test

app.py

@@ -1,65 +1,25 @@
-"""
-tree-segmentation
-Proof of concept showing effectiveness of a fine tuned instance segmentation model for detecting trees.
-"""
-import os
-import cv2
-os.system("pip install 'git+https://github.com/facebookresearch/detectron2.git'")
-from transformers import DetrFeatureExtractor, DetrForSegmentation
-from PIL import Image
 import gradio as gr
-import numpy as np
-import torch
-import torchvision
-import detectron2
+from backend import visualize_image
 
-# import some common detectron2 utilities
-import itertools
-import seaborn as sns
-from detectron2 import model_zoo
-from detectron2.engine import DefaultPredictor
-from detectron2.config import get_cfg
-from detectron2.utils.visualizer import Visualizer
-from detectron2.utils.visualizer import ColorMode
-from detectron2.data import MetadataCatalog, DatasetCatalog
-from detectron2.checkpoint import DetectionCheckpointer
+# gradio inputs
+image_input = gr.inputs.Image(type="pil", label="Input Image")
+mode_dropdown = gr.inputs.Dropdown(["Trees", "Buildings", "Both"])
+tree_threshold_slider = gr.inputs.Slider(0, 1, 0.1, 0.7, label='Set confidence threshold % for trees')
+building_threshold_slider = gr.inputs.Slider(0, 1, 0.1, 0.7, label='Set confidence threshold % for buildings')
+color_mode_select = gr.inputs.Radio(["Black/white", "Random", "Segmentation"])
 
-cfg = get_cfg()
-cfg.merge_from_file("model_weights/treev1_cfg.yaml")
-cfg.MODEL.DEVICE='cpu'
-cfg.MODEL.WEIGHTS = "model_weights/treev1_best.pth"  
-cfg.MODEL.ROI_HEADS.NUM_CLASSES = 2
-
-def segment_image(im):
-
-    cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.25
-    predictor = DefaultPredictor(cfg)
-    im = np.array(im)
-    outputs = predictor(im)
-    v = Visualizer(im[:, :, ::-1],
-                   scale=0.5,
-                   instance_mode=ColorMode.SEGMENTATION
-    )
-    print(len(outputs["instances"])," trees detected.")
-    out = v.draw_instance_predictions(outputs["instances"].to("cpu"))
-    
-    return Image.fromarray(out.get_image()[:, :, ::-1])
-
-# gradio components 
-"""
-gr_slider_confidence = gr.inputs.Slider(0,1,.1,.7,
-                                        label='Set confidence threshold % for masks')
-"""
 # gradio outputs
-inputs = gr.inputs.Image(type="pil", label="Input Image")
-outputs = gr.outputs.Image(type="pil", label="Output Image")
+output_image = gr.outputs.Image(type="pil", label="Output Image")
+title = "Building Segmentation"
+description = "An instance segmentation demo for identifying boundaries of buildings in aerial images using DETR (End-to-End Object Detection) model with MaskRCNN-101 backbone"
 
-title = "Tree Segmentation"
-description = "An instance segmentation demo for identifying trees in aerial images using DETR (End-to-End Object Detection) model with MaskRCNN-101 backbone"
+# gradio interface
+interface = gr.Interface(
+    fn=visualize_image,
+    inputs=[image_input, mode_dropdown, tree_threshold_slider, building_threshold_slider, color_mode_select],
+    outputs=output_image,
+    title=title,
+    description=description
+)
 
-# Create user interface and launch
-gr.Interface(segment_image, 
-                inputs = inputs,
-                outputs = outputs,
-                 title = title,
-                description = description).launch(debug=True)
+interface.launch(debug=True)

app_old.py

@@ -0,0 +1,65 @@
+"""
+tree-segmentation
+Proof of concept showing effectiveness of a fine tuned instance segmentation model for detecting trees.
+"""
+import os
+import cv2
+os.system("pip install 'git+https://github.com/facebookresearch/detectron2.git'")
+from transformers import DetrFeatureExtractor, DetrForSegmentation
+from PIL import Image
+import gradio as gr
+import numpy as np
+import torch
+import torchvision
+import detectron2
+
+# import some common detectron2 utilities
+import itertools
+import seaborn as sns
+from detectron2 import model_zoo
+from detectron2.engine import DefaultPredictor
+from detectron2.config import get_cfg
+from detectron2.utils.visualizer import Visualizer
+from detectron2.utils.visualizer import ColorMode
+from detectron2.data import MetadataCatalog, DatasetCatalog
+from detectron2.checkpoint import DetectionCheckpointer
+
+cfg = get_cfg()
+cfg.merge_from_file("model_weights/treev1_cfg.yaml")
+cfg.MODEL.DEVICE='cpu'
+cfg.MODEL.WEIGHTS = "model_weights/treev1_best.pth"  
+cfg.MODEL.ROI_HEADS.NUM_CLASSES = 2
+
+def segment_image(im):
+
+    cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.25
+    predictor = DefaultPredictor(cfg)
+    im = np.array(im)
+    outputs = predictor(im)
+    v = Visualizer(im[:, :, ::-1],
+                   scale=0.5,
+                   instance_mode=ColorMode.SEGMENTATION
+    )
+    print(len(outputs["instances"])," trees detected.")
+    out = v.draw_instance_predictions(outputs["instances"].to("cpu"))
+    
+    return Image.fromarray(out.get_image()[:, :, ::-1])
+
+# gradio components 
+"""
+gr_slider_confidence = gr.inputs.Slider(0,1,.1,.7,
+                                        label='Set confidence threshold % for masks')
+"""
+# gradio outputs
+inputs = gr.inputs.Image(type="pil", label="Input Image")
+outputs = gr.outputs.Image(type="pil", label="Output Image")
+
+title = "Tree Segmentation"
+description = "An instance segmentation demo for identifying trees in aerial images using DETR (End-to-End Object Detection) model with MaskRCNN-101 backbone"
+
+# Create user interface and launch
+gr.Interface(segment_image, 
+                inputs = inputs,
+                outputs = outputs,
+                 title = title,
+                description = description).launch(debug=True)

