-
Notifications
You must be signed in to change notification settings - Fork 2.3k
New issue
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
[FrontEnd]enable PDPD 16 ops conversion Part2 #6632
[FrontEnd]enable PDPD 16 ops conversion Part2 #6632
Conversation
@jane-intel @mvafin Could you have a look? |
Any reason of not including test models here? Just wanted to check if all cases are covered by tests |
Hi @nosovmik The tests cases are removed here because previously, we have different opinions about how to test conversion. Therefore we remove them in this PR and test them locally. I think we can add them back in another PR because we have alignment with Ilya about how to test the conversion. |
* fix paddle conversion * ops forward declaration
* [FrontEnd]enable 16 ops conversion * [FrontEnd]fix typo in interpolate * param support tensor (#3) * Update hard_sigmoid.cpp (#4) * Yi3/fix paddle part2 * fix paddle conversion * ops forward declaration * use tile instead of broadcast * Add validation check in dropout (#8) * fix conflict * fix code style * fix transpose2 * use perm size in transpose2 * remove check in transpose2 Co-authored-by: Luo Cheng <[email protected]> Co-authored-by: Mang Guo <[email protected]>
* [FrontEnd]enable 16 ops conversion * [FrontEnd]fix typo in interpolate * param support tensor (#3) * Update hard_sigmoid.cpp (#4) * Yi3/fix paddle part2 * fix paddle conversion * ops forward declaration * use tile instead of broadcast * Add validation check in dropout (#8) * fix conflict * fix code style * fix transpose2 * use perm size in transpose2 * remove check in transpose2 Co-authored-by: Luo Cheng <[email protected]> Co-authored-by: Mang Guo <[email protected]>
* [FrontEnd]enable 16 ops conversion * [FrontEnd]fix typo in interpolate * param support tensor (#3) * Update hard_sigmoid.cpp (#4) * Yi3/fix paddle part2 * fix paddle conversion * ops forward declaration * use tile instead of broadcast * Add validation check in dropout (#8) * fix conflict * fix code style * fix transpose2 * use perm size in transpose2 * remove check in transpose2 Co-authored-by: Luo Cheng <[email protected]> Co-authored-by: Mang Guo <[email protected]>
Details:
| bilinear_interp |
| bmm |
| conv2d_transpose |
| dropout |
| equal |
| expand_v2 |
| fill_constant |
| fill_constant_batch_size_like |
| flatten_contiguous_range |
| greater_equal |
| hard_swish |
| nearest_interp |
| leakyrelu |
| log |
| logical_not |
| lstm |
| matmul |
| transpose2 |
Tickets: