lib/core/general.py

import glob
import logging
import os
import platform
import random
import re
import shutil
import subprocess
import time
import torchvision
from contextlib import contextmanager
from copy import copy
from pathlib import Path

import cv2
import math
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import torch
import torch.nn as nn
import yaml
from PIL import Image
from scipy.cluster.vq import kmeans
from scipy.signal import butter, filtfilt
from tqdm import tqdm


def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-9):
    # Returns the IoU of box1 to box2. box1 is 4, box2 is nx4
    box2 = box2.T

    # Get the coordinates of bounding boxes
    if x1y1x2y2:  # x1, y1, x2, y2 = box1
        b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
        b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
    else:  # transform from xywh to xyxy
        b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2
        b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2
        b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2
        b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2

    # Intersection area
    inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
            (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)

    # Union Area
    w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
    w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
    union = w1 * h1 + w2 * h2 - inter + eps

    iou = inter / union
    if GIoU or DIoU or CIoU:
        cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1)  # convex (smallest enclosing box) width
        ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1)  # convex height
        if CIoU or DIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
            c2 = cw ** 2 + ch ** 2 + eps  # convex diagonal squared
            rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 +
                    (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4  # center distance squared
            if DIoU:
                return iou - rho2 / c2  # DIoU
            elif CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
                v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)
                with torch.no_grad():
                    alpha = v / ((1 + eps) - iou + v)
                return iou - (rho2 / c2 + v * alpha)  # CIoU
        else:  # GIoU https://arxiv.org/pdf/1902.09630.pdf
            c_area = cw * ch + eps  # convex area
            return iou - (c_area - union) / c_area  # GIoU
    else:
        return iou  # IoU


def box_iou(box1, box2):
    # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
    """
    Return intersection-over-union (Jaccard index) of boxes.
    Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
    Arguments:
        box1 (Tensor[N, 4])
        box2 (Tensor[M, 4])
    Returns:
        iou (Tensor[N, M]): the NxM matrix containing the pairwise
            IoU values for every element in boxes1 and boxes2
    """

    def box_area(box):
        # box = 4xn
        return (box[2] - box[0]) * (box[3] - box[1]) #(x2-x1)*(y2-y1)

    area1 = box_area(box1.T)
    area2 = box_area(box2.T)

    # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
    inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
    return inter / (area1[:, None] + area2 - inter)  # iou = inter / (area1 + area2 - inter)

def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, labels=()):
    """Performs Non-Maximum Suppression (NMS) on inference results
    Returns:
         detections with shape: nx6 (x1, y1, x2, y2, conf, cls)
    """

    nc = prediction.shape[2] - 5  # number of classes
    xc = prediction[..., 4] > conf_thres  # candidates

    # Settings
    min_wh, max_wh = 2, 4096  # (pixels) minimum and maximum box width and height
    max_det = 300  # maximum number of detections per image
    max_nms = 30000  # maximum number of boxes into torchvision.ops.nms()
    time_limit = 10.0  # seconds to quit after
    redundant = True  # require redundant detections
    multi_label = nc > 1  # multiple labels per box (adds 0.5ms/img)
    merge = False  # use merge-NMS

    t = time.time()
    output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
    for xi, x in enumerate(prediction):  # image index, image inference
        # Apply constraints
        # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0  # width-height
        x = x[xc[xi]]  # confidence

        # Cat apriori labels if autolabelling
        if labels and len(labels[xi]):
            l = labels[xi]
            v = torch.zeros((len(l), nc + 5), device=x.device)
            v[:, :4] = l[:, 1:5]  # box
            v[:, 4] = 1.0  # conf
            v[range(len(l)), l[:, 0].long() + 5] = 1.0  # cls
            x = torch.cat((x, v), 0)

        # If none remain process next image
        if not x.shape[0]:
            continue

        # Compute conf
        x[:, 5:] *= x[:, 4:5]  # conf = obj_conf * cls_conf

        # Box (center x, center y, width, height) to (x1, y1, x2, y2)
        box = xywh2xyxy(x[:, :4])

        # Detections matrix nx6 (xyxy, conf, cls)
        if multi_label:
            i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
            x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
        else:  # best class only
            conf, j = x[:, 5:].max(1, keepdim=True)
            x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]

