improve model

.gitattributes

@@ -41,3 +41,6 @@ assets/imgs/907px-Vincent_van_Gogh_-_De_slaapkamer_-_Google_Art_Project.jpg filt
 assets/imgs/AdobeStock_286429091.jpeg filter=lfs diff=lfs merge=lfs -text
 assets/imgs/AdobeStock_331358641.jpeg filter=lfs diff=lfs merge=lfs -text
 assets/imgs/ filter=lfs diff=lfs merge=lfs -text
+assets/imgs/epic.png filter=lfs diff=lfs merge=lfs -text
+models/paramnet_360cities_edina_rpfpp.pth filter=lfs diff=lfs merge=lfs -text
+models/paramnet_360cities_edina_rpf.pth filter=lfs diff=lfs merge=lfs -text

app.py

@@ -1,8 +1,12 @@
 
 import os
+os.system(f"pip install -U openmim")
+os.system(f"mim install mmcv")
 os.system(f"pip install git+https://github.com/jinlinyi/PerspectiveFields.git@dev#egg=perspective2d")
 
 
+
+
 import gradio as gr
 import cv2
 import copy
@@ -136,6 +140,21 @@ print(examples)
 
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 model_zoo = {
+
+    'Paramnet-360Cities-edina-centered': {
+        'weights': ['https://www.dropbox.com/s/z2dja70bgy007su/paramnet_360cities_edina_rpf.pth'],
+        'opts': ['MODEL.WEIGHTS', 'models/paramnet_360cities_edina_rpf.pth', 'MODEL.DEVICE', device,],
+        'config_file': 'models/paramnet_360cities_edina_rpf.yaml',
+        'param': True,
+    },
+
+   'Paramnet-360Cities-edina-uncentered': {
+        'weights': ['https://www.dropbox.com/s/nt29e1pi83mm1va/paramnet_360cities_edina_rpfpp.pth'],
+        'opts': ['MODEL.WEIGHTS', 'models/paramnet_360cities_edina_rpfpp.pth', 'MODEL.DEVICE', device,],
+        'config_file': 'models/paramnet_360cities_edina_rpfpp.yaml',
+        'param': True,
+    },
+
     'PersNet-360Cities': {
         'weights': ['https://www.dropbox.com/s/czqrepqe7x70b7y/cvpr2023.pth'],
         'opts': ['MODEL.WEIGHTS', 'models/cvpr2023.pth', 'MODEL.DEVICE', device,],

models/paramnet_360cities_edina_rpf.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58fe0285fe5d4592aec77e9ef57ac94273deb79bcb99f27d08bae68a2d1efc4a
+size 837147876

