Upload 8 files

README.md

@@ -1,12 +1,21 @@
----
-title: Face Mask Detection
-emoji: 🐨
-colorFrom: green
-colorTo: gray
-sdk: streamlit
-sdk_version: 1.28.2
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<!-- Title -->
+<h1 align="center"><b>Newspaper Crawling with Scrapy</b></h1>
+
+## Set up environment
+
+```
+conda env create -f environment.yml
+conda activate demo-mm-st
+```
+
+## Streamlit demo
+
+To run streamlit demo, you need to download weights files [Faster-RCNN](https://github.com/laichithien/FaceMaskDetection_StreamlitDemo/releases/download/FaceMaskDetModels/fasterrcnn.pth), [YOLOv3](https://github.com/laichithien/FaceMaskDetection_StreamlitDemo/releases/download/FaceMaskDetModels/yolov3.pth) and place them in `models` folder
+After that, simply run command below
+```
+streamlit run demo.py
+```
+## Demo interface
+![](demo_page-0001.jpg)
+
+

app.py

@@ -0,0 +1,278 @@
+import streamlit as st
+import cv2
+import numpy as np
+import requests
+from mmdet.apis import init_detector, inference_detector
+import mmcv
+import torch
+from mmdet.utils.contextmanagers import concurrent
+from pprint import pprint
+from PIL import Image
+import datetime
+
+def IoU(bbox1, bbox2):
+
+    x1_left = bbox1[0]
+    y1_top = bbox1[1]
+    x1_right = bbox1[2]
+    y1_bot = bbox1[3]
+
+    x2_left = bbox2[0]
+    y2_top = bbox2[1]
+    x2_right = bbox2[2]
+    y2_bot = bbox2[3]
+
+    x_left = max(x1_left, x2_left)
+    x_right = min(x1_right, x2_right)
+    y_top = max(y1_top, y2_top)
+    y_bot = min(y1_bot, y2_bot)
+
+    inter = (x_right - x_left) * (y_bot - y_top)
+    if x_right < x_left or y_bot < y_top:
+        return 0.0
+    area1 = (x1_right - x1_left) * (y1_bot - y1_top)
+    area2 = (x2_right - x2_left) * (y2_bot - y2_top)
+    union = area1 + area2 - inter
+
+    IoU = inter / union
+    return IoU
+
+def file():
+    inputimg = st.file_uploader("Upload your image")
+    if inputimg is not None:
+        inputimg = Image.open(inputimg)
+        inputimg = np.array(inputimg)
+        inputimg = cv2.cvtColor(inputimg, cv2.COLOR_BGR2RGB)
+        cv2.imwrite('demo_file.jpg', inputimg)
+        return inputimg
+
+def webcam():
+    inputimg = st.camera_input("Take a picture")
+    if inputimg is not None:
+        inputimg = Image.open(inputimg)
+        inputimg = np.array(inputimg)
+        inputimg = cv2.cvtColor(inputimg, cv2.COLOR_BGR2RGB)
+        cv2.imwrite('demo_webcam.jpg', inputimg)
+        return inputimg
+
+def phonecam():
+    if st.button("Take picture"):
+        url = 'http://192.168.114.78:8080//photo.jpg'
+        img_resp = requests.get(url)
+        img_arr = np.array(bytearray(img_resp.content), dtype=np.uint8)
+        inputimg = cv2.imdecode(img_arr, -1)
+        cv2.imwrite('demo_phonecam.jpg', inputimg)
+        return inputimg
+    
+
+def detect(inputimg, model):
+    
+    if model == 'f':
+        config_file = './configs/fasterrcnn.py'
+        checkpoint_file = './models/fasterrcnn.pth'
+    # Specify the path to model config and checkpoint file
+    else: 
+        config_file = './configs/yolov3.py'
+        checkpoint_file = './models/yolov3.pth'
+
+    # build the model from a config file and a checkpoint file
+    model = init_detector(config_file, checkpoint_file, device='cuda:0')
+    if (inputimg == 'Webcam'):
+        img = 'demo_webcam.jpg'  # or img = mmcv.imread(img), which will only load it once
+    elif (inputimg == 'File'):
+        img = 'demo_file.jpg'
+    elif (inputimg == 'Phone'):
+        img = 'demo_phonecam.jpg'
+    start = datetime.datetime.now()    
+    result = inference_detector(model, img)
+    end = datetime.datetime.now()
+
+    time = end - start
+
+    time_mcs = time.microseconds
+
+    total_people = 0
+    incorrect = 0
+    withmask = 0
+    withoutmask = 0
+
+    list_objects = []
+    isRemove = []
+    for i in result[1]:
+        temp = i
+        temp = np.append(temp, 1)
+        list_objects.append(temp)
+        isRemove.append(0)
+
+    for i in result[2]:
+        temp = i 
+        temp = np.append(temp, 2)
+        list_objects.append(temp)
+        isRemove.append(0)
+
+    for i in result[3]:
+        temp = i
+        temp = np.append(temp, 3)
+        list_objects.append(temp)
+        isRemove.append(0)
+
+    for i in range(len(list_objects) - 1):
+        for j in range(i + 1, len(list_objects)):
+            bbox1 = [list_objects[i][0], list_objects[i][1], list_objects[i][2], list_objects[i][3]]
