Error during inference #2
Description
Hello! Your work looks cool and I wanted to try it out - I downloaded weights, set the conda environment, started API service, but after pushing my and your test images I kept getting this:
{"detail":"An error occurred during inference: conv2d() received an invalid combination of arguments - got (list, Parameter, NoneType, tuple, tuple, tuple, int), but expected one of:\n * (Tensor input, Tensor weight, Tensor bias = None, tuple of ints stride = 1, tuple of ints padding = 0, tuple of ints dilation = 1, int groups = 1)\n didn't match because some of the arguments have invalid types: (\u001b[31;1mlist of [Tensor]\u001b[0m, \u001b[31;1mParameter\u001b[0m, \u001b[31;1mNoneType\u001b[0m, \u001b[31;1mtuple of (int, int)\u001b[0m, \u001b[31;1mtuple of (int, int)\u001b[0m, \u001b[31;1mtuple of (int, int)\u001b[0m, \u001b[31;1mint\u001b[0m)\n * (Tensor input, Tensor weight, Tensor bias = None, tuple of ints stride = 1, str padding = \"valid\", tuple of ints dilation = 1, int groups = 1)\n didn't match because some of the arguments have invalid types: (\u001b[31;1mlist of [Tensor]\u001b[0m, \u001b[31;1mParameter\u001b[0m, \u001b[31;1mNoneType\u001b[0m, \u001b[31;1mtuple of (int, int)\u001b[0m, \u001b[31;1mtuple of (int, int)\u001b[0m, \u001b[31;1mtuple of (int, int)\u001b[0m, \u001b[31;1mint\u001b[0m)\n"}
The API server is also keep posting this:
ERROR:__main__:Error during inference: conv2d() received an invalid combination of arguments - got (list, Parameter, NoneType, tuple, tuple, tuple, int), but expected one of:
* (Tensor input, Tensor weight, Tensor bias = None, tuple of ints stride = 1, tuple of ints padding = 0, tuple of ints dilation = 1, int groups = 1)
didn't match because some of the arguments have invalid types: (list of [Tensor], Parameter, NoneType, tuple of (int, int), tuple of (int, int), tuple of (int, int), int)
* (Tensor input, Tensor weight, Tensor bias = None, tuple of ints stride = 1, str padding = "valid", tuple of ints dilation = 1, int groups = 1)
didn't match because some of the arguments have invalid types: (list of [Tensor], Parameter, NoneType, tuple of (int, int), tuple of (int, int), tuple of (int, int), int)
INFO: 127.0.0.1:43504 - "POST /run-inference HTTP/1.1" 500 Internal Server Error
It seems to me that the problem can be either in that fact that I'm using conda (but I set everything right) + I mostly believe that the reason is in model...
I would be very happy if you'll find some time to check it out