[quant][ns] Fix ns tool bug for mobilenetv2/v3 #74149

terrychenism · 2022-03-13T17:56:39Z

Stack from ghstack (oldest at bottom):

-> [quant][ns] Fix ns tool bug for mobilenetv2/v3 #74149

Summary:
mobilenet v2/v3 failed when using ns tool to analysis the model
original ns tool would generate the empty tensor, they cannot pass the function of error calculation. we fixed it by filtering the empty tensor

Test Plan:
python3 test/test_quantization.py TestNumericSuiteEager.test_mobilenet

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: D34851886

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]

pytorch-bot · 2022-03-13T17:56:43Z

CI Flow Status

⚛️ CI Flow

Ruleset - Version: v1
Ruleset - File: https://github.com/pytorch/pytorch/blob/7a22e47a027c005bc5ea15ca964ff6dcba7a8cd5/.github/generated-ciflow-ruleset.json
PR ciflow labels: ciflow/default
Add ciflow labels to this PR to trigger more builds:

Workflows	Labels (bold enabled)	Status
Triggered Workflows
linux-binary-conda	`ciflow/binaries`, `ciflow/binaries_conda`, `ciflow/default`	✅ triggered
linux-binary-libtorch-cxx11-abi	`ciflow/all`, `ciflow/binaries`, `ciflow/binaries_libtorch`, `ciflow/default`, `ciflow/trunk`	✅ triggered
linux-binary-libtorch-pre-cxx11	`ciflow/all`, `ciflow/binaries`, `ciflow/binaries_libtorch`, `ciflow/default`, `ciflow/trunk`	✅ triggered
linux-binary-manywheel	`ciflow/all`, `ciflow/binaries`, `ciflow/binaries_wheel`, `ciflow/default`, `ciflow/trunk`	✅ triggered
linux-bionic-py3.7-clang9	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/noarch`, `ciflow/trunk`	✅ triggered
linux-bionic-rocm4.5-py3.7	`ciflow/all`, `ciflow/default`, `ciflow/linux`, `ciflow/rocm`, `ciflow/trunk`	✅ triggered
linux-docs	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/docs`, `ciflow/linux`, `ciflow/trunk`	✅ triggered
linux-vulkan-bionic-py3.7-clang9	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/trunk`, `ciflow/vulkan`	✅ triggered
linux-xenial-cuda11.3-py3.7-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/default`, `ciflow/linux`, `ciflow/trunk`	✅ triggered
linux-xenial-cuda11.3-py3.7-gcc7-bazel-test	`ciflow/all`, `ciflow/bazel`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/trunk`	✅ triggered
linux-xenial-py3-clang5-mobile-build	`ciflow/all`, `ciflow/default`, `ciflow/linux`, `ciflow/mobile`, `ciflow/trunk`	✅ triggered
linux-xenial-py3-clang5-mobile-custom-build-static	`ciflow/all`, `ciflow/default`, `ciflow/linux`, `ciflow/mobile`, `ciflow/trunk`	✅ triggered
