Netron ouptut fix

[CharlieL7]

Fixing a bug with the output dims formatting. Some update with Netron broke the string output on attributes so disabling it.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.29%. Comparing base (810b3f2) to head (2d62c3b).
Report is 4 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3778   +/-   ##
========================================
  Coverage    92.29%   92.29%           
========================================
  Files          519      519           
  Lines        22217    22217           
========================================
  Hits         20505    20505           
  Misses        1712     1712           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[migraphx-bot]

Test	Batch	Rate new bbcfdb	Rate old 838930	Diff	Compare
torchvision-resnet50	64	3,226.68	3,251.92	-0.78%	✅
torchvision-resnet50_fp16	64	6,939.32	6,922.88	0.24%	✅
torchvision-densenet121	32	2,446.80	2,455.98	-0.37%	✅
torchvision-densenet121_fp16	32	4,178.92	4,165.57	0.32%	✅
torchvision-inceptionv3	32	1,617.79	1,629.73	-0.73%	✅
torchvision-inceptionv3_fp16	32	2,700.17	2,713.61	-0.50%	✅
cadene-inceptionv4	16	755.08	763.12	-1.05%	✅
cadene-resnext64x4	16	799.32	813.22	-1.71%	✅
slim-mobilenet	64	7,037.46	7,458.91	-5.65%	🔴
slim-nasnetalarge	64	203.77	208.64	-2.34%	✅
slim-resnet50v2	64	3,414.68	3,443.66	-0.84%	✅
bert-mrpc-onnx	8	1,131.31	1,147.38	-1.40%	✅
bert-mrpc-tf	1	484.47	486.76	-0.47%	✅
pytorch-examples-wlang-gru	1	479.13	477.81	0.28%	✅
pytorch-examples-wlang-lstm	1	441.20	443.02	-0.41%	✅
torchvision-resnet50_1	1	802.96	806.98	-0.50%	✅
cadene-dpn92_1	1	424.60	426.16	-0.36%	✅
cadene-resnext101_1	1	384.05	384.65	-0.16%	✅
onnx-taau-downsample	1	373.04	373.98	-0.25%	✅
dlrm-criteoterabyte	1	32.54	33.29	-2.24%	✅
dlrm-criteoterabyte_fp16	1	51.06	52.62	-2.97%	✅
agentmodel	1	8,815.85	8,622.99	2.24%	✅
unet_fp16	2	58.03	58.29	-0.46%	✅
resnet50v1_fp16	1	1,035.51	1,032.72	0.27%	✅
resnet50v1_int8	1	787.23	1,031.11	-23.65%	🔴
bert_base_cased_fp16	64	1,172.28	1,181.13	-0.75%	✅
bert_large_uncased_fp16	32	362.38	365.27	-0.79%	✅
bert_large_fp16	1	201.34	199.02	1.17%	✅
distilgpt2_fp16	16	2,216.01	2,226.07	-0.45%	✅
yolov5s	1	521.01	522.70	-0.32%	✅
tinyllama	1	43.59	43.59	0.00%	✅
vicuna-fastchat	1	174.20	172.22	1.15%	✅
whisper-tiny-encoder	1	406.07	418.31	-2.93%	✅
whisper-tiny-decoder	1	401.94	430.35	-6.60%	🔴

This build is not recommended to merge 🔴

[migraphx-bot]

     ✅ bert-mrpc-onnx: PASSED: MIGraphX meets tolerance

     ✅ bert-mrpc-tf: PASSED: MIGraphX meets tolerance

     ✅ pytorch-examples-wlang-gru: PASSED: MIGraphX meets tolerance

     ✅ pytorch-examples-wlang-lstm: PASSED: MIGraphX meets tolerance

     ✅ torchvision-resnet50_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-dpn92_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-resnext101_1: PASSED: MIGraphX meets tolerance

     ✅ dlrm-criteoterabyte: PASSED: MIGraphX meets tolerance

     ✅ agentmodel: PASSED: MIGraphX meets tolerance

     ✅ unet: PASSED: MIGraphX meets tolerance

     ✅ resnet50v1: PASSED: MIGraphX meets tolerance

     ✅ bert_base_cased_fp16: PASSED: MIGraphX meets tolerance

🔴bert_large_uncased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

     ✅ bert_large: PASSED: MIGraphX meets tolerance

     ✅ yolov5s: PASSED: MIGraphX meets tolerance

     ✅ tinyllama: PASSED: MIGraphX meets tolerance

     ✅ vicuna-fastchat: PASSED: MIGraphX meets tolerance

     ✅ whisper-tiny-encoder: PASSED: MIGraphX meets tolerance

     ✅ whisper-tiny-decoder: PASSED: MIGraphX meets tolerance

     ✅ distilgpt2_fp16: PASSED: MIGraphX meets tolerance

[pfultz2]

Does the std::back_inserter not work with value class?

[pfultz2]

I see, its supposed to be an object.

[pfultz2]

Actually value::object{} would be cleaner here.

[CharlieL7]

Yes, didn't realize that's how it worked.