[GitHub] [incubator-tvm] anijain2305 commented on issue #4816: [TFLite] Using real image for QNN testing.

anijain2305 commented on issue #4816: [TFLite] Using real image for QNN testing. URL: https://github.com/apache/incubator-tvm/pull/4816#issuecomment-582570933 @inadob Can you please the TFLite pad test portion? I am not very familiar with using fake quant, and I just replicated your code

[GitHub] [incubator-tvm] anijain2305 edited a comment on issue #4816: [TFLite] Using real image for QNN testing.

anijain2305 edited a comment on issue #4816: [TFLite] Using real image for QNN testing. URL: https://github.com/apache/incubator-tvm/pull/4816#issuecomment-582570933 @inadob Can you please review the TFLite pad test portion? I am not very familiar with using fake quant, and I just

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4790: Fast exponent

masahi commented on a change in pull request #4790: Fast exponent URL: https://github.com/apache/incubator-tvm/pull/4790#discussion_r375470574 ## File path: topi/include/topi/elemwise.h ## @@ -360,5 +359,66 @@ inline Tensor full_like(const Tensor& x, }, name, tag); }

[GitHub] [incubator-tvm] masahi commented on issue #4497: [Relay] Add a PyTorch to Relay Parser

masahi commented on issue #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-582598505 @tqchen we should probably finish the docker update in https://github.com/apache/incubator-tvm/pull/4756 before we merge this PR.

[GitHub] [incubator-tvm] alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375519693 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375442180 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375433434 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375435959 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375443845 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375443682 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375437990 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375433264 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375449182 ## File path: tests/python/frontend/pytorch/test_forward.py ## @@ -0,0 +1,851 @@ +# Licensed to the

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375418946 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375429186 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

zhiics commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375442471 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] masahi commented on issue #4790: Fast exponent

masahi commented on issue #4790: Fast exponent URL: https://github.com/apache/incubator-tvm/pull/4790#issuecomment-582577053 @alexgl-github tests cases are absolutely required for a new operator like this. This is an

[incubator-tvm] branch master updated (019356f -> 2989d72)

This is an automated email from the ASF dual-hosted git repository. kevinthesun pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 019356f Fixed subprocess creation under windows (#4820) add 2989d72 [Frontend][TFLite]

[GitHub] [incubator-tvm] vinx13 merged pull request #4798: [QNN] Optimize lowering for requantize and FixedPointMultiply.

vinx13 merged pull request #4798: [QNN] Optimize lowering for requantize and FixedPointMultiply. URL: https://github.com/apache/incubator-tvm/pull/4798 This is an automated message from the Apache Git Service. To respond to

[incubator-tvm] branch master updated (2989d72 -> 23f3988)

This is an automated email from the ASF dual-hosted git repository. wuwei pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 2989d72 [Frontend][TFLite] Dynamically calculate input_stats of any fake_quant range (#4789) add

[GitHub] [incubator-tvm] vinx13 commented on issue #4798: [QNN] Optimize lowering for requantize and FixedPointMultiply.

vinx13 commented on issue #4798: [QNN] Optimize lowering for requantize and FixedPointMultiply. URL: https://github.com/apache/incubator-tvm/pull/4798#issuecomment-582582122 Thanks @anijain2305 @jackwish this is merged This

[GitHub] [incubator-tvm] kevinthesun commented on issue #4789: [Frontend][TFLite] Dynamically calculate input_stats of any fake_quant range

kevinthesun commented on issue #4789: [Frontend][TFLite] Dynamically calculate input_stats of any fake_quant range URL: https://github.com/apache/incubator-tvm/pull/4789#issuecomment-582582023 Thanks @inadob @wyc-ruiker @anijain2305

[GitHub] [incubator-tvm] tqchen commented on issue #4497: [Relay] Add a PyTorch to Relay Parser

tqchen commented on issue #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-582535201 Given that this is a quite big PR, would be great if we can get a few more eyes, cc @FrozenGene @kazum @zhiics @ajtulloch @hlu1 please also