+            bbox2 = [list_objects[j][0], list_objects[j][1], list_objects[j][2], list_objects[j][3]]
+            if abs(IoU(bbox1, bbox2)) > 0.7:
+                if list_objects[i][4] > list_objects[j][4]:
+                    isRemove[j] = 1
+                else:
+                    isRemove[i] = 1
+                # print("IoU", abs(IoU(bbox1, bbox2)))
+            
+
+            if list_objects[i][4] < 0.4:
+                isRemove[i] = 1
+            if list_objects[j][4] < 0.4:
+                isRemove[j] = 1
+
+    selected_list = []
+    for i in range(len(list_objects)):
+        if isRemove[i] == 0:
+            selected_list.append(list_objects[i])
+
+    for i in selected_list:
+        if i[5] == 1:
+            incorrect += 1
+        elif i[5] == 2:
+            withmask += 1
+        elif i[5] ==3:
+            withoutmask += 1
+        
+    total_people += incorrect + withmask + withoutmask
+
+
+    img = cv2.imread(img)
+    for i in selected_list:
+        if i[5] == 1:
+            color = (255, 0, 0)
+            text  = "Mask weared incorrect"
+        elif i[5] == 2:
+            color = (0, 255, 0)
+            text  = "With mask"
+        elif i[5] == 3:
+            color = (0, 0, 255)
+            text = "Without mask"
+        text += ": " + str(round(i[4], 2))
+        x1 = i[0]
+        y1 = i[1]
+        x2 = i[2] - 1
+        y2 = i[3] - 1
+
+        x1 = round(x1)
+        y1 = round(y1)
+        x2 = round(x2)
+        y2 = round(y2)
+
+        img = cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
+        img = cv2.putText(img, text, (x1, y1-10), cv2.FONT_HERSHEY_SIMPLEX, 0.7, color, 2)
+    output ="result_demo.jpg"
+    return img, total_people, incorrect, withmask, withoutmask, time_mcs/1000
+
+st.title("Demo đồ án môn học CS331 - Thị giác máy tính nâng cao")
+
+st.write("Lại Chí Thiện - 20520309")
+st.write("Lê Thị Phương Vy - 20520355")
+
+file_page, webcam_page, phonecam_page = st.tabs(["File", "Webcam", "Phone's camera"])
+
+with file_page:
+    inputimg_file = file()
+    if inputimg_file is not None:
+        st.image(cv2.cvtColor(inputimg_file, cv2.COLOR_BGR2RGB))
+        frcnn, yolov3 = st.columns(2)
+        with frcnn:
+            result_rcnn, total, inc, withm, withoutm, time = detect('File', 'f')
+            st.image(cv2.cvtColor(result_rcnn, cv2.COLOR_BGR2RGB))
+            st.write("Faster R-CNN")
+            st.write("Tổng số người có trong bức ảnh: ", total)
+            st.write("Tổng số người không đeo khẩu trang: ", withoutm)
+            st.write("Tổng số người đeo khẩu trang sai cách: ", inc)
+            st.write("Tổng số người đeo khẩu trang: ", withm)
+            st.write("Tỉ lệ số người không đeo khẩu trang: ", round(withoutm/total, 2))
+            st.write("Tỉ lệ số người đeo khẩu trang sai cách: ", round(inc/total, 2))
+            st.write("Tỉ lệ số người đeo khẩu trang: ", round(withm/total, 2))
+            st.write("Thời gian thực thi (miliseconds): ", time)
+        with yolov3:
+            result_yolov3, total, inc, withm, withoutm, time = detect('File', 'y')
+            st.image(cv2.cvtColor(result_yolov3, cv2.COLOR_BGR2RGB))
+            st.write("YOLOv3")
+            st.write("Tổng số người có trong bức ảnh: ", total)
+            st.write("Tổng số người không đeo khẩu trang: ", withoutm)
+            st.write("Tổng số người đeo khẩu trang sai cách: ", inc)
+            st.write("Tổng số người đeo khẩu trang: ", withm)
+            st.write("Tỉ lệ số người không đeo khẩu trang: ", round(withoutm/total, 2))
+            st.write("Tỉ lệ số người đeo khẩu trang sai cách: ", round(inc/total, 2))
+            st.write("Tỉ lệ số người đeo khẩu trang: ", round(withm/total, 2))
+            st.write("Thời gian thực thi (miliseconds): ", time)
+
+with webcam_page:
+    inputimg_wc = webcam()
+    if inputimg_wc is not None:
+        st.image(cv2.cvtColor(inputimg_wc, cv2.COLOR_BGR2RGB))
+        frcnn, yolov3 = st.columns(2)
+        with frcnn:
+            result_rcnn, total, inc, withm, withoutm, time = detect('Webcam', 'f')
+            st.image(cv2.cvtColor(result_rcnn, cv2.COLOR_BGR2RGB))
+            st.write("Faster R-CNN")
+            st.write("Tổng số người có trong bức ảnh: ", total)
+            st.write("Tổng số người không đeo khẩu trang: ", withoutm)
+            st.write("Tổng số người đeo khẩu trang sai cách: ", inc)
