ベスマ・ゲスミ

Convert output tensor layer from 5 dims to 4 dims

1

Hi, Is there any way to reduce the output layer dimension? Any explanation of what these 5 parameters are after inference: Output Shape (1, 3, 20, 20, 10)

Hi, Is there any way to reduce the output layer dimension? Any explanation of what these 5 parameters are after inference: Output Shape (1, 3, 20, 20, 10)

Hello I have used the same XML and bin file of the project but I didn't found the same result. Does anyone here can help me to solve this problem....

custom model architecture

1

hello I want to use this model with my python architecture, do I need to rewrite my model architecture in c++ file? or modify keras_model.cc?

DeepSORT with custom YOLOv5 model

11

Hi, could I use the DeepSORT model with a custom YOLOv5 model? Because I faced some error when I tried it. Thanks

Wrong detection with custom YOLOv5 RKNN unlike the published YOLOv5s model that works fine

2

Hi all, I manage to get my custom RKNNs running on RK3588, but when I added the post-processing step, I got overlapped BBoxes on the whole output image, unlike the...

Yolov5 with openvino using custom model

1

Hello I'm trying to use yolov5 custom pre-trained model with openvino, I followed your tutorial but when I trained the demo the objects in the image didn't detect! do you...

IS there any effort in handling some 3D operations since it is required for some spatiotemporal models.

Hey ! I have faced an issue in exporting model with shape 5D (for time series purpose) Error: E build: The height_width of r_shape [24, 64, 64] is invalid! Does...