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4790: Fast exponent

tqchen commented on a change in pull request #4790: Fast exponent URL: https://github.com/apache/incubator-tvm/pull/4790#discussion_r375464140 ## File path: topi/include/topi/elemwise.h ## @@ -360,5 +359,66 @@ inline Tensor full_like(const Tensor& x, }, name, tag); }

[GitHub] [incubator-tvm] tqchen commented on issue #4817: [CONTRIB][CC] Enhance cc.cross_compiler

tqchen commented on issue #4817: [CONTRIB][CC] Enhance cc.cross_compiler URL: https://github.com/apache/incubator-tvm/pull/4817#issuecomment-582529320 @FrozenGene please take another look This is an automated message from the

[GitHub] [incubator-tvm] inadob commented on a change in pull request #4816: [TFLite] Using real image for QNN testing.

inadob commented on a change in pull request #4816: [TFLite] Using real image for QNN testing. URL: https://github.com/apache/incubator-tvm/pull/4816#discussion_r375419290 ## File path: python/tvm/relay/frontend/tflite.py ## @@ -1124,10 +1124,14 @@ def convert_conv(self,

[incubator-tvm] branch master updated (fc7dd6d -> 019356f)

This is an automated email from the ASF dual-hosted git repository. lmzheng pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from fc7dd6d [REFACTOR][PY] Establish tvm.runtime (#4818) add 019356f Fixed subprocess creation under

[GitHub] [incubator-tvm] merrymercy merged pull request #4820: Fixed subprocess creation under windows

merrymercy merged pull request #4820: Fixed subprocess creation under windows URL: https://github.com/apache/incubator-tvm/pull/4820 This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [incubator-tvm] anijain2305 commented on issue #4696: [Relay][Frontend][TFlite] Add support for quantized LOGISTIC

anijain2305 commented on issue #4696: [Relay][Frontend][TFlite] Add support for quantized LOGISTIC URL: https://github.com/apache/incubator-tvm/pull/4696#issuecomment-582584426 @inadob Please rebase This is an automated

[incubator-tvm] branch master updated (23f3988 -> 79ce87f)

This is an automated email from the ASF dual-hosted git repository. liuyizhi pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 23f3988 [QNN] Optimize lowering for requantize and FixedPointMultiply. (#4798) add 79ce87f

[GitHub] [incubator-tvm] yzhliu commented on issue #4642: [Relay][Frontend][TFLite] Add parser support for logical operators

yzhliu commented on issue #4642: [Relay][Frontend][TFLite] Add parser support for logical operators URL: https://github.com/apache/incubator-tvm/pull/4642#issuecomment-582590768 Thanks @inadob @anijain2305 This is an

[GitHub] [incubator-tvm] yzhliu merged pull request #4642: [Relay][Frontend][TFLite] Add parser support for logical operators

yzhliu merged pull request #4642: [Relay][Frontend][TFLite] Add parser support for logical operators URL: https://github.com/apache/incubator-tvm/pull/4642 This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375513644 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375513469 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375513313 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375513751 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1093 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4816: [TFLite] Using real image for QNN testing.

anijain2305 commented on a change in pull request #4816: [TFLite] Using real image for QNN testing. URL: https://github.com/apache/incubator-tvm/pull/4816#discussion_r375424616 ## File path: python/tvm/relay/frontend/tflite.py ## @@ -1124,10 +1124,14 @@ def

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4790: Fast exponent

masahi commented on a change in pull request #4790: Fast exponent URL: https://github.com/apache/incubator-tvm/pull/4790#discussion_r375466601 ## File path: topi/include/topi/elemwise.h ## @@ -360,5 +359,66 @@ inline Tensor full_like(const Tensor& x, }, name, tag); }

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

masahi commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375484453 ## File path: tests/python/frontend/pytorch/test_forward.py ## @@ -0,0 +1,851 @@ +# Licensed to the