+            st.write("Tổng số người đeo khẩu trang: ", withm)
+            st.write("Tỉ lệ số người không đeo khẩu trang: ", round(withoutm/total, 2))
+            st.write("Tỉ lệ số người đeo khẩu trang sai cách: ", round(inc/total, 2))
+            st.write("Tỉ lệ số người đeo khẩu trang: ", round(withm/total, 2))
+            st.write("Thời gian thực thi (miliseconds): ", time)
+        with yolov3:
+            result_yolov3, total, inc, withm, withoutm, time = detect('Webcam', 'y')
+            st.image(cv2.cvtColor(result_yolov3, cv2.COLOR_BGR2RGB))
+            st.write("YOLOv3")
+            st.write("Tổng số người có trong bức ảnh: ", total)
+            st.write("Tổng số người không đeo khẩu trang: ", withoutm)
+            st.write("Tổng số người đeo khẩu trang sai cách: ", inc)
+            st.write("Tổng số người đeo khẩu trang: ", withm)
+            st.write("Tỉ lệ số người không đeo khẩu trang: ", round(withoutm/total, 2))
+            st.write("Tỉ lệ số người đeo khẩu trang sai cách: ", round(inc/total, 2))
+            st.write("Tỉ lệ số người đeo khẩu trang: ", round(withm/total, 2))
+            st.write("Thời gian thực thi (miliseconds): ", time)
+
+with phonecam_page:
+    inputimg_pc = phonecam()
+    if inputimg_pc is not None:
+            st.image(cv2.cvtColor(inputimg_pc, cv2.COLOR_BGR2RGB))
+            frcnn, yolov3 = st.columns(2)
+            with frcnn:
+                result_rcnn, total, inc, withm, withoutm, time = detect('Phone', 'f')
+                st.image(cv2.cvtColor(result_rcnn, cv2.COLOR_BGR2RGB))
+                st.write("Faster R-CNN")
+                st.write("Tổng số người có trong bức ảnh: ", total)
+                st.write("Tổng số người không đeo khẩu trang: ", withoutm)
+                st.write("Tổng số người đeo khẩu trang sai cách: ", inc)
+                st.write("Tổng số người đeo khẩu trang: ", withm)
+                st.write("Tỉ lệ số người không đeo khẩu trang: ", round(withoutm/total, 2))
+                st.write("Tỉ lệ số người đeo khẩu trang sai cách: ", round(inc/total, 2))
+                st.write("Tỉ lệ số người đeo khẩu trang: ", round(withm/total, 2))
+                st.write("Thời gian thực thi (miliseconds): ", time)
+            with yolov3:
+                result_yolov3, total, inc, withm, withoutm, time = detect('Phone', 'y')
+                st.image(cv2.cvtColor(result_yolov3, cv2.COLOR_BGR2RGB))
+                st.write("YOLOv3")
+                st.write("Tổng số người có trong bức ảnh: ", total)
+                st.write("Tổng số người không đeo khẩu trang: ", withoutm)
+                st.write("Tổng số người đeo khẩu trang sai cách: ", inc)
+                st.write("Tổng số người đeo khẩu trang: ", withm)
+                st.write("Tỉ lệ số người không đeo khẩu trang: ", round(withoutm/total, 2))
+                st.write("Tỉ lệ số người đeo khẩu trang sai cách: ", round(inc/total, 2))
+                st.write("Tỉ lệ số người đeo khẩu trang: ", round(withm/total, 2))
+                st.write("Thời gian thực thi (miliseconds): ", time)
+
+
+
+

configs/fasterrcnn.py

@@ -0,0 +1,247 @@
+model = dict(
+    type='FasterRCNN',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5),
+    rpn_head=dict(
+        type='RPNHead',
+        in_channels=256,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            scales=[8],
+            ratios=[0.5, 1.0, 2.0],
+            strides=[4, 8, 16, 32, 64]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[0.0, 0.0, 0.0, 0.0],
+            target_stds=[1.0, 1.0, 1.0, 1.0]),
+        loss_cls=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
+    roi_head=dict(
+        type='StandardRoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor',
+            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
+            out_channels=256,
+            featmap_strides=[4, 8, 16, 32]),
+        bbox_head=dict(
+            type='Shared2FCBBoxHead',
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=4,
+            bbox_coder=dict(
+                type='DeltaXYWHBBoxCoder',
+                target_means=[0.0, 0.0, 0.0, 0.0],
+                target_stds=[0.1, 0.1, 0.2, 0.2]),
+            reg_class_agnostic=False,
+            loss_cls=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+            loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
+    train_cfg=dict(
+        rpn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.7,