backend.py

@@ -0,0 +1,93 @@
+"""
+tree-segmentation
+Proof of concept showing effectiveness of a fine tuned instance segmentation model for detecting trees.
+"""
+import os
+import cv2
+os.system("pip install 'git+https://github.com/facebookresearch/detectron2.git'")
+from transformers import DetrFeatureExtractor, DetrForSegmentation
+from PIL import Image
+import gradio as gr
+import numpy as np
+import torch
+import torchvision
+import detectron2
+
+# import some common detectron2 utilities
+import itertools
+import seaborn as sns
+from detectron2 import model_zoo
+from detectron2.engine import DefaultPredictor
+from detectron2.config import get_cfg
+from detectron2.utils.visualizer import Visualizer
+from detectron2.utils.visualizer import ColorMode
+from detectron2.data import MetadataCatalog, DatasetCatalog
+from detectron2.checkpoint import DetectionCheckpointer
+from detectron2.utils.visualizer import ColorMode
+from detectron2.structures import Instances
+
+
+# Model for trees
+tree_cfg = get_cfg()
+tree_cfg.merge_from_file("tree_model_weights/tree_cfg.yml")
+tree_cfg.MODEL.DEVICE='cpu'
+tree_cfg.MODEL.WEIGHTS = "tree_model_weights/treev1_best.pth"
+tree_cfg.MODEL.ROI_HEADS.NUM_CLASSES = 2
+tree_predictor = DefaultPredictor(tree_cfg)
+
+# Model for buildings
+building_cfg = get_cfg()
+building_cfg.merge_from_file("building_model_weight/building_poc_cfg.yml")
+building_cfg.MODEL.DEVICE='cpu'
+building_cfg.MODEL.WEIGHTS = "building_model_weight/model_final.pth"  
+building_cfg.MODEL.ROI_HEADS.NUM_CLASSES = 8
+building_predictor = DefaultPredictor(building_cfg)
+
+# A function that runs the buildings model on an given image and confidence threshold
+def segment_building(im, confidence_threshold):
+    building_cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = confidence_threshold
+    im = np.array(im)
+    outputs = building_predictor(im)
+    building_instances = outputs["instances"].to("cpu")
+
+    return building_instances
+
+# A function that runs the trees model on an given image and confidence threshold
+def segment_tree(im, confidence_threshold):
+    tree_cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = confidence_threshold
+    im = np.array(im)
+    outputs = tree_predictor(im)
+    tree_instances = outputs["instances"].to("cpu")
+
+    return tree_instances
+
+# Function to map strings to color mode
+def map_color_mode(color_mode):
+    if color_mode == "Black/white":
+        return ColorMode.IMAGE_BW
+    elif color_mode == "Random":
+        return ColorMode.IMAGE
+    elif color_mode == "Segmentation":
+        return ColorMode.SEGMENTATION
+
+def visualize_image(im, mode, tree_threshold, building_threshold, color_mode=ColorMode.SEGMENTATION):
+    color_mode = map_color_mode(color_mode)
+
+    if mode == "Trees":
+        instances = segment_tree(im, tree_threshold)
+    elif mode == "Buildings":
+        instances = segment_building(im, building_threshold)
+    elif mode == "Both":
+        tree_instances = segment_tree(im, tree_threshold)
+        building_instances = segment_building(im, building_threshold)
+        instances = Instances.cat([tree_instances, building_instances])
+
+    visualizer = Visualizer(im[:, :, ::-1],
+                            scale=0.5,
+                            instance_mode=color_mode)
+    
+    output_image = visualizer.draw_instance_predictions(instances)
+    
+    return Image.fromarray(output_image.get_image()[:, :, ::-1])
+
+

