""
-    with st.form("query_form"):
-        col1, col2 = st.columns([0.8, 0.2])
-        with col1:
-            st.text_input(
-                "Query",
-                "WHERE labels LIKE '%person%' AND labels LIKE '%dog%'",
-                label_visibility="collapsed",
-                key="query",
-            )
-        with col2:
-            st.form_submit_button("Query", on_click=run_sql_query)
-
-
-def ai_query_form():
-    """Sets up a Streamlit form for user input to initialize Explorer with dataset and model selection."""
-    with st.form("ai_query_form"):
-        col1, col2 = st.columns([0.8, 0.2])
-        with col1:
-            st.text_input("Query", "Show images with 1 person and 1 dog", label_visibility="collapsed", key="ai_query")
-        with col2:
-            st.form_submit_button("Ask AI", on_click=run_ai_query)
-
-
-def find_similar_imgs(imgs):
-    """Initializes a Streamlit form for AI-based image querying with custom input."""
-    exp = st.session_state["explorer"]
-    similar = exp.get_similar(img=imgs, limit=st.session_state.get("limit"), return_type="arrow")
-    paths = similar.to_pydict()["im_file"]
-    st.session_state["imgs"] = paths
-    st.session_state["res"] = similar
-
-
-def similarity_form(selected_imgs):
-    """Initializes a form for AI-based image querying with custom input in Streamlit."""
-    st.write("Similarity Search")
-    with st.form("similarity_form"):
-        subcol1, subcol2 = st.columns([1, 1])
-        with subcol1:
-            st.number_input(
-                "limit", min_value=None, max_value=None, value=25, label_visibility="collapsed", key="limit"
-            )
-
-        with subcol2:
-            disabled = not len(selected_imgs)
-            st.write("Selected: ", len(selected_imgs))
-            st.form_submit_button(
-                "Search",
-                disabled=disabled,
-                on_click=find_similar_imgs,
-                args=(selected_imgs,),
-            )
-        if disabled:
-            st.error("Select at least one image to search.")
-
-
-# def persist_reset_form():
-#    with st.form("persist_reset"):
-#        col1, col2 = st.columns([1, 1])
-#        with col1:
-#            st.form_submit_button("Reset", on_click=reset)
-#
-#        with col2:
-#            st.form_submit_button("Persist", on_click=update_state, args=("PERSISTING", True))
-
-
-def run_sql_query():
-    """Executes an SQL query and returns the results."""
-    st.session_state["error"] = None
-    query = st.session_state.get("query")
-    if query.rstrip().lstrip():
-        exp = st.session_state["explorer"]
-        res = exp.sql_query(query, return_type="arrow")
-        st.session_state["imgs"] = res.to_pydict()["im_file"]
-        st.session_state["res"] = res
-
-
-def run_ai_query():
-    """Execute SQL query and update session state with query results."""
-    if not SETTINGS["openai_api_key"]:
-        st.session_state["error"] = (
-            'OpenAI API key not found in settings. Please run yolo settings openai_api_key="..."'
-        )
-        return
-    import pandas  # scope for faster 'import ultralytics'
-
-    st.session_state["error"] = None
-    query = st.session_state.get("ai_query")
-    if query.rstrip().lstrip():
-        exp = st.session_state["explorer"]
-        res = exp.ask_ai(query)
-        if not isinstance(res, pandas.DataFrame) or res.empty:
-            st.session_state["error"] = "No results found using AI generated query. Try another query or rerun it."
-            return
-        st.session_state["imgs"] = res["im_file"].to_list()
-        st.session_state["res"] = res
-
-
-def reset_explorer():
-    """Resets the explorer to its initial state by clearing session variables."""
-    st.session_state["explorer"] = None
-    st.session_state["imgs"] = None
-    st.session_state["error"] = None
-
-
-def utralytics_explorer_docs_callback():
-    """Resets the explorer to its initial state by clearing session variables."""
-    with st.container(border=True):
-        st.image(
-            "https://raw.githubusercontent.com/ultralytics/assets/main/logo/Ultralytics_Logotype_Original.svg",
-            width=100,
-        )
-        st.markdown(
-            "<p>This demo is built using Ultralytics Explorer API. Visit <a href='https://docs.ultralytics.com/datasets/explorer/'>API docs</a> to try examples & learn more</p>",
-            unsafe_allow_html=True,
-            help=None,
-        )
-        st.link_button("Ultrlaytics Explorer API", "https://docs.ultralytics.com/datasets/explorer/")
-
-
-def layout(data=None, model=None):
-    """Resets explorer session variables and provides documentation with a link to API docs."""