+                neg_iou_thr=0.3,
+                min_pos_iou=0.3,
+                match_low_quality=True,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=256,
+                pos_fraction=0.5,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=False),
+            allowed_border=-1,
+            pos_weight=-1,
+            debug=False),
+        rpn_proposal=dict(
+            nms_pre=2000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssigner',
+                pos_iou_thr=0.5,
+                neg_iou_thr=0.5,
+                min_pos_iou=0.5,
+                match_low_quality=False,
+                ignore_iof_thr=-1),
+            sampler=dict(
+                type='RandomSampler',
+                num=512,
+                pos_fraction=0.25,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=-1,
+            debug=False)),
+    test_cfg=dict(
+        rpn=dict(
+            nms_pre=1000,
+            max_per_img=1000,
+            nms=dict(type='nms', iou_threshold=0.7),
+            min_bbox_size=0),
+        rcnn=dict(
+            score_thr=0.05,
+            nms=dict(type='nms', iou_threshold=0.5),
+            max_per_img=100)))
+classes = ['people', 'mask_weared_incorrect', 'with_mask', 'without_mask']
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        to_rgb=True),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1333, 800),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+data = dict(
+    samples_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type='CocoDataset',
+        ann_file=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/train/_annotations.coco.json',
+        img_prefix=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/train/',
+        classes=[
+            'people', 'mask_weared_incorrect', 'with_mask', 'without_mask'
+        ],
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
+            dict(type='RandomFlip', flip_ratio=0.5),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=32),
+            dict(type='DefaultFormatBundle'),
+            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+        ]),
+    val=dict(
+        type='CocoDataset',
+        ann_file=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/valid/_annotations.coco.json',
+        img_prefix=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/valid/',
+        classes=[
+            'people', 'mask_weared_incorrect', 'with_mask', 'without_mask'
+        ],
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1333, 800),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip'),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=32),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]),
+    test=dict(
+        type='CocoDataset',
+        ann_file=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/test/_annotations.coco.json',
+        img_prefix=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/test/',
+        classes=[
+            'people', 'mask_weared_incorrect', 'with_mask', 'without_mask'
+        ],
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1333, 800),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip'),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=32),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]))
+evaluation = dict(interval=1, metric='bbox')
+optimizer = dict(type='SGD', lr=0.005, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=None)
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=0.001,
+    step=[8, 11])
+runner = dict(type='EpochBasedRunner', max_epochs=24)
+checkpoint_config = dict(interval=1)
+log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
+custom_hooks = [dict(type='NumClassCheckHook')]
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = './workdirs/faster_rcnn_r50_fpn_1x/latest.pth'
+workflow = [('train', 1)]
+opencv_num_threads = 0
+mp_start_method = 'fork'
+auto_scale_lr = dict(enable=False, base_batch_size=16)
+work_dir = './workdirs/faster_rcnn_r50_fpn_1x'
+auto_resume = False
+gpu_ids = [0]

configs/yolov3.py

@@ -0,0 +1,210 @@
+checkpoint_config = dict(interval=50)
+log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
+custom_hooks = [dict(type='NumClassCheckHook')]
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = './workdirs/yolov3_d53_320_273e/latest.pth'
+workflow = [('train', 1)]
+opencv_num_threads = 0
+mp_start_method = 'fork'
+auto_scale_lr = dict(enable=False, base_batch_size=64)
+model = dict(