models/paramnet_360cities_edina_rpf.yaml

@@ -0,0 +1,396 @@
+CUDNN_BENCHMARK: false
+DATALOADER:
+  ASPECT_RATIO_GROUPING: true
+  AUGMENTATION: true
+  AUGMENTATION_FUN: uniform_vfov_crop_resize
+  AUGMENTATION_TYPE: geometry
+  FILTER_EMPTY_ANNOTATIONS: true
+  NO_GEOMETRY_AUG: false
+  NUM_WORKERS: 8
+  REPEAT_THRESHOLD: 0.0
+  RESIZE:
+  - 320
+  - 320
+  SAMPLER_TRAIN: TrainingSampler
+DATASETS:
+  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
+  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
+  PROPOSAL_FILES_TEST: []
+  PROPOSAL_FILES_TRAIN: []
+  TEST:
+  - edina_test_crop_vfov
+  TRAIN:
+  - edina_train
+  - cities360_train
+DEBUG_ON: false
+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:
+  - 800
+  MIN_SIZE_TRAIN_SAMPLING: choice
+  ONLINE_CROP: false
+  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_mit_backbone
+  CENTER_ON: false
+  DEVICE: cuda
+  FPN:
+    FUSE_TYPE: sum
+    IN_FEATURES: []
+    NORM: ''
+    OUT_CHANNELS: 256
+  FPN_CENTER_HEAD:
+    COMMON_STRIDE: 4
+    CONVS_DIM: 128
+    IGNORE_VALUE: 360
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    LOSS_WEIGHT: 1.0
+    NAME: CenterFPNHead
+    NORM: GN
+    NUM_CLASSES: 30
+  FPN_GRAVITY_HEAD:
+    COMMON_STRIDE: 4
+    CONVS_DIM: 128
+    IGNORE_VALUE: 360
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    LOSS_WEIGHT: 1.0
+    NAME: GravityFPNHead
+    NORM: GN
+    NUM_CLASSES: 361
+  FPN_HEADS:
+    NAME: StandardFPNHeads
+  FPN_LATITUDE_HEAD:
+    COMMON_STRIDE: 4
+    CONVS_DIM: 128
+    IGNORE_VALUE: -1
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    LOSS_WEIGHT: 1.0
+    NAME: LatitudeFPNHead
+    NORM: GN
+    NUM_CLASSES: 9
+  FREEZE: []
+  GRAVITY_DECODER:
+    IGNORE_VALUE: 72
+    LOSS_TYPE: regression
+    LOSS_WEIGHT: 1.0
+    NAME: GravityDecoder
+    NUM_CLASSES: 73
+  GRAVITY_ON: true
+  HEIGHT_DECODER:
+    LOSS_WEIGHT: 1.0
+    NAME: HeightDecoder
+  HEIGHT_ON: false
+  KEYPOINT_ON: false
+  LATITUDE_DECODER:
+    IGNORE_VALUE: -1
+    LOSS_TYPE: regression
+    LOSS_WEIGHT: 1.0
+    NAME: LatitudeDecoder
+    NUM_CLASSES: 1
+  LATITUDE_ON: true
+  LOAD_PROPOSALS: false
+  MASK_ON: false
+  META_ARCHITECTURE: PersFormer
+  PANOPTIC_FPN:
+    COMBINE:
+      ENABLED: true
+      INSTANCES_CONFIDENCE_THRESH: 0.5
+      OVERLAP_THRESH: 0.5
+      STUFF_AREA_LIMIT: 4096
+    INSTANCE_LOSS_WEIGHT: 1.0
+  PARAM_DECODER:
+    DEBUG_LAT: false
+    DEBUG_UP: false
+    INPUT_SIZE: 64
+    LOSS_TYPE: regression
+    LOSS_WEIGHT: 1.0
+    NAME: ParamNet
+    PREDICT_PARAMS:
+    - roll
+    - pitch
+    - vfov
+    SYNTHETIC_PRETRAIN: false
+  PERSFORMER_HEADS:
+    NAME: StandardPersformerHeads
+  PIXEL_MEAN:
+  - 103.53
+  - 116.28
+  - 123.675
+  PIXEL_STD:
+  - 1.0
+  - 1.0
+  - 1.0
+  PROPOSAL_GENERATOR:
+    MIN_SIZE: 0
+    NAME: RPN
+  RECOVER_PP: false
+  RECOVER_RPF: true
+  RESNETS:
+    DEFORM_MODULATED: false
+    DEFORM_NUM_GROUPS: 1
+    DEFORM_ON_PER_STAGE:
+    - false
+    - false
+    - false
+    - false
+    DEPTH: 50
+    NORM: FrozenBN
+    NUM_GROUPS: 1
+    OUT_FEATURES:
+    - res4
+    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: ''
+    NORM: ''
+    NUM_CONV: 0
+    NUM_FC: 0
+    POOLER_RESOLUTION: 14
+    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:
+    - res4
+    IOU_LABELS:
+    - 0
+    - 1
+    IOU_THRESHOLDS:
+    - 0.5
+    NAME: Res5ROIHeads
+    NMS_THRESH_TEST: 0.5
+    NUM_CLASSES: 80
+    POSITIVE_FRACTION: 0.25
+    PROPOSAL_APPEND_GT: true
+    SCORE_THRESH_TEST: 0.05
+  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: 0
+    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:
+    - res4
+    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: 2000
+    PRE_NMS_TOPK_TEST: 6000
+    PRE_NMS_TOPK_TRAIN: 12000
+    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: ./init_model_weights/cvpr2023.pth
+OUTPUT_DIR: /home/msticha/exps/e01_edina
+OVERFIT_ON: false
+SEED: -1
+SOLVER:
+  AMP:
+    ENABLED: false
+  BASE_LR: 0.01
+  BASE_LR_END: 0.0
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 500
+  CLIP_GRADIENTS:
+    CLIP_TYPE: value
+    CLIP_VALUE: 1.0
+    ENABLED: false
+    NORM_TYPE: 2.0
+  GAMMA: 0.1
+  IMS_PER_BATCH: 32
+  LR_SCHEDULER_NAME: WarmupMultiStepLR
+  MAX_ITER: 90000
+  MOMENTUM: 0.9
+  NESTEROV: false
+  NUM_DECAYS: 3
+  REFERENCE_WORLD_SIZE: 0
+  RESCALE_INTERVAL: false
+  STEPS:
+  - 40000
+  - 60000
+  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: 500
+  EXPECTED_RESULTS: []
+  KEYPOINT_OKS_SIGMAS: []
+  PRECISE_BN:
+    ENABLED: false
+    NUM_ITER: 200
+VERSION: 2
+VIS_PERIOD: 500