[GitHub] [incubator-tvm] alexwong edited a comment on issue #4497: [Relay] Add a PyTorch to Relay Parser

alexwong edited a comment on issue #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-582619862 > @alexwong please address my comment at https://github.com/apache/incubator-tvm/pull/4497/files#r370911013 > > Add `with

[GitHub] [incubator-tvm] u99127 commented on a change in pull request #4822: [Frontend][TFLite] Add MIRROR_PAD operator

u99127 commented on a change in pull request #4822: [Frontend][TFLite] Add MIRROR_PAD operator URL: https://github.com/apache/incubator-tvm/pull/4822#discussion_r375516566 ## File path: python/tvm/relay/frontend/tflite.py ## @@ -1422,10 +1423,48 @@ def convert_pad(self,

[GitHub] [incubator-tvm] alexwong commented on issue #4497: [Relay] Add a PyTorch to Relay Parser

alexwong commented on issue #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-582619862 > @alexwong please address my comment at https://github.com/apache/incubator-tvm/pull/4497/files#r370911013 > > Add `with

[GitHub] [incubator-tvm] alexgl-github commented on a change in pull request #4790: Fast exponent

alexgl-github commented on a change in pull request #4790: Fast exponent URL: https://github.com/apache/incubator-tvm/pull/4790#discussion_r375425157 ## File path: topi/include/topi/elemwise.h ## @@ -360,5 +359,66 @@ inline Tensor full_like(const Tensor& x, }, name,

[GitHub] [incubator-tvm] masahi edited a comment on issue #4497: [Relay] Add a PyTorch to Relay Parser

masahi edited a comment on issue #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-582565991 @alexwong please address my comment at https://github.com/apache/incubator-tvm/pull/4497/files#r370911013 Add `with

[GitHub] [incubator-tvm] anijain2305 commented on issue #4798: [QNN] Optimize lowering for requantize and FixedPointMultiply.

anijain2305 commented on issue #4798: [QNN] Optimize lowering for requantize and FixedPointMultiply. URL: https://github.com/apache/incubator-tvm/pull/4798#issuecomment-582581737 Ping This is an automated message from the

[GitHub] [incubator-tvm] kevinthesun merged pull request #4789: [Frontend][TFLite] Dynamically calculate input_stats of any fake_quant range

kevinthesun merged pull request #4789: [Frontend][TFLite] Dynamically calculate input_stats of any fake_quant range URL: https://github.com/apache/incubator-tvm/pull/4789 This is an automated message from the Apache Git

[GitHub] [incubator-tvm] anijain2305 commented on issue #4807: [Frontend][TFLite] Fix quantized pad value for convolution

anijain2305 commented on issue #4807: [Frontend][TFLite] Fix quantized pad value for convolution URL: https://github.com/apache/incubator-tvm/pull/4807#issuecomment-582591219 @inadob You can close this one. #4816 covers this.

[GitHub] [incubator-tvm] u99127 commented on a change in pull request #4822: [Frontend][TFLite] Add MIRROR_PAD operator

u99127 commented on a change in pull request #4822: [Frontend][TFLite] Add MIRROR_PAD operator URL: https://github.com/apache/incubator-tvm/pull/4822#discussion_r375518286 ## File path: python/tvm/relay/frontend/tflite.py ## @@ -1422,10 +1423,48 @@ def convert_pad(self,

[GitHub] [incubator-tvm] alexwong edited a comment on issue #4497: [Relay] Add a PyTorch to Relay Parser

alexwong edited a comment on issue #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-582263501 > CI is green now, great! Is it ready for final review? @alexwong Yes I believe so. I think I resolved all of the smaller

[GitHub] [incubator-tvm] alexwong edited a comment on issue #4497: [Relay] Add a PyTorch to Relay Parser

alexwong edited a comment on issue #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-582263501 > CI is green now, great! Is it ready for final review? @alexwong Yes I believe so. I think I resolved all of the smaller

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4816: [TFLite] Using real image for QNN testing.

anijain2305 commented on a change in pull request #4816: [TFLite] Using real image for QNN testing. URL: https://github.com/apache/incubator-tvm/pull/4816#discussion_r375459833 ## File path: python/tvm/relay/frontend/tflite.py ## @@ -1124,10 +1124,14 @@ def