-    st.set_page_config(layout="wide", initial_sidebar_state="collapsed")
-    st.markdown("<h1 style='text-align: center;'>Ultralytics Explorer Demo</h1>", unsafe_allow_html=True)
-
-    if st.session_state.get("explorer") is None:
-        init_explorer_form(data, model)
-        return
-
-    st.button(":arrow_backward: Select Dataset", on_click=reset_explorer)
-    exp = st.session_state.get("explorer")
-    col1, col2 = st.columns([0.75, 0.25], gap="small")
-    imgs = []
-    if st.session_state.get("error"):
-        st.error(st.session_state["error"])
-    elif st.session_state.get("imgs"):
-        imgs = st.session_state.get("imgs")
-    else:
-        imgs = exp.table.to_lance().to_table(columns=["im_file"]).to_pydict()["im_file"]
-        st.session_state["res"] = exp.table.to_arrow()
-    total_imgs, selected_imgs = len(imgs), []
-    with col1:
-        subcol1, subcol2, subcol3, subcol4, subcol5 = st.columns(5)
-        with subcol1:
-            st.write("Max Images Displayed:")
-        with subcol2:
-            num = st.number_input(
-                "Max Images Displayed",
-                min_value=0,
-                max_value=total_imgs,
-                value=min(500, total_imgs),
-                key="num_imgs_displayed",
-                label_visibility="collapsed",
-            )
-        with subcol3:
-            st.write("Start Index:")
-        with subcol4:
-            start_idx = st.number_input(
-                "Start Index",
-                min_value=0,
-                max_value=total_imgs,
-                value=0,
-                key="start_index",
-                label_visibility="collapsed",
-            )
-        with subcol5:
-            reset = st.button("Reset", use_container_width=False, key="reset")
-            if reset:
-                st.session_state["imgs"] = None
-                st.experimental_rerun()
-
-        query_form()
-        ai_query_form()
-        if total_imgs:
-            labels, boxes, masks, kpts, classes = None, None, None, None, None
-            task = exp.model.task
-            if st.session_state.get("display_labels"):
-                labels = st.session_state.get("res").to_pydict()["labels"][start_idx : start_idx + num]
-                boxes = st.session_state.get("res").to_pydict()["bboxes"][start_idx : start_idx + num]
-                masks = st.session_state.get("res").to_pydict()["masks"][start_idx : start_idx + num]
-                kpts = st.session_state.get("res").to_pydict()["keypoints"][start_idx : start_idx + num]
-                classes = st.session_state.get("res").to_pydict()["cls"][start_idx : start_idx + num]
-            imgs_displayed = imgs[start_idx : start_idx + num]
-            selected_imgs = image_select(
-                f"Total samples: {total_imgs}",
-                images=imgs_displayed,
-                use_container_width=False,
-                # indices=[i for i in range(num)] if select_all else None,
-                labels=labels,
-                classes=classes,
-                bboxes=boxes,
-                masks=masks if task == "segment" else None,
-                kpts=kpts if task == "pose" else None,
-            )
-
-    with col2:
-        similarity_form(selected_imgs)
-        st.checkbox("Labels", value=False, key="display_labels")
-        utralytics_explorer_docs_callback()
-
-
-if __name__ == "__main__":
-    kwargs = dict(zip(sys.argv[1::2], sys.argv[2::2]))
-    layout(**kwargs)

ultralytics/data/explorer/utils.py

@@ -1,167 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-
-import getpass
-from typing import List
-
-import cv2
-import numpy as np
-
-from ultralytics.data.augment import LetterBox
-from ultralytics.utils import LOGGER as logger
-from ultralytics.utils import SETTINGS
-from ultralytics.utils.checks import check_requirements
-from ultralytics.utils.ops import xyxy2xywh
-from ultralytics.utils.plotting import plot_images
-
-
-def get_table_schema(vector_size):
-    """Extracts and returns the schema of a database table."""
-    from lancedb.pydantic import LanceModel, Vector
-
-    class Schema(LanceModel):
-        im_file: str
-        labels: List[str]
-        cls: List[int]
-        bboxes: List[List[float]]
-        masks: List[List[List[int]]]
-        keypoints: List[List[List[float]]]
-        vector: Vector(vector_size)
-
-    return Schema
-
-
-def get_sim_index_schema():
-    """Returns a LanceModel schema for a database table with specified vector size."""
-    from lancedb.pydantic import LanceModel
-
-    class Schema(LanceModel):
-        idx: int
-        im_file: str
-        count: int
-        sim_im_files: List[str]
-
-    return Schema
-
-
-def sanitize_batch(batch, dataset_info):
-    """Sanitizes input batch for inference, ensuring correct format and dimensions."""
-    batch["cls"] = batch["cls"].flatten().int().tolist()
-    box_cls_pair = sorted(zip(batch["bboxes"].tolist(), batch["cls"]), key=lambda x: x[1])
-    batch["bboxes"] = [box for box, _ in box_cls_pair]
-    batch["cls"] = [cls for _, cls in box_cls_pair]
-    batch["labels"] = [dataset_info["names"][i] for i in batch["cls"]]
-    batch["masks"] = batch["masks"].tolist() if "masks" in batch else [[[]]]
-    batch["keypoints"] = batch["keypoints"].tolist() if "keypoints" in batch else [[[]]]
-    return batch
-
-
-def plot_query_result(similar_set, plot_labels=True):
-    """
-    Plot images from the similar set.