models/paramnet_360cities_edina_rpfpp.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5220df6d9d89380d490bb9a3e4a162a8a5ca8eeb8610510173410076719fca67
+size 837147876

models/paramnet_360cities_edina_rpfpp.yaml

@@ -0,0 +1,397 @@
+CUDNN_BENCHMARK: false
+DATALOADER:
+  ASPECT_RATIO_GROUPING: true
+  AUGMENTATION: true
+  AUGMENTATION_FUN: uniform_vfov_crop_resize
+  AUGMENTATION_TYPE: geometry
+  FILTER_EMPTY_ANNOTATIONS: true
+  NO_GEOMETRY_AUG: false
+  NUM_WORKERS: 8
+  REPEAT_THRESHOLD: 0.0
+  RESIZE:
+  - 320
+  - 320
+  SAMPLER_TRAIN: TrainingSampler
+DATASETS:
+  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
+  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
+  PROPOSAL_FILES_TEST: []
+  PROPOSAL_FILES_TRAIN: []
+  TEST:
+  - edina_test_crop_uniform
+  TRAIN:
+  - edina_train
+  - cities360_train
+DEBUG_ON: false
+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:
+  - 800
+  MIN_SIZE_TRAIN_SAMPLING: choice
+  ONLINE_CROP: false
+  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_mit_backbone
+  CENTER_ON: false
+  DEVICE: cuda
+  FPN:
+    FUSE_TYPE: sum
+    IN_FEATURES: []
+    NORM: ''
+    OUT_CHANNELS: 256
+  FPN_CENTER_HEAD:
+    COMMON_STRIDE: 4
+    CONVS_DIM: 128
+    IGNORE_VALUE: 360
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    LOSS_WEIGHT: 1.0
+    NAME: CenterFPNHead
+    NORM: GN
+    NUM_CLASSES: 30
+  FPN_GRAVITY_HEAD:
+    COMMON_STRIDE: 4
+    CONVS_DIM: 128
+    IGNORE_VALUE: 360
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    LOSS_WEIGHT: 1.0
+    NAME: GravityFPNHead
+    NORM: GN
+    NUM_CLASSES: 361
+  FPN_HEADS:
+    NAME: StandardFPNHeads
+  FPN_LATITUDE_HEAD:
+    COMMON_STRIDE: 4
+    CONVS_DIM: 128
+    IGNORE_VALUE: -1
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    LOSS_WEIGHT: 1.0
+    NAME: LatitudeFPNHead
+    NORM: GN
+    NUM_CLASSES: 9
+  FREEZE: []
+  GRAVITY_DECODER:
+    IGNORE_VALUE: 72
+    LOSS_TYPE: regression
+    LOSS_WEIGHT: 1.0
+    NAME: GravityDecoder
+    NUM_CLASSES: 73
+  GRAVITY_ON: true
+  HEIGHT_DECODER:
+    LOSS_WEIGHT: 1.0
+    NAME: HeightDecoder
+  HEIGHT_ON: false
+  KEYPOINT_ON: false
+  LATITUDE_DECODER:
+    IGNORE_VALUE: -1
+    LOSS_TYPE: regression
+    LOSS_WEIGHT: 1.0
+    NAME: LatitudeDecoder
+    NUM_CLASSES: 1
+  LATITUDE_ON: true
+  LOAD_PROPOSALS: false
+  MASK_ON: false
+  META_ARCHITECTURE: PersFormer
+  PANOPTIC_FPN:
+    COMBINE:
+      ENABLED: true
+      INSTANCES_CONFIDENCE_THRESH: 0.5
+      OVERLAP_THRESH: 0.5