[GitHub] [incubator-tvm] jroesch commented on issue #4815: [TOPI][Relay] Add bitwise ops

jroesch commented on issue #4815: [TOPI][Relay] Add bitwise ops URL: https://github.com/apache/incubator-tvm/pull/4815#issuecomment-582618898 cc @jwfromm can you review this? This is an automated message from the Apache Git

[GitHub] [incubator-tvm] masahi commented on issue #4497: [Relay] Add a PyTorch to Relay Parser

masahi commented on issue #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-582565991 @alexwong please address my comment at https://github.com/apache/incubator-tvm/pull/4497/files#r370911013 Add `with torch.no_grad()`

[GitHub] [incubator-tvm] tqchen closed issue #4819: AttributeError: module 'os' has no attribute 'setsid'

tqchen closed issue #4819: AttributeError: module 'os' has no attribute 'setsid' URL: https://github.com/apache/incubator-tvm/issues/4819 This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [incubator-tvm] tqchen commented on issue #4819: AttributeError: module 'os' has no attribute 'setsid'

tqchen commented on issue #4819: AttributeError: module 'os' has no attribute 'setsid' URL: https://github.com/apache/incubator-tvm/issues/4819#issuecomment-582573194 Thanks @Coderx7 This is an automated message from the

[GitHub] [incubator-tvm] alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375512544 ## File path: tests/python/frontend/pytorch/test_forward.py ## @@ -0,0 +1,851 @@ +# Licensed to the

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4790: Fast exponent

anijain2305 commented on a change in pull request #4790: Fast exponent URL: https://github.com/apache/incubator-tvm/pull/4790#discussion_r375563628 ## File path: topi/include/topi/elemwise.h ## @@ -360,5 +359,66 @@ inline Tensor full_like(const Tensor& x, }, name, tag);

[incubator-tvm] branch master updated (79ce87f -> 5ea4f0d)

This is an automated email from the ASF dual-hosted git repository. kevinthesun pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 79ce87f [Relay][Frontend][TFLite] Add parser support for logical operators (#4642) add 5ea4f0d

[GitHub] [incubator-tvm] kevinthesun commented on issue #4787: [Relay] Conv2D padding representation

kevinthesun commented on issue #4787: [Relay] Conv2D padding representation URL: https://github.com/apache/incubator-tvm/pull/4787#issuecomment-582664192 Thanks @zxy844288792 @icemelon9 @comaniac This is an automated message

[GitHub] [incubator-tvm] tqchen opened a new pull request #4826: [CI][DOCKER] Update ci-gpu torch1.4 and onnx1.6

tqchen opened a new pull request #4826: [CI][DOCKER] Update ci-gpu torch1.4 and onnx1.6 URL: https://github.com/apache/incubator-tvm/pull/4826 cc @masahi This is a docker image verified with testcases pass This is an

[GitHub] [incubator-tvm] tqchen commented on issue #4826: [CI][DOCKER] Update ci-gpu torch1.4 and onnx1.6

tqchen commented on issue #4826: [CI][DOCKER] Update ci-gpu torch1.4 and onnx1.6 URL: https://github.com/apache/incubator-tvm/pull/4826#issuecomment-582721513 @masahi please take another look This is an automated message from

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4826: [CI][DOCKER] Update ci-gpu torch1.4 and onnx1.6

tqchen commented on a change in pull request #4826: [CI][DOCKER] Update ci-gpu torch1.4 and onnx1.6 URL: https://github.com/apache/incubator-tvm/pull/4826#discussion_r375626423 ## File path: docker/install/ubuntu_install_onnx.sh ## @@ -21,7 +21,7 @@ set -u set -o

[GitHub] [incubator-tvm] zhiics commented on issue #4564: [Doc] Introduction to module serialization

zhiics commented on issue #4564: [Doc] Introduction to module serialization URL: https://github.com/apache/incubator-tvm/pull/4564#issuecomment-582726010 LGTM now. I will wait till tomorrow to see if there are any more comments.