building_model_weight/buildingsv1_best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:061e1e613db507f4023fb91731cde779240793414d7a6477604ca9473bfa05c2
+size 254201166

building_model_weight/buildingsv1_cfg.yaml

@@ -0,0 +1,325 @@
+CUDNN_BENCHMARK: false
+DATALOADER:
+  ASPECT_RATIO_GROUPING: true
+  FILTER_EMPTY_ANNOTATIONS: true
+  NUM_WORKERS: 2
+  REPEAT_THRESHOLD: 0.0
+  SAMPLER_TRAIN: TrainingSampler
+DATASETS:
+  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
+  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
+  PROPOSAL_FILES_TEST: []
+  PROPOSAL_FILES_TRAIN: []
+  TEST:
+  - trees_test
+  TRAIN:
+  - trees_train
+GLOBAL:
+  HACK: 1.0
+INPUT:
+  CROP:
+    ENABLED: false
+    SIZE:
+    - 0.9
+    - 0.9
+    TYPE: relative_range
+  FORMAT: BGR
+  MASK_FORMAT: polygon
+  MAX_SIZE_TEST: 1333
+  MAX_SIZE_TRAIN: 1333
+  MIN_SIZE_TEST: 800
+  MIN_SIZE_TRAIN:
+  - 640
+  - 672
+  - 704
+  - 736
+  - 768
+  - 800
+  MIN_SIZE_TRAIN_SAMPLING: choice
+  RANDOM_FLIP: horizontal
+MODEL:
+  ANCHOR_GENERATOR:
+    ANGLES:
+    - - -90
+      - 0
+      - 90
+    ASPECT_RATIOS:
+    - - 0.5
+      - 1.0
+      - 2.0
+    NAME: DefaultAnchorGenerator
+    OFFSET: 0.0
+    SIZES:
+    - - 32
+    - - 64
+    - - 128
+    - - 256
+    - - 512
+  BACKBONE:
+    FREEZE_AT: 2
+    NAME: build_resnet_fpn_backbone
+  DEVICE: cuda
+  FPN:
+    FUSE_TYPE: sum
+    IN_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    NORM: ''
+    OUT_CHANNELS: 256
+  KEYPOINT_ON: false
+  LOAD_PROPOSALS: false
+  MASK_ON: true
+  META_ARCHITECTURE: GeneralizedRCNN
+  PANOPTIC_FPN:
+    COMBINE:
+      ENABLED: true
+      INSTANCES_CONFIDENCE_THRESH: 0.5
+      OVERLAP_THRESH: 0.5
+      STUFF_AREA_LIMIT: 4096
+    INSTANCE_LOSS_WEIGHT: 1.0
+  PIXEL_MEAN:
+  - 103.53
+  - 116.28
+  - 123.675
+  PIXEL_STD:
+  - 1.0
+  - 1.0
+  - 1.0
+  PROPOSAL_GENERATOR:
+    MIN_SIZE: 0
+    NAME: RPN
+  RESNETS:
+    DEFORM_MODULATED: false
+    DEFORM_NUM_GROUPS: 1
+    DEFORM_ON_PER_STAGE:
+    - false
+    - false
+    - false
+    - false
+    DEPTH: 101
+    NORM: FrozenBN
+    NUM_GROUPS: 1
+    OUT_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    RES2_OUT_CHANNELS: 256
+    RES5_DILATION: 1
+    STEM_OUT_CHANNELS: 64
+    STRIDE_IN_1X1: true
+    WIDTH_PER_GROUP: 64
+  RETINANET:
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_WEIGHTS: &id002
+    - 1.0
+    - 1.0
+    - 1.0
+    - 1.0
+    FOCAL_LOSS_ALPHA: 0.25
+    FOCAL_LOSS_GAMMA: 2.0
+    IN_FEATURES:
+    - p3
+    - p4
+    - p5
+    - p6
+    - p7
+    IOU_LABELS:
+    - 0
+    - -1
+    - 1
+    IOU_THRESHOLDS:
+    - 0.4
+    - 0.5
+    NMS_THRESH_TEST: 0.5
+    NORM: ''
+    NUM_CLASSES: 80
+    NUM_CONVS: 4
+    PRIOR_PROB: 0.01
+    SCORE_THRESH_TEST: 0.05
+    SMOOTH_L1_LOSS_BETA: 0.1
+    TOPK_CANDIDATES_TEST: 1000
+  ROI_BOX_CASCADE_HEAD:
+    BBOX_REG_WEIGHTS:
+    - &id001
+      - 10.0
+      - 10.0
+      - 5.0
+      - 5.0
+    - - 20.0
+      - 20.0
+      - 10.0
+      - 10.0
+    - - 30.0
+      - 30.0
+      - 15.0
+      - 15.0
+    IOUS:
+    - 0.5
+    - 0.6
+    - 0.7
+  ROI_BOX_HEAD:
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_LOSS_WEIGHT: 1.0
+    BBOX_REG_WEIGHTS: *id001
+    CLS_AGNOSTIC_BBOX_REG: false