+    type='YOLOV3',
+    backbone=dict(
+        type='Darknet',
+        depth=53,
+        out_indices=(3, 4, 5),
+        init_cfg=dict(type='Pretrained', checkpoint='open-mmlab://darknet53')),
+    neck=dict(
+        type='YOLOV3Neck',
+        num_scales=3,
+        in_channels=[1024, 512, 256],
+        out_channels=[512, 256, 128]),
+    bbox_head=dict(
+        type='YOLOV3Head',
+        num_classes=4,
+        in_channels=[512, 256, 128],
+        out_channels=[1024, 512, 256],
+        anchor_generator=dict(
+            type='YOLOAnchorGenerator',
+            base_sizes=[[(116, 90), (156, 198), (373, 326)],
+                        [(30, 61), (62, 45), (59, 119)],
+                        [(10, 13), (16, 30), (33, 23)]],
+            strides=[32, 16, 8]),
+        bbox_coder=dict(type='YOLOBBoxCoder'),
+        featmap_strides=[32, 16, 8],
+        loss_cls=dict(
+            type='CrossEntropyLoss',
+            use_sigmoid=True,
+            loss_weight=1.0,
+            reduction='sum'),
+        loss_conf=dict(
+            type='CrossEntropyLoss',
+            use_sigmoid=True,
+            loss_weight=1.0,
+            reduction='sum'),
+        loss_xy=dict(
+            type='CrossEntropyLoss',
+            use_sigmoid=True,
+            loss_weight=2.0,
+            reduction='sum'),
+        loss_wh=dict(type='MSELoss', loss_weight=2.0, reduction='sum')),
+    train_cfg=dict(
+        assigner=dict(
+            type='GridAssigner',
+            pos_iou_thr=0.5,
+            neg_iou_thr=0.5,
+            min_pos_iou=0)),
+    test_cfg=dict(
+        nms_pre=1000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        conf_thr=0.005,
+        nms=dict(type='nms', iou_threshold=0.45),
+        max_per_img=100))
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(mean=[0, 0, 0], std=[255.0, 255.0, 255.0], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Expand', mean=[0, 0, 0], to_rgb=True, ratio_range=(1, 2)),
+    dict(
+        type='MinIoURandomCrop',
+        min_ious=(0.4, 0.5, 0.6, 0.7, 0.8, 0.9),
+        min_crop_size=0.3),
+    dict(type='Resize', img_scale=(416, 416), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(
+        type='Normalize',
+        mean=[0, 0, 0],
+        std=[255.0, 255.0, 255.0],
+        to_rgb=True),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(416, 416),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(
+                type='Normalize',
+                mean=[0, 0, 0],
+                std=[255.0, 255.0, 255.0],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+data = dict(
+    samples_per_gpu=8,
+    workers_per_gpu=8,
+    train=dict(
+        type='CocoDataset',
+        ann_file=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/train/_annotations.coco.json',
+        img_prefix=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/train/',
+        classes=[
+            'people', 'mask_weared_incorrect', 'with_mask', 'without_mask'
+        ],
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True),
+            dict(
+                type='Expand', mean=[0, 0, 0], to_rgb=True,
+                ratio_range=(1, 2)),
+            dict(
+                type='MinIoURandomCrop',
+                min_ious=(0.4, 0.5, 0.6, 0.7, 0.8, 0.9),
+                min_crop_size=0.3),
+            dict(type='Resize', img_scale=(416, 416), keep_ratio=True),
+            dict(type='RandomFlip', flip_ratio=0.5),
+            dict(type='PhotoMetricDistortion'),
+            dict(
+                type='Normalize',
+                mean=[0, 0, 0],
+                std=[255.0, 255.0, 255.0],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=32),
+            dict(type='DefaultFormatBundle'),
+            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+        ]),
+    val=dict(
+        type='CocoDataset',
+        ann_file=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/valid/_annotations.coco.json',
+        img_prefix=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/valid/',
+        classes=[
+            'people', 'mask_weared_incorrect', 'with_mask', 'without_mask'
+        ],
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(416, 416),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip'),
+                    dict(
+                        type='Normalize',
+                        mean=[0, 0, 0],