+      STUFF_AREA_LIMIT: 4096
+    INSTANCE_LOSS_WEIGHT: 1.0
+  PARAM_DECODER:
+    DEBUG_LAT: false
+    DEBUG_UP: false
+    INPUT_SIZE: 64
+    LOSS_TYPE: regression
+    LOSS_WEIGHT: 1.0
+    NAME: ParamNetConvNextRegress
+    PREDICT_PARAMS:
+    - roll
+    - pitch
+    - general_vfov
+    - rel_cx
+    - rel_cy
+    SYNTHETIC_PRETRAIN: false
+  PERSFORMER_HEADS:
+    NAME: StandardPersformerHeads
+  PIXEL_MEAN:
+  - 103.53
+  - 116.28
+  - 123.675
+  PIXEL_STD:
+  - 1.0
+  - 1.0
+  - 1.0
+  PROPOSAL_GENERATOR:
+    MIN_SIZE: 0
+    NAME: RPN
+  RECOVER_PP: true
+  RECOVER_RPF: true
+  RESNETS:
+    DEFORM_MODULATED: false
+    DEFORM_NUM_GROUPS: 1
+    DEFORM_ON_PER_STAGE:
+    - false
+    - false
+    - false
+    - false
+    DEPTH: 50
+    NORM: FrozenBN
+    NUM_GROUPS: 1
+    OUT_FEATURES:
+    - res4
+    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: ''
+    NORM: ''
+    NUM_CONV: 0
+    NUM_FC: 0
+    POOLER_RESOLUTION: 14
+    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:
+    - res4
+    IOU_LABELS:
+    - 0
+    - 1
+    IOU_THRESHOLDS:
+    - 0.5
+    NAME: Res5ROIHeads
+    NMS_THRESH_TEST: 0.5
+    NUM_CLASSES: 80
+    POSITIVE_FRACTION: 0.25
+    PROPOSAL_APPEND_GT: true
+    SCORE_THRESH_TEST: 0.05
+  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: 0
+    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:
+    - res4
+    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: 2000
+    PRE_NMS_TOPK_TEST: 6000
+    PRE_NMS_TOPK_TRAIN: 12000
+    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: ./init_model_weights/cvpr2023.pth
+OUTPUT_DIR: /home/msticha/exps/e01_edina_pp
+OVERFIT_ON: false
+SEED: -1
+SOLVER:
+  AMP:
+    ENABLED: false
+  BASE_LR: 0.005
+  BASE_LR_END: 0.0
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 500
+  CLIP_GRADIENTS:
+    CLIP_TYPE: value
+    CLIP_VALUE: 1.0
+    ENABLED: false
+    NORM_TYPE: 2.0
+  GAMMA: 0.1
+  IMS_PER_BATCH: 32
+  LR_SCHEDULER_NAME: WarmupCosineLR
+  MAX_ITER: 90000
+  MOMENTUM: 0.9
+  NESTEROV: false
+  NUM_DECAYS: 3
+  REFERENCE_WORLD_SIZE: 0
+  RESCALE_INTERVAL: false
+  STEPS:
+  - 30000
+  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: 500
+  EXPECTED_RESULTS: []
+  KEYPOINT_OKS_SIGMAS: []
+  PRECISE_BN:
+    ENABLED: false
+    NUM_ITER: 200
+VERSION: 2
+VIS_PERIOD: 500

requirements.txt

@@ -1,3 +1,3 @@
 --extra-index-url https://download.pytorch.org/whl/cu113
-torch==1.10.0+cu113
-torchvision==0.11.1+cu113
+torch==1.11.0+cu113
+torchvision==0.12.0+cu113