+    CONV_DIM: 256
+    FC_DIM: 1024
+    FED_LOSS_FREQ_WEIGHT_POWER: 0.5
+    FED_LOSS_NUM_CLASSES: 50
+    NAME: FastRCNNConvFCHead
+    NORM: ''
+    NUM_CONV: 0
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+    SMOOTH_L1_BETA: 0.0
+    TRAIN_ON_PRED_BOXES: false
+    USE_FED_LOSS: false
+    USE_SIGMOID_CE: false
+  ROI_HEADS:
+    BATCH_SIZE_PER_IMAGE: 512
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    IOU_LABELS:
+    - 0
+    - 1
+    IOU_THRESHOLDS:
+    - 0.5
+    NAME: StandardROIHeads
+    NMS_THRESH_TEST: 0.5
+    NUM_CLASSES: 81
+    POSITIVE_FRACTION: 0.25
+    PROPOSAL_APPEND_GT: true
+    SCORE_THRESH_TEST: 0.7
+  ROI_KEYPOINT_HEAD:
+    CONV_DIMS:
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    LOSS_WEIGHT: 1.0
+    MIN_KEYPOINTS_PER_IMAGE: 1
+    NAME: KRCNNConvDeconvUpsampleHead
+    NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true
+    NUM_KEYPOINTS: 17
+    POOLER_RESOLUTION: 14
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+  ROI_MASK_HEAD:
+    CLS_AGNOSTIC_MASK: false
+    CONV_DIM: 256
+    NAME: MaskRCNNConvUpsampleHead
+    NORM: ''
+    NUM_CONV: 4
+    POOLER_RESOLUTION: 14
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+  RPN:
+    BATCH_SIZE_PER_IMAGE: 256
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_LOSS_WEIGHT: 1.0
+    BBOX_REG_WEIGHTS: *id002
+    BOUNDARY_THRESH: -1
+    CONV_DIMS:
+    - -1
+    HEAD_NAME: StandardRPNHead
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    - p6
+    IOU_LABELS:
+    - 0
+    - -1
+    - 1
+    IOU_THRESHOLDS:
+    - 0.3
+    - 0.7
+    LOSS_WEIGHT: 1.0
+    NMS_THRESH: 0.7
+    POSITIVE_FRACTION: 0.5
+    POST_NMS_TOPK_TEST: 1000
+    POST_NMS_TOPK_TRAIN: 1000
+    PRE_NMS_TOPK_TEST: 1000
+    PRE_NMS_TOPK_TRAIN: 2000
+    SMOOTH_L1_BETA: 0.0
+  SEM_SEG_HEAD:
+    COMMON_STRIDE: 4
+    CONVS_DIM: 128
+    IGNORE_VALUE: 255
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    LOSS_WEIGHT: 1.0
+    NAME: SemSegFPNHead
+    NORM: GN
+    NUM_CLASSES: 54
+  WEIGHTS: /home/ubuntu/ssd/building_out_0311_10000/model_final.pth
+OUTPUT_DIR: /home/ubuntu/ssd/building_out_0311_10000
+SEED: -1
+SOLVER:
+  AMP:
+    ENABLED: false
+  BASE_LR: 0.00025
+  BASE_LR_END: 0.0
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 5000
+  CLIP_GRADIENTS:
+    CLIP_TYPE: value
+    CLIP_VALUE: 1.0
+    ENABLED: false
+    NORM_TYPE: 2.0
+  GAMMA: 0.1
+  IMS_PER_BATCH: 8
+  LR_SCHEDULER_NAME: WarmupMultiStepLR
+  MAX_ITER: 10000
+  MOMENTUM: 0.9
+  NESTEROV: false
+  NUM_DECAYS: 3
+  REFERENCE_WORLD_SIZE: 0
+  RESCALE_INTERVAL: false
+  STEPS: []
+  WARMUP_FACTOR: 0.001
+  WARMUP_ITERS: 1000
+  WARMUP_METHOD: linear
+  WEIGHT_DECAY: 0.0001
+  WEIGHT_DECAY_BIAS: null
+  WEIGHT_DECAY_NORM: 0.0
+TEST:
+  AUG:
+    ENABLED: false
+    FLIP: true
+    MAX_SIZE: 4000
+    MIN_SIZES:
+    - 400
+    - 500
+    - 600
+    - 700
+    - 800
+    - 900
+    - 1000
+    - 1100
+    - 1200
+  DETECTIONS_PER_IMAGE: 100
+  EVAL_PERIOD: 0
+  EXPECTED_RESULTS: []
+  KEYPOINT_OKS_SIGMAS: []
+  PRECISE_BN:
+    ENABLED: false
+    NUM_ITER: 200
+VERSION: 2
+VIS_PERIOD: 0

tree_model_weights/README.md

@@ -0,0 +1,3 @@
+# Model Weights
+
+This is where pretrained model weights are stored.

