[TVM Discuss] [Development/RFC] Introduce new frontend for Chainer

2020-03-30 Thread ANSHUMAN TRIPATHY via TVM Discuss
@jwfromm: Thank you very much for sharing your view on this. As i recall ONNX-Chainer has limited support in their current code. Please refer [Code](https://github.com/chainer/chainer/blob/master/onnx_chainer/functions/__init__.py) or [Tutorial](https://docs.chainer.org/en/stable/onnx_chaine

[TVM Discuss] [Development/RFC] Introduce new frontend for Chainer

2020-03-30 Thread masahi via TVM Discuss
Your proposal is reasonable from perspective of existing Chainer users looking for deployment solution. However, I see little benefit from TVM side. First of all, compared to other framework like PyTorch, the number of Chainer user had been very tiny even during Chainer was in active developme

[TVM Discuss] [Development/RFC] Introduce new frontend for Chainer

2020-03-30 Thread ANSHUMAN TRIPATHY via TVM Discuss
Thank you very much for sharing your views on this. It was really insightful. Few points i want to reply as below: [quote="masahi, post:7, topic:6129"] First of all, compared to other framework like PyTorch, the number of Chainer user had been very tiny even during Chainer was in active develo

[TVM Discuss] [Development] Separate Relay Depthwise Conv operator

2020-03-30 Thread Yao Wang via TVM Discuss
@anijain2305 Thank you for bringing this up. Would you mind listing the current pain point of managing different categories of conv2d in Relay, and listing pros and cons for keeping the current method VS separating? --- [Visit Topic](https://discuss.tvm.ai/t/separate-relay-depthwise-conv-

[TVM Discuss] [Development/RFC] Introduce new frontend for Chainer

2020-03-30 Thread masahi via TVM Discuss
[quote="ANSHUMAN.TRIPATHY, post:8, topic:6129"] But don’t you think the **“out of scope from TVM”** is applicable for all frontends. As all frontends first need to beakdown the model received and put all the pieces together to in terms of TVM. [/quote] No. For example, both Torchscript and ONNX

[TVM Discuss] [Development/RFC] Performing Relay Passes Non-Recursively

2020-03-30 Thread Matthew Brookhart via TVM Discuss
Okay, I've implemented these APIs and converted a couple of passes to use them, please take a look and review. https://github.com/apache/incubator-tvm/pull/4886 @haichen @MarisaKirisame I'm noticing that the passes with these edge cases all seem to be doing more complicated things than the sim

[TVM Discuss] [Development/RFC] Performing Relay Passes Non-Recursively

2020-03-30 Thread Haichen Shen via TVM Discuss
Yes, that sounds good to me. --- [Visit Topic](https://discuss.tvm.ai/t/performing-relay-passes-non-recursively/5696/21) 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/07c8

Re: [apache/incubator-tvm] [RFC] Unify IR Node and Reference Class Naming Convention (#4648)

2020-03-30 Thread Tianqi Chen
Closed #4648. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/apache/incubator-tvm/issues/4648#event-3180521162

Re: [apache/incubator-tvm] [RFC] Unify IR Node and Reference Class Naming Convention (#4648)

2020-03-30 Thread Tianqi Chen
Close for now as most relay and tir nodes has been updated -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/apache/incubator-tvm/issues/4648#issuecomment-606253206