Why after inference,it change Orientation?

input image
image
A8241AFE-D3CA-4134-8D3E-76BD75826374

after inference


Which network did you train? Please share training spec as well.

random_seed: 42
yolov4_config {
big_anchor_shape: “[(43.65, 201.97),(106.76, 252.52),(221.80, 367.94)]”
mid_anchor_shape: “[(53.48, 34.84),(28.95, 72.96),(82.08, 92.94)]”
small_anchor_shape: “[(6.99, 6.63),(12.70, 13.55),(23.72, 23.07)]”
box_matching_iou: 0.25
matching_neutral_box_iou: 0.5
arch: “resnet”
nlayers: 50
arch_conv_blocks: 2
loss_loc_weight: 0.8
loss_neg_obj_weights: 100.0
loss_class_weights: 0.5
label_smoothing: 0.0
big_grid_xy_extend: 0.05
mid_grid_xy_extend: 0.1
small_grid_xy_extend: 0.2
freeze_bn: false
#freeze_blocks: 0
force_relu: false
}
training_config {
batch_size_per_gpu: 8
num_epochs: 80
enable_qat: false
checkpoint_interval: 10
learning_rate {
soft_start_cosine_annealing_schedule {
min_learning_rate: 1e-7
max_learning_rate: 1e-4
soft_start: 0.3
}
}
regularizer {
type: L1
weight: 3e-5
}
optimizer {
adam {
epsilon: 1e-7
beta1: 0.9
beta2: 0.999
amsgrad: false
}
}
pretrain_model_path: “/workspace/tao-experiments/yolo_v4/pretrained_resnet50/pretrained_object_detection_vresnet50/resnet_50.hdf5”
}
eval_config {
average_precision_mode: SAMPLE
batch_size: 8
matching_iou_threshold: 0.5
}
nms_config {
confidence_threshold: 0.001
clustering_iou_threshold: 0.5
force_on_cpu: true
top_k: 200
}
augmentation_config {
hue: 0.1
saturation: 1.5
exposure:1.5
vertical_flip:0
horizontal_flip: 0.5
jitter: 0.3
output_width: 608
output_height: 608
output_channel: 3
randomize_input_shape_period: 0
mosaic_prob: 0.5
mosaic_min_ratio:0.2
}
dataset_config {
data_sources: {
tfrecords_path: “/workspace/tao-experiments/data/training/tfrecords/train*”
image_directory_path: “/workspace/tao-experiments/data/training”
}
include_difficult_in_training: true
image_extension: “jpg”
target_class_mapping {
key: “badge”
value: “badge”
}
target_class_mapping {
key: “person”
value: “person”
}
target_class_mapping {
key: “glove”
value: “glove”
}
target_class_mapping {
key: “wrongglove”
value: “wrongglove”
}
target_class_mapping {
key: “operatingbar”
value: “operatingbar”
}
target_class_mapping {
key: “powerchecker”
value: “powerchecker”
}
validation_data_sources: {
tfrecords_path: “/workspace/tao-experiments/data/val/tfrecords/val*”
image_directory_path: “/workspace/tao-experiments/data/val”
}
}

Other users do not meet your result. So, it is strange.
How did you get the inference result? With yolo_v4 inference xxx ?

yeah,run tao yolo_v4 inference

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

Please share your full command. Did you run inference against etlt model or trt engine?