tree_model_weights/buildings_poc_cfg.yml

@@ -0,0 +1,325 @@
+CUDNN_BENCHMARK: false
+DATALOADER:
+  ASPECT_RATIO_GROUPING: true
+  FILTER_EMPTY_ANNOTATIONS: true
+  NUM_WORKERS: 2
+  REPEAT_THRESHOLD: 0.0
+  SAMPLER_TRAIN: TrainingSampler
+DATASETS:
+  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
+  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
+  PROPOSAL_FILES_TEST: []
+  PROPOSAL_FILES_TRAIN: []
+  TEST:
+  - urban-small_test
+  TRAIN:
+  - urban-small_train
+GLOBAL:
+  HACK: 1.0
+INPUT:
+  CROP:
+    ENABLED: false
+    SIZE:
+    - 0.9
+    - 0.9
+    TYPE: relative_range
+  FORMAT: BGR
+  MASK_FORMAT: polygon
+  MAX_SIZE_TEST: 1333
+  MAX_SIZE_TRAIN: 1333
+  MIN_SIZE_TEST: 800
+  MIN_SIZE_TRAIN:
+  - 640
+  - 672
+  - 704
+  - 736
+  - 768
+  - 800
+  MIN_SIZE_TRAIN_SAMPLING: choice
+  RANDOM_FLIP: horizontal
+MODEL:
+  ANCHOR_GENERATOR:
+    ANGLES:
+    - - -90
+      - 0
+      - 90
+    ASPECT_RATIOS:
+    - - 0.5
+      - 1.0
+      - 2.0
+    NAME: DefaultAnchorGenerator
+    OFFSET: 0.0
+    SIZES:
+    - - 32
+    - - 64
+    - - 128
+    - - 256
+    - - 512
+  BACKBONE:
+    FREEZE_AT: 2
+    NAME: build_resnet_fpn_backbone
+  DEVICE: cuda
+  FPN:
+    FUSE_TYPE: sum
+    IN_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    NORM: ''
+    OUT_CHANNELS: 256
+  KEYPOINT_ON: false
+  LOAD_PROPOSALS: false
+  MASK_ON: true
+  META_ARCHITECTURE: GeneralizedRCNN
+  PANOPTIC_FPN:
+    COMBINE:
+      ENABLED: true
+      INSTANCES_CONFIDENCE_THRESH: 0.5
+      OVERLAP_THRESH: 0.5
+      STUFF_AREA_LIMIT: 4096
+    INSTANCE_LOSS_WEIGHT: 1.0
+  PIXEL_MEAN:
+  - 103.53
+  - 116.28
+  - 123.675
+  PIXEL_STD:
+  - 1.0
+  - 1.0
+  - 1.0
+  PROPOSAL_GENERATOR:
+    MIN_SIZE: 0
+    NAME: RPN
+  RESNETS:
+    DEFORM_MODULATED: false
+    DEFORM_NUM_GROUPS: 1
+    DEFORM_ON_PER_STAGE:
+    - false
+    - false
+    - false
+    - false
+    DEPTH: 101
+    NORM: FrozenBN
+    NUM_GROUPS: 1
+    OUT_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    RES2_OUT_CHANNELS: 256
+    RES5_DILATION: 1
+    STEM_OUT_CHANNELS: 64
+    STRIDE_IN_1X1: true
+    WIDTH_PER_GROUP: 64
+  RETINANET:
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_WEIGHTS: &id002
+    - 1.0
+    - 1.0
+    - 1.0
+    - 1.0
+    FOCAL_LOSS_ALPHA: 0.25
+    FOCAL_LOSS_GAMMA: 2.0
+    IN_FEATURES:
+    - p3
+    - p4
+    - p5
+    - p6
+    - p7
+    IOU_LABELS:
+    - 0
+    - -1
+    - 1
+    IOU_THRESHOLDS:
+    - 0.4
+    - 0.5
+    NMS_THRESH_TEST: 0.5
+    NORM: ''
+    NUM_CLASSES: 80
+    NUM_CONVS: 4
+    PRIOR_PROB: 0.01
+    SCORE_THRESH_TEST: 0.05
+    SMOOTH_L1_LOSS_BETA: 0.1
+    TOPK_CANDIDATES_TEST: 1000
+  ROI_BOX_CASCADE_HEAD:
+    BBOX_REG_WEIGHTS:
+    - &id001
+      - 10.0
+      - 10.0
+      - 5.0
+      - 5.0
+    - - 20.0
+      - 20.0
+      - 10.0
+      - 10.0
+    - - 30.0
+      - 30.0
+      - 15.0
+      - 15.0
+    IOUS:
+    - 0.5
+    - 0.6
+    - 0.7
+  ROI_BOX_HEAD:
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_LOSS_WEIGHT: 1.0
+    BBOX_REG_WEIGHTS: *id001
+    CLS_AGNOSTIC_BBOX_REG: false
+    CONV_DIM: 256
+    FC_DIM: 1024
+    FED_LOSS_FREQ_WEIGHT_POWER: 0.5