linux-xenial-py3.7-clang7-asan	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/sanitizers`, `ciflow/trunk`	✅ triggered
linux-xenial-py3.7-clang7-onnx	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/onnx`, `ciflow/trunk`	✅ triggered
linux-xenial-py3.7-gcc5.4	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/trunk`	✅ triggered
linux-xenial-py3.7-gcc5.4-mobile-lightweight-dispatch-build	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/libtorch`, `ciflow/linux`, `ciflow/mobile`, `ciflow/trunk`	✅ triggered
linux-xenial-py3.7-gcc7	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/trunk`	✅ triggered
linux-xenial-py3.7-gcc7-no-ops	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/trunk`	✅ triggered
macos-arm64-binary-conda	`ciflow/binaries`, `ciflow/binaries_conda`, `ciflow/default`	✅ triggered
macos-arm64-binary-wheel	`ciflow/binaries`, `ciflow/binaries_wheel`, `ciflow/default`	✅ triggered
macos-binary-conda	`ciflow/binaries`, `ciflow/binaries_conda`, `ciflow/default`	✅ triggered
macos-binary-libtorch-cxx11-abi	`ciflow/binaries`, `ciflow/binaries_libtorch`, `ciflow/default`	✅ triggered
macos-binary-libtorch-pre-cxx11	`ciflow/binaries`, `ciflow/binaries_libtorch`, `ciflow/default`	✅ triggered
macos-binary-wheel	`ciflow/binaries`, `ciflow/binaries_wheel`, `ciflow/default`	✅ triggered
pytorch-linux-xenial-py3-clang5-android-ndk-r19c-gradle-custom-build-single	`ciflow/all`, `ciflow/android`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/trunk`	✅ triggered
pytorch-linux-xenial-py3-clang5-android-ndk-r19c-gradle-custom-build-single-full-jit	`ciflow/all`, `ciflow/android`, `ciflow/cpu`, `ciflow/default`, `ciflow/linux`, `ciflow/trunk`	✅ triggered
win-vs2019-cpu-py3	`ciflow/all`, `ciflow/cpu`, `ciflow/default`, `ciflow/trunk`, `ciflow/win`	✅ triggered
win-vs2019-cuda11.3-py3	`ciflow/all`, `ciflow/cuda`, `ciflow/default`, `ciflow/trunk`, `ciflow/win`	✅ triggered
windows-binary-conda	`ciflow/binaries`, `ciflow/binaries_conda`, `ciflow/default`	✅ triggered
windows-binary-libtorch-debug	`ciflow/all`, `ciflow/binaries`, `ciflow/binaries_libtorch`, `ciflow/default`, `ciflow/trunk`	✅ triggered
windows-binary-libtorch-release	`ciflow/all`, `ciflow/binaries`, `ciflow/binaries_libtorch`, `ciflow/default`, `ciflow/trunk`	✅ triggered
windows-binary-wheel	`ciflow/all`, `ciflow/binaries`, `ciflow/binaries_wheel`, `ciflow/default`, `ciflow/trunk`	✅ triggered
Skipped Workflows
caffe2-linux-xenial-py3.7-gcc5.4	`ciflow/all`, `ciflow/cpu`, `ciflow/linux`, `ciflow/trunk`	🚫 skipped
docker-builds	`ciflow/all`, `ciflow/trunk`	🚫 skipped
