Problem in detecting of all objects in pictures using Faster R-CNN - tensorflow

Question

I am trying to detect the tree species in an images using Faster R-CNN Inception ResNet V2 1024x1024. Problem is that the model cannot detect all the trees in an image. setting the value of first_stage_max_proposals to 1500, only slightly helps. Also adjusting the values of grid_anchor_generator, max_detections_per_class and max_total_detections has not significant effect. Can anyone help me ? Which parameters should I adjust ?
Here is my model config file and one image where model missed most of the trees
enter image description here
# Faster R-CNN with Inception Resnet v2 (no atrous)
# Sync-trained on COCO (with 8 GPUs) with batch size 16 (800x1333 resolution)
# Initialized from Imagenet classification checkpoint
# TF2-Compatible, *Not* TPU-Compatible
#
# Achieves 39.6 mAP on COCO
model {
faster_rcnn {
num_classes: 7
image_resizer {
fixed_shape_resizer {
height: 867
width: 867
}
}
feature_extractor {
type: 'faster_rcnn_inception_resnet_v2_keras'
}
first_stage_anchor_generator {
grid_anchor_generator {
scales:[0.1,0.4,0.45,0.5,0.6,0.7,0.8,0.90,1.0,
1.2,1.25,1.3,1.35,1.4,1.45,1.5,1.6,1.8,1.90,1.95,2.0,
2.2,2.25,2.3,2.35,2.4,2.45,2.5,2.6,2.8,2.90,2.95,3.0,
3.2,3.25,3.3,3.35,3.4,3.45,3.5,3.6,3.8,3.90,3.95,4.0,
4.2,4.25,4.3,4.35,4.4,4.45,4.5,4.6,4.8,4.90,4.95,5.0,
5.2,5.25,5.3,5.35,5.4,5.45,5.5,5.6,5.8,5.90,5.95,6.0,
6.2,6.25,6.3,6.35,6.4,6.45,6.5,6.6,6.8,6.90,6.95,7.0,
7.2,7.25,7.3,7.35,7.4,7.45,7.5,7.6,7.8,7.90,7.95,8.0,
8.2,8.25,8.3,8.35,8.4,8.45,8.5,8.55,8.6,8.8,8.90,8.95,9.0
]
aspect_ratios: [0.2,0.5,0.75,1.0,1.25,1.3,1.35,1.4,1.45,1.5,1.6,1.7,1.75,1.8,1.9,1.95,2.0,2.25,2.5,2.75,3.0,3.5,4.0]
height_stride: 16
width_stride: 16
}
}
first_stage_box_predictor_conv_hyperparams {
op: CONV
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
truncated_normal_initializer {
stddev: 0.01
}
}
}
first_stage_nms_score_threshold: 0.0
first_stage_nms_iou_threshold: 0.4
first_stage_max_proposals: 300
first_stage_localization_loss_weight: 2.0
first_stage_objectness_loss_weight: 1.0
initial_crop_size: 17
maxpool_kernel_size: 1
maxpool_stride: 1
second_stage_box_predictor {
mask_rcnn_box_predictor {
use_dropout: false
dropout_keep_probability: 1.0
fc_hyperparams {
op: FC
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
variance_scaling_initializer {
factor: 1.0
uniform: true
mode: FAN_AVG
}
}
}
}
}
second_stage_post_processing {
batch_non_max_suppression {
score_threshold: 0.0
iou_threshold: 0.25
max_detections_per_class: 100
max_total_detections: 700
}
score_converter: SOFTMAX
}
second_stage_localization_loss_weight: 2.0
second_stage_classification_loss_weight: 1.0
}
}
train_config: {
batch_size: 2
num_steps: 25000
optimizer {
momentum_optimizer: {
learning_rate: {
cosine_decay_learning_rate {
learning_rate_base: 0.0008
total_steps: 25000
warmup_learning_rate: 0.00001
warmup_steps: 2000
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint_version: V2
fine_tune_checkpoint: "faster_rcnn_inception_resnet_v2_1024x1024_coco17_tpu-8/checkpoint/ckpt-0"
fine_tune_checkpoint_type: "detection"
}
train_input_reader: {
label_map_path: "images/labelmap.pbtxt"
tf_record_input_reader {
input_path: "train.record"
}
}
eval_config: {
metrics_set: "coco_detection_metrics"
use_moving_averages: false
batch_size: 1;
}
eval_input_reader: {
label_map_path: "images/labelmap.pbtxt"
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: "test.record"
}
}