+    FED_LOSS_NUM_CLASSES: 50
+    NAME: FastRCNNConvFCHead
+    NORM: ''
+    NUM_CONV: 0
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+    SMOOTH_L1_BETA: 0.0
+    TRAIN_ON_PRED_BOXES: false
+    USE_FED_LOSS: false
+    USE_SIGMOID_CE: false
+  ROI_HEADS:
+    BATCH_SIZE_PER_IMAGE: 512
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    IOU_LABELS:
+    - 0
+    - 1
+    IOU_THRESHOLDS:
+    - 0.5
+    NAME: StandardROIHeads
+    NMS_THRESH_TEST: 0.5
+    NUM_CLASSES: 8
+    POSITIVE_FRACTION: 0.25
+    PROPOSAL_APPEND_GT: true
+    SCORE_THRESH_TEST: 0.25
+  ROI_KEYPOINT_HEAD:
+    CONV_DIMS:
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    LOSS_WEIGHT: 1.0
+    MIN_KEYPOINTS_PER_IMAGE: 1
+    NAME: KRCNNConvDeconvUpsampleHead
+    NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true
+    NUM_KEYPOINTS: 17
+    POOLER_RESOLUTION: 14
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+  ROI_MASK_HEAD:
+    CLS_AGNOSTIC_MASK: false
+    CONV_DIM: 256
+    NAME: MaskRCNNConvUpsampleHead
+    NORM: ''
+    NUM_CONV: 4
+    POOLER_RESOLUTION: 14
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+  RPN:
+    BATCH_SIZE_PER_IMAGE: 256
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_LOSS_WEIGHT: 1.0
+    BBOX_REG_WEIGHTS: *id002
+    BOUNDARY_THRESH: -1
+    CONV_DIMS:
+    - -1
+    HEAD_NAME: StandardRPNHead
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    - p6
+    IOU_LABELS:
+    - 0
+    - -1
+    - 1
+    IOU_THRESHOLDS:
+    - 0.3
+    - 0.7
+    LOSS_WEIGHT: 1.0
+    NMS_THRESH: 0.7
+    POSITIVE_FRACTION: 0.5
+    POST_NMS_TOPK_TEST: 1000
+    POST_NMS_TOPK_TRAIN: 1000
+    PRE_NMS_TOPK_TEST: 1000
+    PRE_NMS_TOPK_TRAIN: 2000
+    SMOOTH_L1_BETA: 0.0
+  SEM_SEG_HEAD:
+    COMMON_STRIDE: 4
+    CONVS_DIM: 128
+    IGNORE_VALUE: 255
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    LOSS_WEIGHT: 1.0
+    NAME: SemSegFPNHead
+    NORM: GN
+    NUM_CLASSES: 54
+  WEIGHTS: ./output/model_final.pth
+OUTPUT_DIR: ./output
+SEED: -1
+SOLVER:
+  AMP:
+    ENABLED: false
+  BASE_LR: 0.00025
+  BASE_LR_END: 0.0
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 5000
+  CLIP_GRADIENTS:
+    CLIP_TYPE: value
+    CLIP_VALUE: 1.0
+    ENABLED: false
+    NORM_TYPE: 2.0
+  GAMMA: 0.1
+  IMS_PER_BATCH: 2
+  LR_SCHEDULER_NAME: WarmupMultiStepLR
+  MAX_ITER: 3000
+  MOMENTUM: 0.9
+  NESTEROV: false
+  NUM_DECAYS: 3
+  REFERENCE_WORLD_SIZE: 0
+  RESCALE_INTERVAL: false
+  STEPS: []
+  WARMUP_FACTOR: 0.001
+  WARMUP_ITERS: 1000
+  WARMUP_METHOD: linear
+  WEIGHT_DECAY: 0.0001
+  WEIGHT_DECAY_BIAS: null
+  WEIGHT_DECAY_NORM: 0.0
+TEST:
+  AUG:
+    ENABLED: false
+    FLIP: true
+    MAX_SIZE: 4000
+    MIN_SIZES:
+    - 400
+    - 500
+    - 600
+    - 700
+    - 800
+    - 900
+    - 1000
+    - 1100
+    - 1200
+  DETECTIONS_PER_IMAGE: 100
+  EVAL_PERIOD: 0
+  EXPECTED_RESULTS: []
+  KEYPOINT_OKS_SIGMAS: []
+  PRECISE_BN:
+    ENABLED: false
+    NUM_ITER: 200
+VERSION: 2
+VIS_PERIOD: 0

tree_model_weights/model_final.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b87453ef364938795263c24d9be8cbc4cd7e01c3390690a6c4cfb71a6ce23e
+size 503364111