ios-12-5-1-arm64	`ciflow/all`, `ciflow/ios`, `ciflow/macos`, `ciflow/scheduled`	🚫 skipped
ios-12-5-1-arm64-coreml	`ciflow/all`, `ciflow/ios`, `ciflow/macos`, `ciflow/scheduled`	🚫 skipped
ios-12-5-1-arm64-custom-ops	`ciflow/all`, `ciflow/ios`, `ciflow/macos`, `ciflow/scheduled`	🚫 skipped
ios-12-5-1-arm64-metal	`ciflow/all`, `ciflow/ios`, `ciflow/macos`, `ciflow/scheduled`	🚫 skipped
ios-12-5-1-x86-64	`ciflow/all`, `ciflow/ios`, `ciflow/macos`, `ciflow/trunk`	🚫 skipped
ios-12-5-1-x86-64-coreml	`ciflow/all`, `ciflow/ios`, `ciflow/macos`, `ciflow/trunk`	🚫 skipped
libtorch-linux-xenial-cuda10.2-py3.7-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/libtorch`, `ciflow/linux`, `ciflow/trunk`	🚫 skipped
libtorch-linux-xenial-cuda11.3-py3.7-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/libtorch`, `ciflow/linux`, `ciflow/trunk`	🚫 skipped
linux-bionic-cuda10.2-py3.9-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/linux`, `ciflow/slow`, `ciflow/trunk`	🚫 skipped
linux-bionic-rocm4.5-py3.7-distributed	`ciflow/all`, `ciflow/linux`, `ciflow/rocm`, `ciflow/trunk`	🚫 skipped
linux-docs-push	`ciflow/all`, `ciflow/cpu`, `ciflow/linux`, `ciflow/scheduled`	🚫 skipped
linux-xenial-cuda11.3-py3.7-gcc7-no-ops	`ciflow/all`, `ciflow/cuda`, `ciflow/linux`, `ciflow/trunk`	🚫 skipped
macos-10-15-py3-arm64	`ciflow/all`, `ciflow/macos`, `ciflow/trunk`	🚫 skipped
macos-10-15-py3-lite-interpreter-x86-64	`ciflow/all`, `ciflow/macos`, `ciflow/trunk`	🚫 skipped
macos-11-py3-x86-64	`ciflow/all`, `ciflow/macos`, `ciflow/trunk`	🚫 skipped
parallelnative-linux-xenial-py3.7-gcc5.4	`ciflow/all`, `ciflow/cpu`, `ciflow/linux`, `ciflow/trunk`	🚫 skipped
periodic-libtorch-linux-bionic-cuda11.5-py3.7-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/libtorch`, `ciflow/linux`, `ciflow/scheduled`	🚫 skipped
periodic-linux-bionic-cuda11.5-py3.7-gcc7	`ciflow/all`, `ciflow/cuda`, `ciflow/linux`, `ciflow/scheduled`	🚫 skipped
periodic-linux-xenial-cuda10.2-py3-gcc7-slow-gradcheck	`ciflow/all`, `ciflow/cuda`, `ciflow/linux`, `ciflow/scheduled`, `ciflow/slow`, `ciflow/slow-gradcheck`	🚫 skipped
periodic-linux-xenial-cuda11.3-py3.7-gcc7-debug	`ciflow/all`, `ciflow/cuda`, `ciflow/linux`, `ciflow/scheduled`	🚫 skipped
periodic-win-vs2019-cuda11.5-py3	`ciflow/all`, `ciflow/cuda`, `ciflow/scheduled`, `ciflow/win`	🚫 skipped
pytorch-linux-xenial-py3-clang5-android-ndk-r19c-build	`ciflow/all`, `ciflow/android`, `ciflow/cpu`, `ciflow/linux`, `ciflow/trunk`	🚫 skipped
pytorch-xla-linux-bionic-py3.7-clang8	`ciflow/all`, `ciflow/cpu`, `ciflow/linux`, `ciflow/trunk`, `ciflow/xla`	🚫 skipped

