I think the last dimension of your input tensor is the channel dimension.
Which kind of model are you using? uff, tlt (tensorflow), caffe or pytorch?
You can update following parameters if you are using uff:
infer-dims=288;288;3
# 0: NCHW 1: NHWC 2: NC
uff-input-order=1
You’d better add a transpose layer into your model to transpose input from (3, 288, 288) into (288, 288, 3) before deploying the model onto DeepStream 5.0 if you are other models like tensorflow or pytorch