-
-    Args:
-        similar_set (list): Pyarrow or pandas object containing the similar data points
-        plot_labels (bool): Whether to plot labels or not
-    """
-    import pandas  # scope for faster 'import ultralytics'
-
-    similar_set = (
-        similar_set.to_dict(orient="list") if isinstance(similar_set, pandas.DataFrame) else similar_set.to_pydict()
-    )
-    empty_masks = [[[]]]
-    empty_boxes = [[]]
-    images = similar_set.get("im_file", [])
-    bboxes = similar_set.get("bboxes", []) if similar_set.get("bboxes") is not empty_boxes else []
-    masks = similar_set.get("masks") if similar_set.get("masks")[0] != empty_masks else []
-    kpts = similar_set.get("keypoints") if similar_set.get("keypoints")[0] != empty_masks else []
-    cls = similar_set.get("cls", [])
-
-    plot_size = 640
-    imgs, batch_idx, plot_boxes, plot_masks, plot_kpts = [], [], [], [], []
-    for i, imf in enumerate(images):
-        im = cv2.imread(imf)
-        im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
-        h, w = im.shape[:2]
-        r = min(plot_size / h, plot_size / w)
-        imgs.append(LetterBox(plot_size, center=False)(image=im).transpose(2, 0, 1))
-        if plot_labels:
-            if len(bboxes) > i and len(bboxes[i]) > 0:
-                box = np.array(bboxes[i], dtype=np.float32)
-                box[:, [0, 2]] *= r
-                box[:, [1, 3]] *= r
-                plot_boxes.append(box)
-            if len(masks) > i and len(masks[i]) > 0:
-                mask = np.array(masks[i], dtype=np.uint8)[0]
-                plot_masks.append(LetterBox(plot_size, center=False)(image=mask))
-            if len(kpts) > i and kpts[i] is not None:
-                kpt = np.array(kpts[i], dtype=np.float32)
-                kpt[:, :, :2] *= r
-                plot_kpts.append(kpt)
-        batch_idx.append(np.ones(len(np.array(bboxes[i], dtype=np.float32))) * i)
-    imgs = np.stack(imgs, axis=0)
-    masks = np.stack(plot_masks, axis=0) if plot_masks else np.zeros(0, dtype=np.uint8)
-    kpts = np.concatenate(plot_kpts, axis=0) if plot_kpts else np.zeros((0, 51), dtype=np.float32)
-    boxes = xyxy2xywh(np.concatenate(plot_boxes, axis=0)) if plot_boxes else np.zeros(0, dtype=np.float32)
-    batch_idx = np.concatenate(batch_idx, axis=0)
-    cls = np.concatenate([np.array(c, dtype=np.int32) for c in cls], axis=0)
-
-    return plot_images(
-        imgs, batch_idx, cls, bboxes=boxes, masks=masks, kpts=kpts, max_subplots=len(images), save=False, threaded=False
-    )
-
-
-def prompt_sql_query(query):
-    """Plots images with optional labels from a similar data set."""
-    check_requirements("openai>=1.6.1")
-    from openai import OpenAI
-
-    if not SETTINGS["openai_api_key"]:
-        logger.warning("OpenAI API key not found in settings. Please enter your API key below.")
-        openai_api_key = getpass.getpass("OpenAI API key: ")
-        SETTINGS.update({"openai_api_key": openai_api_key})
-    openai = OpenAI(api_key=SETTINGS["openai_api_key"])
-
-    messages = [
-        {
-            "role": "system",
-            "content": """
-                You are a helpful data scientist proficient in SQL. You need to output exactly one SQL query based on
-                the following schema and a user request. You only need to output the format with fixed selection
-                statement that selects everything from "'table'", like `SELECT * from 'table'`
-
-                Schema:
-                im_file: string not null
-                labels: list<item: string> not null
-                child 0, item: string
-                cls: list<item: int64> not null
-                child 0, item: int64
-                bboxes: list<item: list<item: double>> not null
-                child 0, item: list<item: double>
-                    child 0, item: double
-                masks: list<item: list<item: list<item: int64>>> not null
-                child 0, item: list<item: list<item: int64>>
-                    child 0, item: list<item: int64>
-                        child 0, item: int64
-                keypoints: list<item: list<item: list<item: double>>> not null
-                child 0, item: list<item: list<item: double>>
-                    child 0, item: list<item: double>
-                        child 0, item: double
-                vector: fixed_size_list<item: float>[256] not null
-                child 0, item: float
-
-                Some details about the schema:
-                - the "labels" column contains the string values like 'person' and 'dog' for the respective objects
-                    in each image
-                - the "cls" column contains the integer values on these classes that map them the labels
-
-                Example of a correct query:
-                request - Get all data points that contain 2 or more people and at least one dog
-                correct query-
-                SELECT * FROM 'table' WHERE  ARRAY_LENGTH(cls) >= 2  AND ARRAY_LENGTH(FILTER(labels, x -> x = 'person')) >= 2  AND ARRAY_LENGTH(FILTER(labels, x -> x = 'dog')) >= 1;
-             """,
-        },
-        {"role": "user", "content": f"{query}"},
-    ]
-
-    response = openai.chat.completions.create(model="gpt-3.5-turbo", messages=messages)
-    return response.choices[0].message.content