facebook-github-bot · 2022-03-13T17:56:46Z

🔗 Helpful links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/74149
↩️ [fb-only] Re-run with SSH instructions
Need help or want to give feedback on the CI? Visit our office hours

💊 CI failures summary and remediations

As of commit 2079ad7 (more details on the Dr. CI page):

4/4 failures introduced in this PR

🕵️ 3 new failures recognized by patterns

The following CI failures do not appear to be due to upstream breakages:

pull / linux-xenial-cuda11.3-py3.7-gcc7-bazel-test / build-and-test (1/3)

Step: "Build" (full log | diagnosis details | 🔁 rerun)

2022-03-30T21:13:37.3558106Z �[36;1m echo "ERR...t available for the merge-base of your branch"�[0m

2022-03-30T21:13:37.3555067Z �[36;1mfi�[0m
2022-03-30T21:13:37.3555369Z �[36;1m# Covers the case where a previous tag doesn't exist for the tree�[0m
2022-03-30T21:13:37.3555727Z �[36;1m# this is only really applicable on trees that don't have `.circleci/docker` at its merge base, i.e. nightly�[0m
2022-03-30T21:13:37.3556054Z �[36;1mif ! git rev-parse "$MERGE_BASE:.circleci/docker"; then�[0m
2022-03-30T21:13:37.3556410Z �[36;1m  echo "Directory '.circleci/docker' not found in commit $MERGE_BASE, you should probably rebase onto a more recent commit"�[0m
2022-03-30T21:13:37.3556703Z �[36;1m  exit 1�[0m
2022-03-30T21:13:37.3556874Z �[36;1mfi�[0m
2022-03-30T21:13:37.3557103Z �[36;1mPREVIOUS_DOCKER_TAG=$(git rev-parse "$MERGE_BASE:.circleci/docker")�[0m
2022-03-30T21:13:37.3557447Z �[36;1m# If no image exists but the hash is the same as the previous hash then we should error out here�[0m
2022-03-30T21:13:37.3557760Z �[36;1mif [[ "${PREVIOUS_DOCKER_TAG}" = "${DOCKER_TAG}" ]]; then�[0m
2022-03-30T21:13:37.3558106Z �[36;1m  echo "ERROR: Something has gone wrong and the previous image isn't available for the merge-base of your branch"�[0m
2022-03-30T21:13:37.3558508Z �[36;1m  echo "       contact the PyTorch team to restore the original images"�[0m
2022-03-30T21:13:37.3558750Z �[36;1m  exit 1�[0m
2022-03-30T21:13:37.3558916Z �[36;1mfi�[0m
2022-03-30T21:13:37.3559107Z �[36;1mecho ::set-output name=rebuild::yes�[0m
2022-03-30T21:13:37.3569536Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2022-03-30T21:13:37.3569764Z env:
2022-03-30T21:13:37.3569914Z   IN_CI: 1
2022-03-30T21:13:37.3570078Z   IS_GHA: 1
2022-03-30T21:13:37.3570264Z   GIT_DEFAULT_BRANCH: master
2022-03-30T21:13:37.3570496Z   BASE_REVISION: e773d21034fcba4bd242b9cf8759ac8d6358409f

pull / linux-xenial-cuda11.3-py3.7-gcc7 / build (2/3)

Step: "Build" (full log | diagnosis details | 🔁 rerun)

2022-03-30T21:13:59.6935110Z �[36;1m echo "ERR...t available for the merge-base of your branch"�[0m

2022-03-30T21:13:59.6931976Z �[36;1mfi�[0m
2022-03-30T21:13:59.6932207Z �[36;1m# Covers the case where a previous tag doesn't exist for the tree�[0m
2022-03-30T21:13:59.6932555Z �[36;1m# this is only really applicable on trees that don't have `.circleci/docker` at its merge base, i.e. nightly�[0m
2022-03-30T21:13:59.6932873Z �[36;1mif ! git rev-parse "$MERGE_BASE:.circleci/docker"; then�[0m
2022-03-30T21:13:59.6933220Z �[36;1m  echo "Directory '.circleci/docker' not found in commit $MERGE_BASE, you should probably rebase onto a more recent commit"�[0m
2022-03-30T21:13:59.6933501Z �[36;1m  exit 1�[0m
2022-03-30T21:13:59.6933656Z �[36;1mfi�[0m
2022-03-30T21:13:59.6933892Z �[36;1mPREVIOUS_DOCKER_TAG=$(git rev-parse "$MERGE_BASE:.circleci/docker")�[0m
2022-03-30T21:13:59.6934289Z �[36;1m# If no image exists but the hash is the same as the previous hash then we should error out here�[0m
2022-03-30T21:13:59.6934785Z �[36;1mif [[ "${PREVIOUS_DOCKER_TAG}" = "${DOCKER_TAG}" ]]; then�[0m
2022-03-30T21:13:59.6935110Z �[36;1m  echo "ERROR: Something has gone wrong and the previous image isn't available for the merge-base of your branch"�[0m
2022-03-30T21:13:59.6935459Z �[36;1m  echo "       contact the PyTorch team to restore the original images"�[0m
2022-03-30T21:13:59.6935757Z �[36;1m  exit 1�[0m
2022-03-30T21:13:59.6935928Z �[36;1mfi�[0m
2022-03-30T21:13:59.6936116Z �[36;1mecho ::set-output name=rebuild::yes�[0m
2022-03-30T21:13:59.6946789Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2022-03-30T21:13:59.6947013Z env:
2022-03-30T21:13:59.6947159Z   IN_CI: 1
2022-03-30T21:13:59.6947330Z   IS_GHA: 1
2022-03-30T21:13:59.6947554Z   BASE_REVISION: e773d21034fcba4bd242b9cf8759ac8d6358409f
2022-03-30T21:13:59.6947966Z   DOCKER_IMAGE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-cuda11.3-cudnn8-py3-gcc7:a2c09c6009bb8a10cbb45a8c5f7c573593289be0

pull / deploy-linux-xenial-cuda11.3-py3.7-gcc7 / build (3/3)