        # Filter by class
        if classes is not None:
            x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]

        # Apply finite constraint
        # if not torch.isfinite(x).all():
        #     x = x[torch.isfinite(x).all(1)]

        # Check shape
        n = x.shape[0]  # number of boxes
        if not n:  # no boxes
            continue
        elif n > max_nms:  # excess boxes
            x = x[x[:, 4].argsort(descending=True)[:max_nms]]  # sort by confidence

        # Batched NMS
        c = x[:, 5:6] * (0 if agnostic else max_wh)  # classes
        boxes, scores = x[:, :4] + c, x[:, 4]  # boxes (offset by class), scores
        i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
        if i.shape[0] > max_det:  # limit detections
            i = i[:max_det]
        if merge and (1 < n < 3E3):  # Merge NMS (boxes merged using weighted mean)
            # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
            iou = box_iou(boxes[i], boxes) > iou_thres  # iou matrix
            weights = iou * scores[None]  # box weights
            x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True)  # merged boxes
            if redundant:
                i = i[iou.sum(1) > 1]  # require redundancy

        output[xi] = x[i]
        if (time.time() - t) > time_limit:
            print(f'WARNING: NMS time limit {time_limit}s exceeded')
            break  # time limit exceeded

    return output


def xywh2xyxy(x):
    # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
    y = torch.zeros_like(x) if isinstance(x, torch.Tensor) else np.zeros_like(x)
    y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
    y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
    y[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right x
    y[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right y
    return y
    
def fitness(x):
    # Returns fitness (for use with results.txt or evolve.txt)
    w = [0.0, 0.0, 0.1, 0.9]  # weights for [P, R, [email protected], [email protected]:0.95]
    return (x[:, :4] * w).sum(1)

def check_img_size(img_size, s=32):
    # Verify img_size is a multiple of stride s
    new_size = make_divisible(img_size, int(s))  # ceil gs-multiple
    if new_size != img_size:
        print('WARNING: --img-size %g must be multiple of max stride %g, updating to %g' % (img_size, s, new_size))
    return new_size

def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
    # Rescale coords (xyxy) from img1_shape to img0_shape
    if ratio_pad is None:  # calculate from img0_shape
        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
        pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
    else:
        gain = ratio_pad[0][0]
        pad = ratio_pad[1]

    coords[:, [0, 2]] -= pad[0]  # x padding
    coords[:, [1, 3]] -= pad[1]  # y padding
    coords[:, :4] /= gain
    clip_coords(coords, img0_shape)
    return coords

def clip_coords(boxes, img_shape):
    # Clip bounding xyxy bounding boxes to image shape (height, width)
    boxes[:, 0].clamp_(0, img_shape[1])  # x1
    boxes[:, 1].clamp_(0, img_shape[0])  # y1
    boxes[:, 2].clamp_(0, img_shape[1])  # x2
    boxes[:, 3].clamp_(0, img_shape[0])  # y2

def make_divisible(x, divisor):
    # Returns x evenly divisible by divisor
    return math.ceil(x / divisor) * divisor

def xyxy2xywh(x):
    # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
    y = torch.zeros_like(x) if isinstance(x, torch.Tensor) else np.zeros_like(x)
    y[:, 0] = (x[:, 0] + x[:, 2]) / 2  # x center
    y[:, 1] = (x[:, 1] + x[:, 3]) / 2  # y center
    y[:, 2] = x[:, 2] - x[:, 0]  # width
    y[:, 3] = x[:, 3] - x[:, 1]  # height
    return y

def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max_size=640, max_subplots=16):
    # Plot image grid with labels

    if isinstance(images, torch.Tensor):
        images = images.cpu().float().numpy()
    if isinstance(targets, torch.Tensor):
        targets = targets.cpu().numpy()

    # un-normalise
    if np.max(images[0]) <= 1:
        images *= 255

    tl = 3  # line thickness
    tf = max(tl - 1, 1)  # font thickness
    bs, _, h, w = images.shape  # batch size, _, height, width
    bs = min(bs, max_subplots)  # limit plot images
    ns = np.ceil(bs ** 0.5)  # number of subplots (square)

