I want to run vta on a custom zynq platform, and my zynq chip is
**xczu2eg-sfva625-1-e**. I rebuild pynq image from scratch for this board, and
it can work normally.
I use ultra96's vta config file and just change the fpga_device in
vta-hw/config/pkg_config.py file. But my vta seems very slow. The log in host
is:
> download failed due to URLError(ConnectionRefusedError(111, 'Connection
> refused')), retrying, 2 attempts left
download failed due to URLError(ConnectionRefusedError(111, 'Connection
refused')), retrying, 1 attempt left
WARNING:root:Failed to download tophub package for vta: <urlopen error [Errno
111] Connection refused>
Conv2DWorkload(batch=1, height=56, width=56, in_filter=64, out_filter=64,
hkernel=3, wkernel=3, hpad=1, wpad=1, hstride=1, wstride=1)
WARNING:autotvm:Cannot find config for target=ext_dev -keys=vta,cpu -device=vta
-model=ultra96_1x16_i8w8a32_15_15_18_17, workload=('conv2d_packed.vta',
('TENSOR', (1, 4, 56, 56, 1, 16), 'int8'), ('TENSOR', (4, 4, 3, 3, 16, 16),
'int8'), (1, 1), (1, 1, 1, 1), (1, 1), 'NCHW1n16c', 'int32'). A fallback
configuration is used, which may bring great performance regression.
VTA CONV2D TEST FAILED: Time cost = 0.0912439 sec/op, 2.53399 GOPS
Conv2DWorkload(batch=1, height=56, width=56, in_filter=64, out_filter=128,
hkernel=3, wkernel=3, hpad=1, wpad=1, hstride=2, wstride=2)
WARNING:autotvm:Cannot find config for target=ext_dev -keys=vta,cpu -device=vta
-model=ultra96_1x16_i8w8a32_15_15_18_17, workload=('conv2d_packed.vta',
('TENSOR', (1, 4, 56, 56, 1, 16), 'int8'), ('TENSOR', (8, 4, 3, 3, 16, 16),
'int8'), (2, 2), (1, 1, 1, 1), (1, 1), 'NCHW1n16c', 'int32'). A fallback
configuration is used, which may bring great performance regression.
VTA CONV2D TEST FAILED: Time cost = 0.0457273 sec/op, 2.52815 GOPS
Conv2DWorkload(batch=1, height=56, width=56, in_filter=64, out_filter=128,
hkernel=1, wkernel=1, hpad=0, wpad=0, hstride=2, wstride=2)
WARNING:autotvm:Cannot find config for target=ext_dev -keys=vta,cpu -device=vta
-model=ultra96_1x16_i8w8a32_15_15_18_17, workload=('conv2d_packed.vta',
('TENSOR', (1, 4, 56, 56, 1, 16), 'int8'), ('TENSOR', (8, 4, 1, 1, 16, 16),
'int8'), (2, 2), (0, 0, 0, 0), (1, 1), 'NCHW1n16c', 'int32'). A fallback
configuration is used, which may bring great performance regression.
VTA CONV2D TEST PASSED: Time cost = 0.0274279 sec/op, 0.46832 GOPS
Conv2DWorkload(batch=1, height=28, width=28, in_filter=128, out_filter=128,
hkernel=3, wkernel=3, hpad=1, wpad=1, hstride=1, wstride=1)
WARNING:autotvm:Cannot find config for target=ext_dev -keys=vta,cpu -device=vta
-model=ultra96_1x16_i8w8a32_15_15_18_17, workload=('conv2d_packed.vta',
('TENSOR', (1, 8, 28, 28, 1, 16), 'int8'), ('TENSOR', (8, 8, 3, 3, 16, 16),
'int8'), (1, 1), (1, 1, 1, 1), (1, 1), 'NCHW1n16c', 'int32'). A fallback
configuration is used, which may bring great performance regression.
It was so slow and even stuck at running a conv2d computation.
Do I need to change my config or something to make vta work normally on my
board?
---
[Visit
Topic](https://discuss.tvm.ai/t/vta-on-custom-board-a-warning-about-autotvm/7693/1)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai/email/unsubscribe/f37b9c5790d77d8467ff06248bd5d22bc5c1d5e9ab7630a7cc4facbba306b44f).