Step: "Build" (full log | diagnosis details | 🔁 rerun)

2022-03-30T21:13:50.9637586Z �[36;1m echo "ERR...t available for the merge-base of your branch"�[0m

2022-03-30T21:13:50.9634497Z �[36;1mfi�[0m
2022-03-30T21:13:50.9634740Z �[36;1m# Covers the case where a previous tag doesn't exist for the tree�[0m
2022-03-30T21:13:50.9635089Z �[36;1m# this is only really applicable on trees that don't have `.circleci/docker` at its merge base, i.e. nightly�[0m
2022-03-30T21:13:50.9635430Z �[36;1mif ! git rev-parse "$MERGE_BASE:.circleci/docker"; then�[0m
2022-03-30T21:13:50.9635883Z �[36;1m  echo "Directory '.circleci/docker' not found in commit $MERGE_BASE, you should probably rebase onto a more recent commit"�[0m
2022-03-30T21:13:50.9636179Z �[36;1m  exit 1�[0m
2022-03-30T21:13:50.9636339Z �[36;1mfi�[0m
2022-03-30T21:13:50.9636586Z �[36;1mPREVIOUS_DOCKER_TAG=$(git rev-parse "$MERGE_BASE:.circleci/docker")�[0m
2022-03-30T21:13:50.9636934Z �[36;1m# If no image exists but the hash is the same as the previous hash then we should error out here�[0m
2022-03-30T21:13:50.9637239Z �[36;1mif [[ "${PREVIOUS_DOCKER_TAG}" = "${DOCKER_TAG}" ]]; then�[0m
2022-03-30T21:13:50.9637586Z �[36;1m  echo "ERROR: Something has gone wrong and the previous image isn't available for the merge-base of your branch"�[0m
2022-03-30T21:13:50.9637953Z �[36;1m  echo "       contact the PyTorch team to restore the original images"�[0m
2022-03-30T21:13:50.9638254Z �[36;1m  exit 1�[0m
2022-03-30T21:13:50.9638416Z �[36;1mfi�[0m
2022-03-30T21:13:50.9638627Z �[36;1mecho ::set-output name=rebuild::yes�[0m
2022-03-30T21:13:50.9649328Z shell: /usr/bin/bash --noprofile --norc -e -o pipefail {0}
2022-03-30T21:13:50.9649548Z env:
2022-03-30T21:13:50.9649713Z   IN_CI: 1
2022-03-30T21:13:50.9649883Z   IS_GHA: 1
2022-03-30T21:13:50.9650100Z   BASE_REVISION: e773d21034fcba4bd242b9cf8759ac8d6358409f
2022-03-30T21:13:50.9650542Z   DOCKER_IMAGE: 308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/pytorch-linux-xenial-cuda11.3-cudnn8-py3-gcc7:a2c09c6009bb8a10cbb45a8c5f7c573593289be0

1 failure not recognized by patterns:

Job	Step	Action
^{pull / pytorch-xla-linux-bionic-py3.7-clang8 / test (xla, 1, 1, linux.2xlarge)}	^Test	🔁 rerun

This comment was automatically generated by Dr. CI (expand for details).

Please report bugs/suggestions to the (internal) Dr. CI Users group.

Click here to manually regenerate this comment.

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 31ed6cd Pull Request resolved: #74149

terrychenism · 2022-03-13T17:57:21Z

@terrychenism has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D34851886](https://our.internmc.facebook.com/intern/diff/D34851886) [ghstack-poisoned]

terrychenism · 2022-03-14T03:38:57Z

@terrychenism has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D34851886](https://our.internmc.facebook.com/intern/diff/D34851886) [ghstack-poisoned]

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 041f395 Pull Request resolved: #74149

terrychenism · 2022-03-14T03:45:47Z

@terrychenism has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

vkuzo · 2022-03-15T12:51:08Z

thanks for fixing this, would it be possible to add a reproducible test plan?

jerryzh168 · 2022-03-23T21:46:18Z

test/quantization/eager/test_numeric_suite_eager.py

            "myadd_relu.stats",
-            "my_scalar_add.stats",
-            "my_scalar_mul.stats",
+            # "my_scalar_add.stats", # empty


is this change relevant?

