update config, fix small bugs for testing

pcdet/datasets/processor/data_processor.py

@@ -70,9 +70,6 @@ class DataProcessor(object):
         if num_points == -1:
             return data_dict
 
-        if config.FIX_SEED[self.mode]:
-            np.random.seed(512)
-
         points = data_dict['points']
         if num_points < len(points):
             pts_depth = np.linalg.norm(points[:, 0:3], axis=1)

pcdet/utils/common_utils.py

@@ -133,6 +133,7 @@ def init_dist_slurm(tcp_port, local_rank, backend='nccl'):
     dist.init_process_group(backend=backend)
 
     total_gpus = dist.get_world_size()
+    rank = dist.get_rank()
     return total_gpus, rank
 
 

tools/cfgs/kitti_models/pointrcnn.yaml

@@ -12,10 +12,6 @@ DATA_CONFIG:
                 'train': 16384,
                 'test': 16384
             }
-            FIX_SEED: {
-                'train': False,
-                'test': True
-            }
 
         -   NAME: shuffle_points
             SHUFFLE_ENABLED: {

tools/cfgs/kitti_models/pointrcnn_iou.yaml

+CLASS_NAMES: ['Car', 'Pedestrian', 'Cyclist']
+
+DATA_CONFIG:
+    _BASE_CONFIG_: cfgs/dataset_configs/kitti_dataset.yaml
+
+    DATA_PROCESSOR:
+        -   NAME: mask_points_and_boxes_outside_range
+            REMOVE_OUTSIDE_BOXES: True
+
+        -   NAME: sample_points
+            NUM_POINTS: {
+                'train': 16384,
+                'test': 16384
+            }
+
+        -   NAME: shuffle_points
+            SHUFFLE_ENABLED: {
+                'train': True,
+                'test': False
+            }
+
+MODEL:
+    NAME: PointRCNN
+
+    BACKBONE_3D:
+        NAME: PointNet2MSG
+        SA_CONFIG:
+            NPOINTS: [4096, 1024, 256, 64]
+            RADIUS: [[0.1, 0.5], [0.5, 1.0], [1.0, 2.0], [2.0, 4.0]]
+            NSAMPLE: [[16, 32], [16, 32], [16, 32], [16, 32]]
+            MLPS: [[[16, 16, 32], [32, 32, 64]],
+                   [[64, 64, 128], [64, 96, 128]],
+                   [[128, 196, 256], [128, 196, 256]],
+                   [[256, 256, 512], [256, 384, 512]]]
+        FP_MLPS: [[128, 128], [256, 256], [512, 512], [512, 512]]
+
+    POINT_HEAD:
+        NAME: PointHeadBox
+        CLS_FC: [256, 256]
+        REG_FC: [256, 256]
+        CLASS_AGNOSTIC: False
+        USE_POINT_FEATURES_BEFORE_FUSION: False
+        TARGET_CONFIG:
+            GT_EXTRA_WIDTH: [0.2, 0.2, 0.2]
+            BOX_CODER: PointResidualCoder
+            BOX_CODER_CONFIG: {
+                'use_mean_size': True,
+                'mean_size': [
+                    [3.9, 1.6, 1.56],
+                    [0.8, 0.6, 1.73],
+                    [1.76, 0.6, 1.73]
+                ]
+            }
+
+        LOSS_CONFIG:
+            LOSS_REG: WeightedSmoothL1Loss
+            LOSS_WEIGHTS: {
+                'point_cls_weight': 1.0,
+                'point_box_weight': 1.0,
+                'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
+            }
+
+    ROI_HEAD:
+        NAME: PointRCNNHead
+        CLASS_AGNOSTIC: True
+
+        ROI_POINT_POOL:
+            POOL_EXTRA_WIDTH: [0.0, 0.0, 0.0]
+            NUM_SAMPLED_POINTS: 512
+            DEPTH_NORMALIZER: 70.0
+
+        XYZ_UP_LAYER: [128, 128]
+        CLS_FC: [256, 256]
+        REG_FC: [256, 256]
+        DP_RATIO: 0.0
+        USE_BN: False
+
+        SA_CONFIG:
+            NPOINTS: [128, 32, -1]
+            RADIUS: [0.2, 0.4, 100]
+            NSAMPLE: [16, 16, 16]
+            MLPS: [[128, 128, 128],
+                   [128, 128, 256],
+                   [256, 256, 512]]
+
+        NMS_CONFIG:
+            TRAIN:
+                NMS_TYPE: nms_gpu
+                MULTI_CLASSES_NMS: False
+                NMS_PRE_MAXSIZE: 9000
+                NMS_POST_MAXSIZE: 512
+                NMS_THRESH: 0.8
+            TEST:
+                NMS_TYPE: nms_gpu
+                MULTI_CLASSES_NMS: False
+                NMS_PRE_MAXSIZE: 9000
+                NMS_POST_MAXSIZE: 100
+                NMS_THRESH: 0.85
+
+        TARGET_CONFIG:
+            BOX_CODER: ResidualCoder
+            ROI_PER_IMAGE: 128
+            FG_RATIO: 0.5
+
+            SAMPLE_ROI_BY_EACH_CLASS: True
+            CLS_SCORE_TYPE: roi_iou
+
+            CLS_FG_THRESH: 0.7
+            CLS_BG_THRESH: 0.25
+            CLS_BG_THRESH_LO: 0.1
+            HARD_BG_RATIO: 0.8
+
+            REG_FG_THRESH: 0.55
+
+        LOSS_CONFIG:
+            CLS_LOSS: BinaryCrossEntropy
+            REG_LOSS: smooth-l1
+            CORNER_LOSS_REGULARIZATION: True
+            LOSS_WEIGHTS: {
+                'rcnn_cls_weight': 1.0,
+                'rcnn_reg_weight': 1.0,
+                'rcnn_corner_weight': 1.0,
+                'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
+            }
+
+    POST_PROCESSING:
+        RECALL_THRESH_LIST: [0.3, 0.5, 0.7]
+        SCORE_THRESH: 0.1
+        OUTPUT_RAW_SCORE: False
+
+        EVAL_METRIC: kitti
+
+        NMS_CONFIG:
+            MULTI_CLASSES_NMS: False
+            NMS_TYPE: nms_gpu
+            NMS_THRESH: 0.1
+            NMS_PRE_MAXSIZE: 4096
+            NMS_POST_MAXSIZE: 500
+
+
+OPTIMIZATION:
+    BATCH_SIZE_PER_GPU: 3
+    NUM_EPOCHS: 80
+
+    OPTIMIZER: adam_onecycle
+    LR: 0.01
+    WEIGHT_DECAY: 0.01
+    MOMENTUM: 0.9
+
+    MOMS: [0.95, 0.85]
+    PCT_START: 0.4
+    DIV_FACTOR: 10
+    DECAY_STEP_LIST: [35, 45]
+    LR_DECAY: 0.1
+    LR_CLIP: 0.0000001
+
+    LR_WARMUP: False
+    WARMUP_EPOCH: 1
+
+    GRAD_NORM_CLIP: 10

