Add Faster R-CNN

.gitignore

@@ -1,2 +1,8 @@
 .idea/
 __pycache__
+_ext
+*.pyc
+*.so
+maskrcnn_benchmark.egg-info/
+build/
+dist/

configs/object_detector/e2e_faster_rcnn_R_50_FPN_1x.yaml

@@ -0,0 +1,33 @@
+MODEL:
+  META_ARCHITECTURE: "ObjectDetRCNN"
+  WEIGHT: "pretrained_model/e2e_faster_rcnn_R_50_FPN_1x.pth"
+  BACKBONE:
+    CONV_BODY: "R-50-FPN"
+  RESNETS:
+    BACKBONE_OUT_CHANNELS: 256
+  RPN:
+    USE_FPN: True
+    ANCHOR_STRIDE: (4, 8, 16, 32, 64)
+    PRE_NMS_TOP_N_TRAIN: 2000
+    PRE_NMS_TOP_N_TEST: 1000
+    POST_NMS_TOP_N_TEST: 1000
+    FPN_POST_NMS_TOP_N_TEST: 1000
+  ROI_HEADS:
+    USE_FPN: True
+  ROI_BOX_HEAD:
+    POOLER_RESOLUTION: 7
+    POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125)
+    POOLER_SAMPLING_RATIO: 2
+    FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor"
+    PREDICTOR: "FPNPredictor"
+    NUM_CLASSES: 81
+DATASETS:
+  TRAIN: ("coco_2014_train", "coco_2014_valminusminival")
+  TEST: ("coco_2014_minival",)
+DATALOADER:
+  SIZE_DIVISIBILITY: 32
+SOLVER:
+  BASE_LR: 0.02
+  WEIGHT_DECAY: 0.0001
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000

demo/demo_obj_det.py

@@ -0,0 +1,77 @@
+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+import argparse
+import cv2
+
+from maskrcnn_benchmark.config import cfg
+from predictor import COCODemo
+
+import time
+
+
+def main():
+    parser = argparse.ArgumentParser(description="PyTorch Object Detection Webcam Demo")
+    parser.add_argument(
+        "--config-file",
+        default="configs/object_detector/e2e_faster_rcnn_R_50_FPN_1x.yaml",
+        metavar="FILE",
+        help="path to config file",
+    )
+    parser.add_argument(
+        "--confidence-threshold",
+        type=float,
+        default=0.1,
+        help="Minimum score for the prediction to be shown",
+    )
+    parser.add_argument(
+        "--min-image-size",
+        type=int,
+        default=224,
+        help="Smallest size of the image to feed to the model. "
+            "Model was trained with 800, which gives best results",
+    )
+    parser.add_argument(
+        "--show-mask-heatmaps",
+        dest="show_mask_heatmaps",
+        help="Show a heatmap probability for the top masks-per-dim masks",
+        action="store_true",
+    )
+    parser.add_argument(
+        "--masks-per-dim",
+        type=int,
+        default=2,
+        help="Number of heatmaps per dimension to show",
+    )
+    parser.add_argument(
+        "opts",
+        help="Modify model config options using the command-line",
+        default=None,
+        nargs=argparse.REMAINDER,
+    )
+
+    args = parser.parse_args()
+
+    # load config from file and command-line arguments
+    cfg.merge_from_file(args.config_file)
+    cfg.merge_from_list(args.opts)
+    cfg.freeze()
+
+    # prepare object that handles inference plus adds predictions on top of image
+    coco_demo = COCODemo(
+        cfg,
+        confidence_threshold=args.confidence_threshold,
+        show_mask_heatmaps=args.show_mask_heatmaps,
+        masks_per_dim=args.masks_per_dim,
+        min_image_size=args.min_image_size,
+        weight_loading='pretrained_model/e2e_faster_rcnn_R_50_FPN_1x.pth'
+    )
+
+    img = cv2.imread('demo/coco_demo.jpg')
+    # Get a dict of results
+    result_dict = coco_demo.get_result_dict(img)
+    # Visualization
+    #composite = coco_demo.run_on_opencv_image(img)
+    #cv2.imwrite('test.png', composite)
+
+
+if __name__ == "__main__":
+    main()