Jetson-Nano-image icon indicating copy to clipboard operation
Jetson-Nano-image copied to clipboard

Published 20 hours ago • verified publisher icon Qengineering

Tensorflow using run error

Open mgsmustafa opened this issue 3 years ago • 1 comments

I’m trying to run a TensorRT Tiny YOLOv4 model on a 4GB Nano development board.

I’m running the Nano headless, so should have enough memory :

021-12-14 07:54:04.568367: F tensorflow/core/kernels/image/resize_bilinear_op_gpu.cu.cc:447] Non-OK-status: GpuLaunchKernel(kernel, config.block_count, config.thread_per_block, 0, d.stream(), config.virtual_thread_count, images.data(), height_scale, width_scale, batch, in_height, in_width, channels, out_height, out_width, output.data()) status: Internal: too many resources requested for launch Fatal Python error: Aborted

mgsmustafa avatar Dec 14 '21 07:12 mgsmustafa

Dear @mgsmustafa,

I'm sorry. I can't help you with this issue. You using TensorRT and Python, both are original NVIDIA installations. You're better of at the NVIVIA forum.

Qengineering avatar Dec 14 '21 09:12 Qengineering