[GitHub] [incubator-tvm] u99127 opened a new issue #4823: Improve tflite testing for quantized conv2d.

u99127 opened a new issue #4823: Improve tflite testing for quantized conv2d. URL: https://github.com/apache/incubator-tvm/issues/4823 @anijain2305 , @inadob While we have tests for qnn.conv2d at the relay level, the recent issue with padding highlighted by the pull request #4807

[GitHub] [incubator-tvm] jroesch commented on a change in pull request #4818: [REFACTOR][PY] Establish tvm.runtime

jroesch commented on a change in pull request #4818: [REFACTOR][PY] Establish tvm.runtime URL: https://github.com/apache/incubator-tvm/pull/4818#discussion_r375559169 ## File path: python/tvm/runtime/ndarray.py ## @@ -18,132 +18,36 @@ """Runtime NDArray api""" import

[GitHub] [incubator-tvm] jroesch commented on issue #4818: [REFACTOR][PY] Establish tvm.runtime

jroesch commented on issue #4818: [REFACTOR][PY] Establish tvm.runtime URL: https://github.com/apache/incubator-tvm/pull/4818#issuecomment-582656463 cc @robo-corg This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] tqchen commented on issue #4821: OSError: [WinError 10048] Only one usage of each socket address (protocol/network address/port) is normally permitted and OSError: [WinError 1

tqchen commented on issue #4821: OSError: [WinError 10048] Only one usage of each socket address (protocol/network address/port) is normally permitted and OSError: [WinError 10049] The requested address is not valid in its context URL:

[GitHub] [incubator-tvm] tqchen closed issue #4821: OSError: [WinError 10048] Only one usage of each socket address (protocol/network address/port) is normally permitted and OSError: [WinError 10049]

tqchen closed issue #4821: OSError: [WinError 10048] Only one usage of each socket address (protocol/network address/port) is normally permitted and OSError: [WinError 10049] The requested address is not valid in its context URL: https://github.com/apache/incubator-tvm/issues/4821

[GitHub] [incubator-tvm] wyc-ruiker commented on a change in pull request #4822: [Frontend][TFLite] Add MIRROR_PAD operator

wyc-ruiker commented on a change in pull request #4822: [Frontend][TFLite] Add MIRROR_PAD operator URL: https://github.com/apache/incubator-tvm/pull/4822#discussion_r375629498 ## File path: python/tvm/relay/frontend/tflite.py ## @@ -1422,10 +1423,48 @@ def

[GitHub] [incubator-tvm] alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375549738 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1023 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375549738 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1023 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] jwfromm commented on issue #4825: [Frontend][ONNX] LSTM Support

jwfromm commented on issue #4825: [Frontend][ONNX] LSTM Support URL: https://github.com/apache/incubator-tvm/pull/4825#issuecomment-582692382 @masahi, @soiferj, @mbrookhart can you take a look at this PR? This is an automated

[GitHub] [incubator-tvm] jwfromm opened a new pull request #4825: [Frontend][ONNX] LSTM Support

jwfromm opened a new pull request #4825: [Frontend][ONNX] LSTM Support URL: https://github.com/apache/incubator-tvm/pull/4825 This PR adds LSTM support to the relay Onnx frontend. Besides adding the LSTM parser itself, we encountered an issue where for some Onnx operations (like

[GitHub] [incubator-tvm] junrushao1994 commented on a change in pull request #4644: [WIP] Relay op strategy

junrushao1994 commented on a change in pull request #4644: [WIP] Relay op strategy URL: https://github.com/apache/incubator-tvm/pull/4644#discussion_r375566300 ## File path: include/tvm/relay/op_attr_types.h ## @@ -207,14 +216,182 @@ enum AnyCodegenStrategy {

[GitHub] [incubator-tvm] soiferj commented on issue #4825: [Frontend][ONNX] LSTM Support

soiferj commented on issue #4825: [Frontend][ONNX] LSTM Support URL: https://github.com/apache/incubator-tvm/pull/4825#issuecomment-582713458 Awesome!! I was looking at implementing this myself yesterday. I’ll take a look as soon as possible. Thanks for sending the PR!