tree_model_weights/tree_cfg.yml

@@ -0,0 +1,325 @@
+CUDNN_BENCHMARK: false
+DATALOADER:
+  ASPECT_RATIO_GROUPING: true
+  FILTER_EMPTY_ANNOTATIONS: true
+  NUM_WORKERS: 2
+  REPEAT_THRESHOLD: 0.0
+  SAMPLER_TRAIN: TrainingSampler
+DATASETS:
+  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
+  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
+  PROPOSAL_FILES_TEST: []
+  PROPOSAL_FILES_TRAIN: []
+  TEST:
+  - urban-trees-fdokv_test
+  TRAIN:
+  - urban-trees-fdokv_train
+GLOBAL:
+  HACK: 1.0
+INPUT:
+  CROP:
+    ENABLED: false
+    SIZE:
+    - 0.9
+    - 0.9
+    TYPE: relative_range
+  FORMAT: BGR
+  MASK_FORMAT: polygon
+  MAX_SIZE_TEST: 1333
+  MAX_SIZE_TRAIN: 1333
+  MIN_SIZE_TEST: 800
+  MIN_SIZE_TRAIN:
+  - 640
+  - 672
+  - 704
+  - 736
+  - 768
+  - 800
+  MIN_SIZE_TRAIN_SAMPLING: choice
+  RANDOM_FLIP: horizontal
+MODEL:
+  ANCHOR_GENERATOR:
+    ANGLES:
+    - - -90
+      - 0
+      - 90
+    ASPECT_RATIOS:
+    - - 0.5
+      - 1.0
+      - 2.0
+    NAME: DefaultAnchorGenerator
+    OFFSET: 0.0
+    SIZES:
+    - - 32
+    - - 64
+    - - 128
+    - - 256
+    - - 512
+  BACKBONE:
+    FREEZE_AT: 2
+    NAME: build_resnet_fpn_backbone
+  DEVICE: cuda
+  FPN:
+    FUSE_TYPE: sum
+    IN_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    NORM: ''
+    OUT_CHANNELS: 256
+  KEYPOINT_ON: false
+  LOAD_PROPOSALS: false
+  MASK_ON: true
+  META_ARCHITECTURE: GeneralizedRCNN
+  PANOPTIC_FPN:
+    COMBINE:
+      ENABLED: true
+      INSTANCES_CONFIDENCE_THRESH: 0.5
+      OVERLAP_THRESH: 0.5
+      STUFF_AREA_LIMIT: 4096
+    INSTANCE_LOSS_WEIGHT: 1.0
+  PIXEL_MEAN:
+  - 103.53
+  - 116.28
+  - 123.675
+  PIXEL_STD:
+  - 1.0
+  - 1.0
+  - 1.0
+  PROPOSAL_GENERATOR:
+    MIN_SIZE: 0
+    NAME: RPN
+  RESNETS:
+    DEFORM_MODULATED: false
+    DEFORM_NUM_GROUPS: 1
+    DEFORM_ON_PER_STAGE:
+    - false
+    - false
+    - false
+    - false
+    DEPTH: 101
+    NORM: FrozenBN
+    NUM_GROUPS: 1
+    OUT_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    RES2_OUT_CHANNELS: 256
+    RES5_DILATION: 1
+    STEM_OUT_CHANNELS: 64
+    STRIDE_IN_1X1: true
+    WIDTH_PER_GROUP: 64
+  RETINANET:
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_WEIGHTS: &id002
+    - 1.0
+    - 1.0
+    - 1.0
+    - 1.0
+    FOCAL_LOSS_ALPHA: 0.25
+    FOCAL_LOSS_GAMMA: 2.0
+    IN_FEATURES:
+    - p3
+    - p4
+    - p5
+    - p6
+    - p7
+    IOU_LABELS:
+    - 0
+    - -1
+    - 1
+    IOU_THRESHOLDS:
+    - 0.4
+    - 0.5
+    NMS_THRESH_TEST: 0.5
+    NORM: ''
+    NUM_CLASSES: 80
+    NUM_CONVS: 4
+    PRIOR_PROB: 0.01
+    SCORE_THRESH_TEST: 0.05
+    SMOOTH_L1_LOSS_BETA: 0.1
+    TOPK_CANDIDATES_TEST: 1000
+  ROI_BOX_CASCADE_HEAD:
+    BBOX_REG_WEIGHTS:
+    - &id001
+      - 10.0
+      - 10.0
+      - 5.0
+      - 5.0
+    - - 20.0
+      - 20.0
+      - 10.0
+      - 10.0
+    - - 30.0
+      - 30.0
+      - 15.0
+      - 15.0
+    IOUS:
+    - 0.5
+    - 0.6
+    - 0.7
+  ROI_BOX_HEAD:
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_LOSS_WEIGHT: 1.0
+    BBOX_REG_WEIGHTS: *id001
+    CLS_AGNOSTIC_BBOX_REG: false
+    CONV_DIM: 256
+    FC_DIM: 1024
+    FED_LOSS_FREQ_WEIGHT_POWER: 0.5