+                        std=[255.0, 255.0, 255.0],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=32),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]),
+    test=dict(
+        type='CocoDataset',
+        ann_file=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/test/_annotations.coco.json',
+        img_prefix=
+        '/content/drive/MyDrive/ComputerVisionPP/Data/mmdet/FaceMaskDetection-2/test/',
+        classes=[
+            'people', 'mask_weared_incorrect', 'with_mask', 'without_mask'
+        ],
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(416, 416),
+                flip=False,
+                transforms=[
+                    dict(type='Resize', keep_ratio=True),
+                    dict(type='RandomFlip'),
+                    dict(
+                        type='Normalize',
+                        mean=[0, 0, 0],
+                        std=[255.0, 255.0, 255.0],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=32),
+                    dict(type='ImageToTensor', keys=['img']),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ]))
+optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=2000,
+    warmup_ratio=0.1,
+    step=[218, 246])
+runner = dict(type='EpochBasedRunner', max_epochs=300)
+evaluation = dict(interval=1, metric=['bbox'])
+work_dir = './workdirs/yolov3_d53_320_273e'
+auto_resume = False
+gpu_ids = [0]

environment.yml

@@ -0,0 +1,227 @@
+name: demo-mm-st
+channels:
+  - pytorch
+  - nvidia
+  - defaults
+dependencies:
+  - altair=4.1.0=py_1
+  - arrow-cpp=8.0.0=py310h38b8b19_1
+  - asttokens=2.0.5=pyhd3eb1b0_0
+  - attrs=22.1.0=py310haa95532_0
+  - aws-c-common=0.4.57=ha925a31_1
+  - aws-c-event-stream=0.1.6=hd77b12b_5
+  - aws-checksums=0.1.9=ha925a31_0
+  - aws-sdk-cpp=1.8.185=hd77b12b_0
+  - backcall=0.2.0=pyhd3eb1b0_0
+  - blas=1.0=mkl
+  - blinker=1.4=py310haa95532_0
+  - boost-cpp=1.73.0=h2bbff1b_12
+  - bottleneck=1.3.5=py310h9128911_0
+  - brotlipy=0.7.0=py310h2bbff1b_1002
+  - bzip2=1.0.8=he774522_0
+  - c-ares=1.19.0=h2bbff1b_0
+  - ca-certificates=2023.01.10=haa95532_0
+  - cachetools=4.2.2=pyhd3eb1b0_0
+  - certifi=2022.12.7=py310haa95532_0
+  - cffi=1.15.1=py310h2bbff1b_3
+  - charset-normalizer=2.0.4=pyhd3eb1b0_0
+  - colorama=0.4.6=py310haa95532_0
+  - comm=0.1.2=py310haa95532_0
+  - commonmark=0.9.1=pyhd3eb1b0_0
+  - cryptography=39.0.1=py310h21b164f_0
+  - cuda-cccl=12.1.55=0
+  - cuda-cudart=11.8.89=0
+  - cuda-cudart-dev=11.8.89=0
+  - cuda-cupti=11.8.87=0
+  - cuda-libraries=11.8.0=0
+  - cuda-libraries-dev=11.8.0=0
+  - cuda-nvrtc=11.8.89=0
+  - cuda-nvrtc-dev=11.8.89=0
+  - cuda-nvtx=11.8.86=0
+  - cuda-profiler-api=12.1.55=0
+  - cuda-runtime=11.8.0=0
+  - dataclasses=0.8=pyh6d0b6a4_7
+  - debugpy=1.5.1=py310hd77b12b_0
+  - decorator=5.1.1=pyhd3eb1b0_0
+  - eigen=3.3.7=h59b6b97_1
+  - entrypoints=0.4=py310haa95532_0
+  - executing=0.8.3=pyhd3eb1b0_0
+  - ffmpeg=4.2.2=he774522_0
+  - filelock=3.9.0=py310haa95532_0
+  - flit-core=3.8.0=py310haa95532_0
+  - freetype=2.12.1=ha860e81_0
+  - future=0.18.3=py310haa95532_0
+  - gflags=2.2.2=ha925a31_0
+  - giflib=5.2.1=h8cc25b3_3
+  - gitdb=4.0.7=pyhd3eb1b0_0
+  - gitpython=3.1.30=py310haa95532_0
+  - glib=2.69.1=h5dc1a3c_2
+  - glog=0.5.0=hd77b12b_0
+  - gst-plugins-base=1.18.5=h9e645db_0
+  - gstreamer=1.18.5=hd78058f_0
+  - hdf5=1.10.6=h1756f20_1
+  - icc_rt=2022.1.0=h6049295_2
+  - icu=58.2=ha925a31_3
+  - idna=3.4=py310haa95532_0
+  - importlib-metadata=6.0.0=py310haa95532_0
+  - intel-openmp=2021.4.0=haa95532_3556
+  - ipykernel=6.19.2=py310h9909e9c_0
+  - ipython=8.10.0=py310haa95532_0
+  - ipywidgets=8.0.4=py310haa95532_0
+  - jedi=0.18.1=py310haa95532_1
+  - jinja2=3.1.2=py310haa95532_0
+  - jpeg=9e=h2bbff1b_1
+  - jsonschema=4.17.3=py310haa95532_0
+  - jupyter_client=7.4.9=py310haa95532_0
+  - jupyter_core=5.2.0=py310haa95532_0
+  - jupyterlab_widgets=3.0.5=py310haa95532_0
+  - lerc=3.0=hd77b12b_0
+  - libboost=1.73.0=h6c2663c_12
+  - libbrotlicommon=1.0.9=h2bbff1b_7
+  - libbrotlidec=1.0.9=h2bbff1b_7
+  - libbrotlienc=1.0.9=h2bbff1b_7
+  - libclang=12.0.0=default_h627e005_2
+  - libcublas=11.11.3.6=0
+  - libcublas-dev=11.11.3.6=0
+  - libcufft=10.9.0.58=0
+  - libcufft-dev=10.9.0.58=0
+  - libcurand=10.3.2.56=0
+  - libcurand-dev=10.3.2.56=0
+  - libcurl=7.88.1=h86230a5_0
+  - libcusolver=11.4.1.48=0
+  - libcusolver-dev=11.4.1.48=0
+  - libcusparse=11.7.5.86=0
+  - libcusparse-dev=11.7.5.86=0
+  - libdeflate=1.17=h2bbff1b_0
+  - libffi=3.4.2=hd77b12b_6
+  - libiconv=1.16=h2bbff1b_2