+1, what's the context for this?

this tensor is empty, it would be filtered after this PR.

in that case, I think it would be better to delete the lines instead of commenting them out

torch/ao/ns/_numeric_suite.py

vkuzo

requesting changes for test plan

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D34851886](https://our.internmc.facebook.com/intern/diff/D34851886) [ghstack-poisoned]

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 6c82b95 Pull Request resolved: #74149

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D34851886](https://our.internmc.facebook.com/intern/diff/D34851886) [ghstack-poisoned]

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 25f6b7d Pull Request resolved: #74149

terrychenism · 2022-03-24T18:25:37Z

@terrychenism has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: python3 test/test_quantization.py TestNumericSuiteEager.test_mobilenet Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D34851886](https://our.internmc.facebook.com/intern/diff/D34851886) [ghstack-poisoned]

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: c459017 Pull Request resolved: #74149

terrychenism · 2022-03-24T23:22:06Z

@terrychenism has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

vkuzo · 2022-03-29T19:19:19Z

test/quantization/eager/test_numeric_suite_eager.py

+    @skip_if_no_torchvision
+    def test_mobilenet(self):
+        from torchvision.models.quantization import mobilenet_v2, mobilenet_v3_large
+        self._test_vision_model(mobilenet_v2(pretrained=True, quantize=False))


can we do separate test cases for these two models, instead of combining into one test case?

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model original ns tool would generate the empty tensor, they cannot pass the function of error calculation. we fixed it by filtering the empty tensor Test Plan: python3 test/test_quantization.py TestNumericSuiteEager.test_mobilenet Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D34851886](https://our.internmc.facebook.com/intern/diff/D34851886) [ghstack-poisoned]

terrychenism · 2022-03-29T20:41:56Z

@terrychenism has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model original ns tool would generate the empty tensor, they cannot pass the function of error calculation. we fixed it by filtering the empty tensor Test Plan: python3 test/test_quantization.py TestNumericSuiteEager.test_mobilenet Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D34851886](https://our.internmc.facebook.com/intern/diff/D34851886) [ghstack-poisoned]

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 8c015fe Pull Request resolved: #74149

terrychenism · 2022-03-29T21:22:56Z

@terrychenism has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

vkuzo

looks good, thanks for fixing this!

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model original ns tool would generate the empty tensor, they cannot pass the function of error calculation. we fixed it by filtering the empty tensor Test Plan: python3 test/test_quantization.py TestNumericSuiteEager.test_mobilenet Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D34851886](https://our.internmc.facebook.com/intern/diff/D34851886) [ghstack-poisoned]

terrychenism · 2022-03-30T16:42:51Z

@terrychenism has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model original ns tool would generate the empty tensor, they cannot pass the function of error calculation. we fixed it by filtering the empty tensor Test Plan: python3 test/test_quantization.py TestNumericSuiteEager.test_mobilenet Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D34851886](https://our.internmc.facebook.com/intern/diff/D34851886) [ghstack-poisoned]

terrychenism · 2022-03-30T17:13:12Z

@terrychenism has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model original ns tool would generate the empty tensor, they cannot pass the function of error calculation. we fixed it by filtering the empty tensor Test Plan: python3 test/test_quantization.py TestNumericSuiteEager.test_mobilenet Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D34851886](https://our.internmc.facebook.com/intern/diff/D34851886) [ghstack-poisoned]

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 9a16a07 Pull Request resolved: #74149

terrychenism · 2022-03-30T21:09:22Z

@terrychenism has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Summary: Pull Request resolved: #74149 mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Imported from OSS Reviewed By: vkuzo Differential Revision: D34851886 fbshipit-source-id: db94fd5cef7d4a7a128d46bfe3f5ff4e532845fe

github-actions · 2022-03-31T05:32:25Z

Hey @terrychenism.
You've committed this PR, but it does not have both a 'release notes: ...' and 'topics: ...' label. Please add one of each to the PR. The 'release notes: ...' label should represent the part of PyTorch that this PR changes (fx, autograd, distributed, etc) and the 'topics: ...' label should represent the kind of PR it is (not user facing, new feature, bug fix, perf improvement, etc). The list of valid labels can be found here for the 'release notes: ...' and here for the 'topics: ...'.
For changes that are 'topic: not user facing' there is no need for a release notes label.