+    FED_LOSS_NUM_CLASSES: 50
+    NAME: FastRCNNConvFCHead
+    NORM: ''
+    NUM_CONV: 0
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+    SMOOTH_L1_BETA: 0.0
+    TRAIN_ON_PRED_BOXES: false
+    USE_FED_LOSS: false
+    USE_SIGMOID_CE: false
+  ROI_HEADS:
+    BATCH_SIZE_PER_IMAGE: 512
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    IOU_LABELS:
+    - 0
+    - 1
+    IOU_THRESHOLDS:
+    - 0.5
+    NAME: StandardROIHeads
+    NMS_THRESH_TEST: 0.5
+    NUM_CLASSES: 2
+    POSITIVE_FRACTION: 0.25
+    PROPOSAL_APPEND_GT: true
+    SCORE_THRESH_TEST: 0.25
+  ROI_KEYPOINT_HEAD:
+    CONV_DIMS:
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    LOSS_WEIGHT: 1.0
+    MIN_KEYPOINTS_PER_IMAGE: 1
+    NAME: KRCNNConvDeconvUpsampleHead
+    NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true
+    NUM_KEYPOINTS: 17
+    POOLER_RESOLUTION: 14
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+  ROI_MASK_HEAD:
+    CLS_AGNOSTIC_MASK: false
+    CONV_DIM: 256
+    NAME: MaskRCNNConvUpsampleHead
+    NORM: ''
+    NUM_CONV: 4
+    POOLER_RESOLUTION: 14
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+  RPN:
+    BATCH_SIZE_PER_IMAGE: 256
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_LOSS_WEIGHT: 1.0
+    BBOX_REG_WEIGHTS: *id002
+    BOUNDARY_THRESH: -1
+    CONV_DIMS:
+    - -1
+    HEAD_NAME: StandardRPNHead
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    - p6
+    IOU_LABELS:
+    - 0
+    - -1
+    - 1
+    IOU_THRESHOLDS:
+    - 0.3
+    - 0.7
+    LOSS_WEIGHT: 1.0
+    NMS_THRESH: 0.7
+    POSITIVE_FRACTION: 0.5
+    POST_NMS_TOPK_TEST: 1000
+    POST_NMS_TOPK_TRAIN: 1000
+    PRE_NMS_TOPK_TEST: 1000
+    PRE_NMS_TOPK_TRAIN: 2000
+    SMOOTH_L1_BETA: 0.0
+  SEM_SEG_HEAD:
+    COMMON_STRIDE: 4
+    CONVS_DIM: 128
+    IGNORE_VALUE: 255
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    LOSS_WEIGHT: 1.0
+    NAME: SemSegFPNHead
+    NORM: GN
+    NUM_CLASSES: 54
+  WEIGHTS: ./output/model_final.pth
+OUTPUT_DIR: ./output
+SEED: -1
+SOLVER:
+  AMP:
+    ENABLED: false
+  BASE_LR: 0.00025
+  BASE_LR_END: 0.0
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 5000
+  CLIP_GRADIENTS:
+    CLIP_TYPE: value
+    CLIP_VALUE: 1.0
+    ENABLED: false
+    NORM_TYPE: 2.0
+  GAMMA: 0.1
+  IMS_PER_BATCH: 2
+  LR_SCHEDULER_NAME: WarmupMultiStepLR
+  MAX_ITER: 3000
+  MOMENTUM: 0.9
+  NESTEROV: false
+  NUM_DECAYS: 3
+  REFERENCE_WORLD_SIZE: 0
+  RESCALE_INTERVAL: false
+  STEPS: []
+  WARMUP_FACTOR: 0.001
+  WARMUP_ITERS: 1000
+  WARMUP_METHOD: linear
+  WEIGHT_DECAY: 0.0001
+  WEIGHT_DECAY_BIAS: null
+  WEIGHT_DECAY_NORM: 0.0
+TEST:
+  AUG:
+    ENABLED: false
+    FLIP: true
+    MAX_SIZE: 4000
+    MIN_SIZES:
+    - 400
+    - 500
+    - 600
+    - 700
+    - 800
+    - 900
+    - 1000
+    - 1100
+    - 1200
+  DETECTIONS_PER_IMAGE: 100
+  EVAL_PERIOD: 0
+  EXPECTED_RESULTS: []
+  KEYPOINT_OKS_SIGMAS: []
+  PRECISE_BN:
+    ENABLED: false
+    NUM_ITER: 200
+VERSION: 2
+VIS_PERIOD: 0

tree_model_weights/tree_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552742a48b35b5d30104379da031963eb696758794d6c23c36b24dd35c32cc8b
+size 503106240