    # Check if we should resize
    scale_factor = max_size / max(h, w)
    if scale_factor < 1:
        h = math.ceil(scale_factor * h)
        w = math.ceil(scale_factor * w)

    colors = color_list()  # list of colors
    mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8)  # init
    for i, img in enumerate(images):
        if i == max_subplots:  # if last batch has fewer images than we expect
            break

        block_x = int(w * (i // ns))
        block_y = int(h * (i % ns))

        img = img.transpose(1, 2, 0)
        if scale_factor < 1:
            img = cv2.resize(img, (w, h))

        mosaic[block_y:block_y + h, block_x:block_x + w, :] = img
        if len(targets) > 0:
            image_targets = targets[targets[:, 0] == i]
            boxes = xywh2xyxy(image_targets[:, 2:6]).T
            classes = image_targets[:, 1].astype('int')
            labels = image_targets.shape[1] == 6  # labels if no conf column
            conf = None if labels else image_targets[:, 6]  # check for confidence presence (label vs pred)

            if boxes.shape[1]:
                if boxes.max() <= 1.01:  # if normalized with tolerance 0.01
                    boxes[[0, 2]] *= w  # scale to pixels
                    boxes[[1, 3]] *= h
                elif scale_factor < 1:  # absolute coords need scale if image scales
                    boxes *= scale_factor
            boxes[[0, 2]] += block_x
            boxes[[1, 3]] += block_y
            for j, box in enumerate(boxes.T):
                cls = int(classes[j])
                color = colors[cls % len(colors)]
                cls = names[cls] if names else cls
                if labels or conf[j] > 0.25:  # 0.25 conf thresh
                    label = '%s' % cls if labels else '%s %.1f' % (cls, conf[j])
                    plot_one_box(box, mosaic, label=label, color=color, line_thickness=tl)

        # Draw image filename labels
        if paths:
            label = Path(paths[i]).name[:40]  # trim to 40 char
            t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
            cv2.putText(mosaic, label, (block_x + 5, block_y + t_size[1] + 5), 0, tl / 3, [220, 220, 220], thickness=tf,
                        lineType=cv2.LINE_AA)

        # Image border
        cv2.rectangle(mosaic, (block_x, block_y), (block_x + w, block_y + h), (255, 255, 255), thickness=3)

    if fname:
        r = min(1280. / max(h, w) / ns, 1.0)  # ratio to limit image size
        mosaic = cv2.resize(mosaic, (int(ns * w * r), int(ns * h * r)), interpolation=cv2.INTER_AREA)
        # cv2.imwrite(fname, cv2.cvtColor(mosaic, cv2.COLOR_BGR2RGB))  # cv2 save
        Image.fromarray(mosaic).save(fname)  # PIL save
    return mosaic

def plot_one_box(x, img, color=None, label=None, line_thickness=None):
    # Plots one bounding box on image img
    tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1  # line/font thickness
    color = color or [random.randint(0, 255) for _ in range(3)]
    c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
    cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
    if label:
        tf = max(tl - 1, 1)  # font thickness
        t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
        c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
        cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA)  # filled
        cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)

def color_list():
    # Return first 10 plt colors as (r,g,b) https://stackoverflow.com/questions/51350872/python-from-color-name-to-rgb
    def hex2rgb(h):
        return tuple(int(str(h[1 + i:1 + i + 2]), 16) for i in (0, 2, 4))

    return [hex2rgb(h) for h in plt.rcParams['axes.prop_cycle'].by_key()['color']]

def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='precision-recall_curve.png', names=[]):
    """ Compute the average precision, given the recall and precision curves.
    Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
    # Arguments
        tp:  True positives (nparray, nx1 or nx10).
        conf:  Objectness value from 0-1 (nparray).
        pred_cls:  Predicted object classes (nparray).
        target_cls:  True object classes (nparray).
        plot:  Plot precision-recall curve at [email protected]
        save_dir:  Plot save directory
    # Returns
        The average precision as computed in py-faster-rcnn.
    """