+  - libnpp=11.8.0.86=0
+  - libnpp-dev=11.8.0.86=0
+  - libnvjpeg=11.9.0.86=0
+  - libnvjpeg-dev=11.9.0.86=0
+  - libogg=1.3.5=h2bbff1b_1
+  - libpng=1.6.39=h8cc25b3_0
+  - libprotobuf=3.20.3=h23ce68f_0
+  - libsodium=1.0.18=h62dcd97_0
+  - libssh2=1.10.0=hcd4344a_0
+  - libthrift=0.15.0=he1d8c1a_0
+  - libtiff=4.5.0=h6c2663c_2
+  - libuv=1.44.2=h2bbff1b_0
+  - libvorbis=1.3.7=he774522_0
+  - libwebp=1.2.4=hbc33d0d_1
+  - libwebp-base=1.2.4=h2bbff1b_1
+  - libxml2=2.9.14=h0ad7f3c_0
+  - libxslt=1.1.35=h2bbff1b_0
+  - lz4-c=1.9.4=h2bbff1b_0
+  - markupsafe=2.1.1=py310h2bbff1b_0
+  - matplotlib-inline=0.1.6=py310haa95532_0
+  - mkl=2021.4.0=haa95532_640
+  - mkl-service=2.4.0=py310h2bbff1b_0
+  - mkl_fft=1.3.1=py310ha0764ea_0
+  - mkl_random=1.2.2=py310h4ed8f06_0
+  - mpmath=1.2.1=py310haa95532_0
+  - nest-asyncio=1.5.6=py310haa95532_0
+  - networkx=2.8.4=py310haa95532_1
+  - numexpr=2.8.4=py310hd213c9f_0
+  - numpy=1.23.5=py310h60c9a35_0
+  - numpy-base=1.23.5=py310h04254f7_0
+  - opencv=4.6.0=py310h4ed8f06_3
+  - openssl=1.1.1t=h2bbff1b_0
+  - packaging=23.0=py310haa95532_0
+  - pandas=1.5.3=py310h4ed8f06_0
+  - parso=0.8.3=pyhd3eb1b0_0
+  - pcre=8.45=hd77b12b_0
+  - pickleshare=0.7.5=pyhd3eb1b0_1003
+  - pillow=9.4.0=py310hd77b12b_0
+  - pip=23.0.1=py310haa95532_0
+  - platformdirs=2.5.2=py310haa95532_0
+  - prompt-toolkit=3.0.36=py310haa95532_0
+  - protobuf=3.20.3=py310hd77b12b_0
+  - psutil=5.9.0=py310h2bbff1b_0
+  - pure_eval=0.2.2=pyhd3eb1b0_0
+  - pyarrow=8.0.0=py310h26aae1b_0
+  - pycparser=2.21=pyhd3eb1b0_0
+  - pydeck=0.7.1=py310haa95532_0
+  - pympler=0.9=py_0
+  - pyopenssl=23.0.0=py310haa95532_0
+  - pyrsistent=0.18.0=py310h2bbff1b_0
+  - pysocks=1.7.1=py310haa95532_0
+  - python=3.10.10=h966fe2a_2
+  - python-dateutil=2.8.2=pyhd3eb1b0_0
+  - pytorch=2.0.0=py3.10_cuda11.8_cudnn8_0
+  - pytorch-cuda=11.8=h24eeafa_3
+  - pytorch-mutex=1.0=cuda
+  - pywin32=305=py310h2bbff1b_0
+  - pyyaml=6.0=py310h2bbff1b_1
+  - pyzmq=23.2.0=py310hd77b12b_0
+  - qt-main=5.15.2=he8e5bd7_7
+  - qt-webengine=5.15.9=hb9a9bb5_5
+  - qtwebkit=5.212=h3ad3cdb_4
+  - re2=2022.04.01=hd77b12b_0
+  - requests=2.28.1=py310haa95532_1
+  - semver=2.13.0=pyhd3eb1b0_0
+  - setuptools=65.6.3=py310haa95532_0
+  - six=1.16.0=pyhd3eb1b0_1
+  - smmap=4.0.0=pyhd3eb1b0_0
+  - snappy=1.1.9=h6c2663c_0
+  - sqlite=3.41.1=h2bbff1b_0
+  - stack_data=0.2.0=pyhd3eb1b0_0
+  - sympy=1.11.1=py310haa95532_0
+  - tk=8.6.12=h2bbff1b_0
+  - toml=0.10.2=pyhd3eb1b0_0
+  - toolz=0.12.0=py310haa95532_0
+  - tornado=6.2=py310h2bbff1b_0
+  - traitlets=5.7.1=py310haa95532_0
+  - typing_extensions=4.4.0=py310haa95532_0
+  - tzdata=2022g=h04d1e81_0
+  - tzlocal=2.1=py310haa95532_1
+  - urllib3=1.26.14=py310haa95532_0
+  - utf8proc=2.6.1=h2bbff1b_0
+  - validators=0.18.2=pyhd3eb1b0_0
+  - vc=14.2=h21ff451_1
+  - vs2015_runtime=14.27.29016=h5e58377_2
+  - watchdog=2.1.6=py310haa95532_0
+  - wcwidth=0.2.5=pyhd3eb1b0_0
+  - wheel=0.38.4=py310haa95532_0
+  - widgetsnbextension=4.0.5=py310haa95532_0
+  - win_inet_pton=1.1.0=py310haa95532_0
+  - wincertstore=0.2=py310haa95532_2
+  - xz=5.2.10=h8cc25b3_1
+  - yaml=0.2.5=he774522_0
+  - zeromq=4.3.4=hd77b12b_0
+  - zipp=3.11.0=py310haa95532_0
+  - zlib=1.2.13=h8cc25b3_0
+  - zstd=1.5.2=h19a0ad4_0
+  - pip:
+    - addict==2.4.0
+    - click==8.1.3
+    - contourpy==1.0.7
+    - cycler==0.11.0
+    - cython==0.29.33
+    - fonttools==4.39.2
+    - kiwisolver==1.4.4
+    - markdown==3.4.3
+    - markdown-it-py==2.2.0
+    - matplotlib==3.7.1
+    - mdurl==0.1.2
+    - mmcls==0.25.0
+    - mmcv==1.7.1
+    - mmcv-full==1.7.1
+    - mmpycocotools==12.0.3
+    - model-index==0.1.11
+    - openmim==0.3.7
+    - ordered-set==4.1.0
+    - pycocotools==2.0.6
+    - pygments==2.14.0
+    - pyparsing==3.0.9
+    - pytz==2023.2
+    - regex==2023.3.23
+    - rich==13.3.2
+    - scipy==1.10.1
+    - streamlit==1.20.0
+    - tabulate==0.9.0
+    - terminaltables==3.1.10
+    - torchaudio==2.0.0
+    - torchvision==0.15.0
+    - yapf==0.32.0
+prefix: C:\Users\laich\anaconda3\envs\demo-mm-st

generate.py

@@ -0,0 +1,182 @@
+import streamlit as st
+import cv2
+import numpy as np
+import requests
+from mmdet.apis import init_detector, inference_detector
+import mmcv
+import torch
+from mmdet.utils.contextmanagers import concurrent
+from pprint import pprint
+from PIL import Image
+import datetime
+
+
+
+# Specify the path to model config and checkpoint file
+config_file = 'configs/fasterrcnn.py'