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4826: [CI][DOCKER] Update ci-gpu torch1.4 and onnx1.6

masahi commented on a change in pull request #4826: [CI][DOCKER] Update ci-gpu torch1.4 and onnx1.6 URL: https://github.com/apache/incubator-tvm/pull/4826#discussion_r375625372 ## File path: docker/install/ubuntu_install_onnx.sh ## @@ -21,7 +21,7 @@ set -u set -o

[GitHub] [incubator-tvm] tqchen commented on issue #4696: [Relay][Frontend][TFlite] Add support for quantized LOGISTIC

tqchen commented on issue #4696: [Relay][Frontend][TFlite] Add support for quantized LOGISTIC URL: https://github.com/apache/incubator-tvm/pull/4696#issuecomment-582719957 @inadob please rebase, @FrozenGene please

[GitHub] [incubator-tvm] tqchen commented on issue #4564: [Doc] Introduction to module serialization

tqchen commented on issue #4564: [Doc] Introduction to module serialization URL: https://github.com/apache/incubator-tvm/pull/4564#issuecomment-582719710 ping @zhiics @yzhliu @FrozenGene @yangjunpro please followup on this thread :)

[GitHub] [incubator-tvm] anijain2305 commented on issue #4823: Improve tflite testing for quantized conv2d.

anijain2305 commented on issue #4823: Improve tflite testing for quantized conv2d. URL: https://github.com/apache/incubator-tvm/issues/4823#issuecomment-582641958 Thanks @u99127 for raising this. I will work in coming weeks to get the unit coverage better. @FrozenGene might also be

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

masahi commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r37170 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1023 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4818: [REFACTOR][PY] Establish tvm.runtime

tqchen commented on a change in pull request #4818: [REFACTOR][PY] Establish tvm.runtime URL: https://github.com/apache/incubator-tvm/pull/4818#discussion_r375561036 ## File path: python/tvm/runtime/ndarray.py ## @@ -18,132 +18,36 @@ """Runtime NDArray api""" import

[GitHub] [incubator-tvm] kevinthesun merged pull request #4787: [Relay] Conv2D padding representation

kevinthesun merged pull request #4787: [Relay] Conv2D padding representation URL: https://github.com/apache/incubator-tvm/pull/4787 This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [incubator-tvm] tqchen commented on issue #4750: Fix onnx import bugs

tqchen commented on issue #4750: Fix onnx import bugs URL: https://github.com/apache/incubator-tvm/pull/4750#issuecomment-582718831 ping @kice can you please add a few testcases? This is an automated message from the Apache

[GitHub] [incubator-tvm] tqchen commented on issue #4815: [TOPI][Relay] Add bitwise ops

tqchen commented on issue #4815: [TOPI][Relay] Add bitwise ops URL: https://github.com/apache/incubator-tvm/pull/4815#issuecomment-582718578 Thanks @jroesch @jwfromm @abergeron ! This is an automated message from the Apache

[incubator-tvm] branch master updated (19d0d15 -> 2bd2f99)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 19d0d15 [CONTRIB][CC] Enhance cc.cross_compiler (#4817) add 2bd2f99 [TOPI][Relay] Add bitwise ops

[GitHub] [incubator-tvm] tqchen commented on issue #4827: [CI][DOCKER] Update ci-gpu to v0.60

tqchen commented on issue #4827: [CI][DOCKER] Update ci-gpu to v0.60 URL: https://github.com/apache/incubator-tvm/pull/4827#issuecomment-582721675 ``` docker/bash.sh tvmai/ci-gpu:v0.60 >>> import torch >>> import torchvision >>> torch.__version__ '1.4.0' >>>

