Append Common Object Detection COCO

Python/Object Detection/Coco/ssd_mobilenet_v3_large_coco_2020_01_14/checkpoint

@@ -0,0 +1,2 @@
+model_checkpoint_path: "model.ckpt"
+all_model_checkpoint_paths: "model.ckpt"

Python/Object Detection/Coco/ssd_mobilenet_v3_large_coco_2020_01_14/pipeline.config

@@ -0,0 +1,203 @@
+# SSDLite with Mobilenet v3 large feature extractor.
+# Trained on COCO14, initialized from scratch.
+# 3.22M parameters, 1.02B FLOPs
+# TPU-compatible.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  ssd {
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+    num_classes: 90
+    box_coder {
+      faster_rcnn_box_coder {
+        y_scale: 10.0
+        x_scale: 10.0
+        height_scale: 5.0
+        width_scale: 5.0
+      }
+    }
+    matcher {
+      argmax_matcher {
+        matched_threshold: 0.5
+        unmatched_threshold: 0.5
+        ignore_thresholds: false
+        negatives_lower_than_unmatched: true
+        force_match_for_each_row: true
+        use_matmul_gather: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    encode_background_as_zeros: true
+    anchor_generator {
+      ssd_anchor_generator {
+        num_layers: 6
+        min_scale: 0.2
+        max_scale: 0.95
+        aspect_ratios: 1.0
+        aspect_ratios: 2.0
+        aspect_ratios: 0.5
+        aspect_ratios: 3.0
+        aspect_ratios: 0.3333
+      }
+    }
+    image_resizer {
+      fixed_shape_resizer {
+        height: 320
+        width: 320
+      }
+    }
+    box_predictor {
+      convolutional_box_predictor {
+        min_depth: 0
+        max_depth: 0
+        num_layers_before_predictor: 0
+        use_dropout: false
+        dropout_keep_probability: 0.8
+        kernel_size: 3
+        use_depthwise: true
+        box_code_size: 4
+        apply_sigmoid_to_scores: false
+        class_prediction_bias_init: -4.6
+        conv_hyperparams {
+          activation: RELU_6,
+          regularizer {
+            l2_regularizer {
+              weight: 0.00004
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              stddev: 0.03
+              mean: 0.0
+            }
+          }
+          batch_norm {
+            train: true,
+            scale: true,
+            center: true,
+            decay: 0.97,
+            epsilon: 0.001,
+          }
+        }
+      }
+    }
+    feature_extractor {
+      type: 'ssd_mobilenet_v3_large'
+      min_depth: 16
+      depth_multiplier: 1.0
+      use_depthwise: true
+      conv_hyperparams {
+        activation: RELU_6,
+        regularizer {
+          l2_regularizer {
+            weight: 0.00004
+          }
+        }
+        initializer {
+          truncated_normal_initializer {
+            stddev: 0.03
+            mean: 0.0
+          }
+        }
+        batch_norm {
+          train: true,
+          scale: true,
+          center: true,
+          decay: 0.97,
+          epsilon: 0.001,
+        }
+      }
+      override_base_feature_extractor_hyperparams: true
+    }
+    loss {
+      classification_loss {
+        weighted_sigmoid_focal {
+          alpha: 0.75,
+          gamma: 2.0
+        }
+      }
+      localization_loss {
+        weighted_smooth_l1 {
+          delta: 1.0
+        }
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    normalize_loss_by_num_matches: true
+    normalize_loc_loss_by_codesize: true
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 1e-8
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 100
+        use_static_shapes: true
+      }
+      score_converter: SIGMOID
+    }
+  }
+}
+
+train_config: {
+  batch_size: 512
+  sync_replicas: true
+  startup_delay_steps: 0
+  replicas_to_aggregate: 32
+  num_steps: 400000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    ssd_random_crop {
+    }
+  }
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        cosine_decay_learning_rate {
+          learning_rate_base: 0.4
+          total_steps: 400000
+          warmup_learning_rate: 0.13333
+          warmup_steps: 2000
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record-?????-of-00100"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+}
+
+eval_config: {
+  num_examples: 8000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record-?????-of-00010"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
+  shuffle: false
+  num_readers: 1
+}
+

