18242360613

我检查了ppq.parser.tensorRT.py 196行处的代码input_shapes已经被设置为[32,3,640,640],并且在247行for循环后添加了下面的代码，设置了proile，min.opt，max的尺寸都是[32,3,640,640]。 min, opt, max = input_shapes[inp.name] profile.set_shape_input(inp.name, min, opt, max) config.add_optimization_profile(profile) trt_engine = builder.build_engine(network, config) 但是还是会出现上面这个问题。 后来我修改了04_Benchmark.py中的代码，将batch_size设置成了1,将inputshape设置成了[32,3,640,640],代码也可以运行，相对于fp32的也实现了快10倍的加速（基于3090显卡）。 ENGINE_PATH = '/home/cp/git/ppq/model/yolov6s_ppq_int8_b32.engine' BATCH_SIZE = 1 INPUT_SHAPE = [32, 3, 640, 640]...

hi @fabianschenk , In my case, "0. jpg" is set as a fixed image and "20. jpg" is set as a moving image. When these two images were taken, there...