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4826: [CI][DOCKER] Update ci-gpu torch1.4 and onnx1.6

masahi commented on a change in pull request #4826: [CI][DOCKER] Update ci-gpu torch1.4 and onnx1.6 URL: https://github.com/apache/incubator-tvm/pull/4826#discussion_r375627008 ## File path: docker/install/ubuntu_install_onnx.sh ## @@ -21,7 +21,7 @@ set -u set -o

[GitHub] [incubator-tvm] tqchen commented on issue #4543: [FRONTEND][TFLITE] Add support for TFLite_Detection_PostProcess

tqchen commented on issue #4543: [FRONTEND][TFLITE] Add support for TFLite_Detection_PostProcess URL: https://github.com/apache/incubator-tvm/pull/4543#issuecomment-582721889 @mbarrett97 please rebase, @FrozenGene please followup :)

[GitHub] [incubator-tvm] u99127 opened a new issue #4824: Tflite frontend needs to use zero point of input tensor while lowering qnn.conv2d for padding

u99127 opened a new issue #4824: Tflite frontend needs to use zero point of input tensor while lowering qnn.conv2d for padding URL: https://github.com/apache/incubator-tvm/issues/4824 The Tflite frontend ignores the zero point for input tensors when creating a separate pad operation while

[GitHub] [incubator-tvm] alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser

alexwong commented on a change in pull request #4497: [Relay] Add a PyTorch to Relay Parser URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r375549738 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -0,0 +1,1023 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass

zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass URL: https://github.com/apache/incubator-tvm/pull/4771#discussion_r375547370 ## File path: src/relay/pass/merge_composite.cc ## @@ -0,0 +1,205 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass

zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass URL: https://github.com/apache/incubator-tvm/pull/4771#discussion_r375530819 ## File path: src/relay/pass/merge_composite.cc ## @@ -0,0 +1,205 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass

zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass URL: https://github.com/apache/incubator-tvm/pull/4771#discussion_r375524422 ## File path: src/relay/pass/merge_composite.cc ## @@ -0,0 +1,205 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass

zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass URL: https://github.com/apache/incubator-tvm/pull/4771#discussion_r375542736 ## File path: tests/python/relay/test_pass_merge_composite.py ## @@ -0,0 +1,439 @@ +# Licensed to the Apache

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass

zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass URL: https://github.com/apache/incubator-tvm/pull/4771#discussion_r375526504 ## File path: src/relay/pass/merge_composite.cc ## @@ -0,0 +1,205 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass

zhiics commented on a change in pull request #4771: [Relay] Added Merge Composite pass URL: https://github.com/apache/incubator-tvm/pull/4771#discussion_r375526504 ## File path: src/relay/pass/merge_composite.cc ## @@ -0,0 +1,205 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] tqchen commented on issue #4475: onnx frontend support layout choice depend on hardware target support…

tqchen commented on issue #4475: onnx frontend support layout choice depend on hardware target support… URL: https://github.com/apache/incubator-tvm/pull/4475#issuecomment-582719028 Close this for now, as it is likely superceded by the layout transform by @anijain2305 Thanks @Beya2019

[GitHub] [incubator-tvm] tqchen commented on issue #3934: [WIP][Runtime] MISRA-C compliant TVM runtime

tqchen commented on issue #3934: [WIP][Runtime] MISRA-C compliant TVM runtime URL: https://github.com/apache/incubator-tvm/pull/3934#issuecomment-582719122 ping @liangfu please see if you are interested in continue pushing this thread

[GitHub] [incubator-tvm] tqchen closed pull request #4370: [WIP] Relay visualization: exporter + visualizer

tqchen closed pull request #4370: [WIP] Relay visualization: exporter + visualizer URL: https://github.com/apache/incubator-tvm/pull/4370 This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [incubator-tvm] tqchen commented on issue #4370: [WIP] Relay visualization: exporter + visualizer

tqchen commented on issue #4370: [WIP] Relay visualization: exporter + visualizer URL: https://github.com/apache/incubator-tvm/pull/4370#issuecomment-582719302 close due to inactive status, @hcho3 feel free to reopen :) This

  1   2   >