[quant][ns] Fix ns tool bug for mobilenetv2/v3

7a22e47

Summary: mobilenet v2/v3 failed when using ns tool to analysis the model due to the empty the tensor, fixed it by filtering the empty tensor Test Plan: Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]

pytorch-bot bot added the ciflow/default label Mar 13, 2022

facebook-github-bot added the cla signed label Mar 13, 2022

terrychenism requested a review from vkuzo March 13, 2022 17:57

terrychenism requested a review from jerryzh168 March 13, 2022 17:57

suo removed the ciflow/default label Mar 22, 2022

jerryzh168 reviewed Mar 23, 2022

View reviewed changes

torch/ao/ns/_numeric_suite.py Show resolved Hide resolved

vkuzo requested changes Mar 24, 2022

View reviewed changes

vkuzo reviewed Mar 29, 2022

View reviewed changes

vkuzo approved these changes Mar 29, 2022

View reviewed changes

pytorchmergebot closed this in 3c70146 Mar 31, 2022

facebook-github-bot deleted the gh/terrychenism/22/head branch April 3, 2022 14:16

WBobby mentioned this pull request Aug 17, 2022

Add ROCm5.2.3/AMDGPU support for PyTorch WBobby/pytorch#2

Closed

[quant][ns] Fix ns tool bug for mobilenetv2/v3 #74149

[quant][ns] Fix ns tool bug for mobilenetv2/v3 #74149

Conversation

terrychenism commented Mar 13, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pytorch-bot bot commented Mar 13, 2022

⚛️ CI Flow

Uh oh!

facebook-github-bot commented Mar 13, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful links

💊 CI failures summary and remediations

🕵️ 3 new failures recognized by patterns

pull / linux-xenial-cuda11.3-py3.7-gcc7-bazel-test / build-and-test (1/3)

pull / linux-xenial-cuda11.3-py3.7-gcc7 / build (2/3)

pull / deploy-linux-xenial-cuda11.3-py3.7-gcc7 / build (3/3)

1 failure not recognized by patterns:

Uh oh!

terrychenism commented Mar 13, 2022

Uh oh!

terrychenism commented Mar 14, 2022

Uh oh!

terrychenism commented Mar 14, 2022

Uh oh!

vkuzo commented Mar 15, 2022

Uh oh!

jerryzh168 Mar 23, 2022

Choose a reason for hiding this comment

Uh oh!

vkuzo Mar 29, 2022

Choose a reason for hiding this comment

Uh oh!

terrychenism Mar 29, 2022

Choose a reason for hiding this comment

Uh oh!

vkuzo Mar 29, 2022

Choose a reason for hiding this comment

Uh oh!

terrychenism Mar 29, 2022

Choose a reason for hiding this comment

Uh oh!

Uh oh!

vkuzo left a comment

Choose a reason for hiding this comment

Uh oh!

terrychenism commented Mar 24, 2022

Uh oh!

terrychenism commented Mar 24, 2022

Uh oh!

vkuzo Mar 29, 2022

Choose a reason for hiding this comment

Uh oh!

terrychenism Mar 29, 2022

Choose a reason for hiding this comment

Uh oh!

terrychenism commented Mar 29, 2022

Uh oh!

terrychenism commented Mar 29, 2022

Uh oh!

vkuzo left a comment

Choose a reason for hiding this comment

Uh oh!

terrychenism commented Mar 30, 2022

Uh oh!

terrychenism commented Mar 30, 2022

Uh oh!

terrychenism commented Mar 30, 2022

Uh oh!

github-actions bot commented Mar 31, 2022

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

6 participants

terrychenism commented Mar 13, 2022 •

edited

Loading

facebook-github-bot commented Mar 13, 2022 •

edited

Loading