    # Sort by objectness
    i = np.argsort(-conf)
    tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]

    # Find unique classes
    unique_classes = np.unique(target_cls)

    # Create Precision-Recall curve and compute AP for each class
    px, py = np.linspace(0, 1, 1000), []  # for plotting
    pr_score = 0.1  # score to evaluate P and R https://github.com/ultralytics/yolov3/issues/898
    s = [unique_classes.shape[0], tp.shape[1]]  # number class, number iou thresholds (i.e. 10 for mAP0.5...0.95)
    ap, p, r = np.zeros(s), np.zeros((unique_classes.shape[0], 1000)), np.zeros((unique_classes.shape[0], 1000))
    for ci, c in enumerate(unique_classes):
        i = pred_cls == c
        n_l = (target_cls == c).sum()  # number of labels
        n_p = i.sum()  # number of predictions

        if n_p == 0 or n_l == 0:
            continue
        else:
            # Accumulate FPs and TPs
            fpc = (1 - tp[i]).cumsum(0)
            tpc = tp[i].cumsum(0)

            # Recall
            recall = tpc / (n_l + 1e-16)  # recall curve
            r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0)  # negative x, xp because xp decreases

            # Precision
            precision = tpc / (tpc + fpc)  # precision curve
            p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1)  # p at pr_score
            # AP from recall-precision curve
            for j in range(tp.shape[1]):
                ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j])
                if plot and (j == 0):
                    py.append(np.interp(px, mrec, mpre))  # precision at [email protected]

    # Compute F1 score (harmonic mean of precision and recall)
    f1 = 2 * p * r / (p + r + 1e-16)
    i=r.mean(0).argmax()

    if plot:
        plot_pr_curve(px, py, ap, save_dir, names)

    return p[:, i], r[:, i], ap, f1[:, i], unique_classes.astype('int32')

def compute_ap(recall, precision):
    """ Compute the average precision, given the recall and precision curves.
    Source: https://github.com/rbgirshick/py-faster-rcnn.
    # Arguments
        recall:    The recall curve (list).
        precision: The precision curve (list).
    # Returns
        The average precision as computed in py-faster-rcnn.
    """

    # Append sentinel values to beginning and end
    mrec = np.concatenate(([0.], recall, [recall[-1] + 1E-3]))
    mpre = np.concatenate(([1.], precision, [0.]))

    # Compute the precision envelope
    mpre = np.flip(np.maximum.accumulate(np.flip(mpre)))

    # Integrate area under curve
    method = 'interp'  # methods: 'continuous', 'interp'
    if method == 'interp':
        x = np.linspace(0, 1, 101)  # 101-point interp (COCO)
        ap = np.trapz(np.interp(x, mrec, mpre), x)  # integrate

    else:  # 'continuous'
        i = np.where(mrec[1:] != mrec[:-1])[0]  # points where x axis (recall) changes
        ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])  # area under curve

    return ap, mpre, mrec

def coco80_to_coco91_class():  # converts 80-index (val2014) to 91-index (paper)
    # https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/
    # a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
    # b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
    # x1 = [list(a[i] == b).index(True) + 1 for i in range(80)]  # darknet to coco
    # x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)]  # coco to darknet
    x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
         35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
         64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]
    return x

def output_to_target(output):
    # Convert model output to target format [batch_id, class_id, x, y, w, h, conf]
    targets = []
    for i, o in enumerate(output):
        for *box, conf, cls in o.cpu().numpy():
            targets.append([i, cls, *list(*xyxy2xywh(np.array(box)[None])), conf])
    return np.array(targets)

def plot_pr_curve(px, py, ap, save_dir='.', names=()):
    fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
    py = np.stack(py, axis=1)

    if 0 < len(names) < 21:  # show mAP in legend if < 10 classes
        for i, y in enumerate(py.T):
            ax.plot(px, y, linewidth=1, label=f'{names[i]} %.3f' % ap[i, 0])  # plot(recall, precision)
    else:
        ax.plot(px, py, linewidth=1, color='grey')  # plot(recall, precision)

    ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f [email protected]' % ap[:, 0].mean())
    ax.set_xlabel('Recall')
    ax.set_ylabel('Precision')
    ax.set_xlim(0, 1)
    ax.set_ylim(0, 1)
    plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
    fig.savefig(Path(save_dir) / 'precision_recall_curve.png', dpi=250)