tools/scripts/slurm_test_mgpu.sh

@@ -9,6 +9,8 @@ PY_ARGS=${@:3}
 JOB_NAME=eval
 SRUN_ARGS=${SRUN_ARGS:-""}
 
+PORT=$(( ( RANDOM % 10000 )  + 10000 ))
+
 srun -p ${PARTITION} \
     --job-name=${JOB_NAME} \
     --gres=gpu:${GPUS_PER_NODE} \
@@ -16,5 +18,5 @@ srun -p ${PARTITION} \
     --ntasks-per-node=${GPUS_PER_NODE} \
     --kill-on-bad-exit=1 \
     ${SRUN_ARGS} \
-    python -u test.py --launcher slurm ${PY_ARGS}
+    python -u test.py --launcher slurm ${PY_ARGS} --tcp_port $PORT
 

tools/scripts/slurm_train.sh

@@ -11,6 +11,7 @@ GPUS_PER_NODE=${GPUS_PER_NODE:-8}
 CPUS_PER_TASK=${CPUS_PER_TASK:-5}
 SRUN_ARGS=${SRUN_ARGS:-""}
 
+PORT=$(( ( RANDOM % 10000 )  + 10000 ))
 
 srun -p ${PARTITION} \
     --job-name=${JOB_NAME} \
@@ -20,4 +21,4 @@ srun -p ${PARTITION} \
     --cpus-per-task=${CPUS_PER_TASK} \
     --kill-on-bad-exit=1 \
     ${SRUN_ARGS} \
-    python -u train.py --launcher slurm ${PY_ARGS}
+    python -u train.py --launcher slurm ${PY_ARGS} --tcp_port $PORT

tools/test.py

 import os
+import numpy as np
 import torch
 from tensorboardX import SummaryWriter
 import time
@@ -40,6 +41,9 @@ def parse_config():
     cfg_from_yaml_file(args.cfg_file, cfg)
     cfg.TAG = Path(args.cfg_file).stem
     cfg.EXP_GROUP_PATH = '/'.join(args.cfg_file.split('/')[1:-1])  # remove 'cfgs' and 'xxxx.yaml'
+
+    np.random.seed(1024)
+
     if args.set_cfgs is not None:
         cfg_from_list(args.set_cfgs, cfg)