Python/Object Detection/Detection_over_video.py

@@ -0,0 +1,46 @@
+import cv2 as cv
+import numpy as np
+import os
+
+config_file = (r'D:\Hacktoberfest2021-2\Python\Object Detection\Coco\ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt')
+frozen_model = (r'D:\Hacktoberfest2021-2\Python\Object Detection\Coco\frozen_inference_graph.pb')
+out = cv.VideoWriter('Result.mp4', cv.VideoWriter_fourcc(*'m', 'p', '4', 'v'), 20, (700, 500))
+
+
+model = cv.dnn_DetectionModel(frozen_model, config_file)
+
+classLabels = []
+file_name = (r'D:\Hacktoberfest2021-2\Python\Object Detection\Labels.txt')
+with open(file_name, 'rt') as fpt:
+    classLabels = fpt.read().rstrip('\n').split('\n')
+
+# print(classLabels)
+
+capture = cv.VideoCapture(0)#r'D:\3D-Object-Detection\Photos\street2.wmv'
+while True:
+    isTrue, img = capture.read()
+    width, height = 700, 500
+    img = cv.resize(img, (width, height))
+
+    model.setInputSize(320, 320)
+    model.setInputScale(1.0 / 127.5)
+    model.setInputMean((127.5, 127.5, 127.5))
+    model.setInputSwapRB(True)
+
+    ClassIndex, confidence, bbox = model.detect(img, confThreshold=0.5)
+    if len(ClassIndex) != 0:
+        for ClassInd, conf, boxes in zip(ClassIndex.flatten(), confidence.flatten(), bbox):
+            if (ClassInd <= 80):
+
+                cv.rectangle(img, boxes, (255, 0, 0), 2)
+                cv.putText(img, classLabels[int(ClassInd - 1)], (boxes[0] + 10, boxes[1] + 40), cv.FONT_HERSHEY_PLAIN,
+                           3, color=(255, 0, 0), thickness=3)
+
+        out.write(img)
+        cv.imshow('Video', img)
+
+        if cv.waitKey(1) & 0xFF == 27:
+            break
+capture.release()
+out.release()
+capture.destroAllWindows

Python/Object Detection/Labels.txt

@@ -0,0 +1,80 @@
+person
+bicycle
+car
+motorbike
+aeroplane
+bus
+train
+truck
+boat
+traffic light
+fire hydrant
+stop sign
+parking meter
+bench
+bird
+cat
+dog
+horse
+sheep
+cow
+elephant
+bear
+zebra
+giraffe
+backpack
+umbrella
+handbag
+tie
+suitcase
+frisbee
+skis
+snowboard
+sports ball
+kite
+baseball bat
+baseball glove
+skateboard
+surfboard
+tennis racket
+bottle
+wine glass
+cup
+fork
+knife
+spoon
+bowl
+banana
+apple
+sandwich
+orange
+broccoli
+carrot
+hot dog
+pizza
+donut
+cake
+chair
+sofa
+pottedplant
+bed
+diningtable
+toilet
+tvmonitor
+laptop
+mouse
+remote
+keyboard
+cell phone
+microwave
+oven
+toaster
+sink
+refrigerator
+book
+clock
+vase
+scissors
+teddy bear
+hair drier
+toothbrush

Python/Object Detection/README.md

@@ -0,0 +1,23 @@
+## 3D-Object-Detection
+
+[MediaPipe Objectron](https://google.github.io/mediapipe/solutions/objectron.html) is a mobile real-time 3D object detection solution for everyday objects by Google. It detects objects in 2D images, and estimates their poses through a machine learning (ML) model, trained on the Objectron dataset.
+
+<img src="https://github.com/souvik0306/3D-Object-Detection/blob/master/Photos/Result.gif" width="600" height="400">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+## ***References*** -
+1. The Coding Lab's MediaPipe Tutorial - [YouTube](https://www.youtube.com/watch?v=f-Ibri14KMY&ab_channel=TheCodingLib)