+checkpoint_file = 'models/fasterrcnn.pth'
+
+# build the model from a config file and a checkpoint file
+model = init_detector(config_file, checkpoint_file, device='cuda:0')
+
+# test a single image and show the results
+img = 'demo2.png'  # or img = mmcv.imread(img), which will only load it once
+result = inference_detector(model, img)
+# visualize the results in a new window
+model.show_result(img, result)
+# or save the visualization results to image files
+model.show_result(img, result, out_file='result.jpg')
+
+list_objects = []
+
+for i in result[1]:
+    temp = i
+    temp = np.append(temp, 1)
+    list_objects.append(temp)
+
+for i in result[2]:
+    temp = i 
+    temp = np.append(temp, 2)
+    list_objects.append(temp)
+
+for i in result[3]:
+    temp = i
+    temp = np.append(temp, 3)
+    list_objects.append(temp)
+
+img = cv2.imread(img)
+for i in list_objects:
+    if i[5] == 1:
+        color = (255, 0, 0)
+        text  = "Mask weared incorrect"
+    elif i[5] == 2:
+        color = (0, 255, 0)
+        text  = "With mask"
+    elif i[5] == 3:
+        color = (0, 0, 255)
+        text = "Without mask"
+    text += ": " + str(round(i[4], 2))
+    x1 = i[0]
+    y1 = i[1]
+    x2 = i[2] - 1
+    y2 = i[3] - 1
+
+    x1 = round(x1)
+    y1 = round(y1)
+    x2 = round(x2)
+    y2 = round(y2)
+
+    img = cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
+    img = cv2.putText(img, text, (x1, y1-10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
+cv2.imwrite('Original_result.jpg', img)
+
+def IoU(bbox1, bbox2):
+
+    x1_left = bbox1[0]
+    y1_top = bbox1[1]
+    x1_right = bbox1[2]
+    y1_bot = bbox1[3]
+
+    x2_left = bbox2[0]
+    y2_top = bbox2[1]
+    x2_right = bbox2[2]
+    y2_bot = bbox2[3]
+
+    x_left = max(x1_left, x2_left)
+    x_right = min(x1_right, x2_right)
+    y_top = max(y1_top, y2_top)
+    y_bot = min(y1_bot, y2_bot)
+
+    inter = (x_right - x_left) * (y_bot - y_top)
+    if x_right < x_left or y_bot < y_top:
+        return 0.0
+    area1 = (x1_right - x1_left) * (y1_bot - y1_top)
+    area2 = (x2_right - x2_left) * (y2_bot - y2_top)
+    union = area1 + area2 - inter
+
+    IoU = inter / union
+    return IoU
+
+total_people = 0
+incorrect = 0
+withmask = 0
+withoutmask = 0
+list_objects = []
+isRemove = []
+for i in result[1]:
+    temp = i
+    temp = np.append(temp, 1)
+    list_objects.append(temp)
+    isRemove.append(0)
+
+for i in result[2]:
+    temp = i 
+    temp = np.append(temp, 2)
+    list_objects.append(temp)
+    isRemove.append(0)
+
+for i in result[3]:
+    temp = i
+    temp = np.append(temp, 3)
+    list_objects.append(temp)
+    isRemove.append(0)
+
+for i in range(len(list_objects) - 1):
+    for j in range(i + 1, len(list_objects)):
+        bbox1 = [list_objects[i][0], list_objects[i][1], list_objects[i][2], list_objects[i][3]]
+        bbox2 = [list_objects[j][0], list_objects[j][1], list_objects[j][2], list_objects[j][3]]
+        if abs(IoU(bbox1, bbox2)) > 0.7:
+            if list_objects[i][4] > list_objects[j][4]:
+                isRemove[j] = 1
+            else:
+                isRemove[i] = 1
+            # print("IoU", abs(IoU(bbox1, bbox2)))
+        
+
+        if list_objects[i][4] < 0.4:
+            isRemove[i] = 1
+        if list_objects[j][4] < 0.4:
+            isRemove[j] = 1
+
+selected_list = []
+for i in range(len(list_objects)):
+    if isRemove[i] == 0:
+        selected_list.append(list_objects[i])
+
+for i in selected_list:
+    if i[5] == 1:
+        incorrect += 1
+    elif i[5] == 2:
+        withmask += 1
+    elif i[5] ==3:
+        withoutmask += 1
+    
+total_people += incorrect + withmask + withoutmask
+
+img = 'demo2.png'  # or img = mmcv.imread(img), which will only load it once
+
+img = cv2.imread(img)
+for i in selected_list:
+    if i[5] == 1:
+        color = (255, 0, 0)
+        text  = "Mask weared incorrect"
+    elif i[5] == 2:
+        color = (0, 255, 0)
+        text  = "With mask"
+    elif i[5] == 3:
+        color = (0, 0, 255)
+        text = "Without mask"
+    text += ": " + str(round(i[4], 2))
+    x1 = i[0]
+    y1 = i[1]
+    x2 = i[2] - 1
+    y2 = i[3] - 1
+
+    x1 = round(x1)
+    y1 = round(y1)
+    x2 = round(x2)
+    y2 = round(y2)
+
+    img = cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
+    img = cv2.putText(img, text, (x1, y1-10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
+cv2.imwrite('New_result.jpg', img)