We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
I have a problem when i compute ggml_conv_2d. ggml_tensor *output = ggml_conv_2d(gctx,weight, input,stride,stride, 0, 0, 1, 1); the inputs is:
ggml_tensor *output = ggml_conv_2d(gctx,weight, input,stride,stride, 0, 0, 1, 1);
weight->ne[0]: 1792 weight->ne[1]: 3 weight->ne[2]: 14 weight->ne[3]: 14 input->ne[0]: 1 input->ne[1]: 3 input->ne[2]: 14 input->ne[3]: 224
the output is:
output->ne[0]: -126 output->ne[1]: 1 output->ne[2]: 14 output->ne[3]: 224
I don’t know why the results of the convolution are like this? In addition, in ggml_im2col , why is a-> ne [2] == b-> ne [2]?
ggml_im2col
a-> ne [2] == b-> ne [2]
The text was updated successfully, but these errors were encountered:
No branches or pull requests
I have a problem when i compute ggml_conv_2d.
ggml_tensor *output = ggml_conv_2d(gctx,weight, input,stride,stride, 0, 0, 1, 1);
the inputs is:
the output is:
I don’t know why the results of the convolution are like this?
In addition, in
ggml_im2col
, why isa-> ne [2] == b-> ne [2]
?The text was updated successfully, but these errors were encountered: