Add fp16 flag to test runner to check models quantized to fp16

[pfultz2]

Also, added flags to adjust the tolerance.

[codecov]

Codecov Report

Merging #2182 (e9a9af6) into develop (752f13c) will not change coverage.
Report is 1 commits behind head on develop.
The diff coverage is n/a.

❗ Current head e9a9af6 differs from pull request most recent head 702f12f. Consider uploading reports for the commit 702f12f to get more accurate results

@@           Coverage Diff            @@
##           develop    #2182   +/-   ##
========================================
  Coverage    91.48%   91.48%           
========================================
  Files          426      426           
  Lines        15927    15927           
========================================
  Hits         14571    14571           
  Misses        1356     1356           

[TedThemistokleous]

Is this linked to a ticket in our project board?

[migraphx-bot]

Test	Batch	Rate new e24f19	Rate old 28fad2	Diff	Compare
torchvision-resnet50	64	2,281.15	2,282.65	-0.07%	✅
torchvision-resnet50_fp16	64	5,337.43	5,356.46	-0.36%	✅
torchvision-densenet121	32	1,823.03	1,829.72	-0.37%	✅
torchvision-densenet121_fp16	32	3,392.16	3,385.91	0.18%	✅
torchvision-inceptionv3	32	1,341.89	1,342.12	-0.02%	✅
torchvision-inceptionv3_fp16	32	2,591.37	2,584.17	0.28%	✅
cadene-inceptionv4	16	678.92	680.65	-0.25%	✅
cadene-resnext64x4	16	589.85	591.36	-0.25%	✅
slim-mobilenet	64	7,218.86	7,223.75	-0.07%	✅
slim-nasnetalarge	64	236.77	237.11	-0.14%	✅
slim-resnet50v2	64	2,525.54	2,527.89	-0.09%	✅
bert-mrpc-onnx	8	720.90	721.16	-0.04%	✅
bert-mrpc-tf	1	390.88	389.70	0.30%	✅
pytorch-examples-wlang-gru	1	302.51	301.30	0.40%	✅
pytorch-examples-wlang-lstm	1	307.49	315.88	-2.66%	✅
torchvision-resnet50_1	1	556.33	555.32	0.18%	✅
torchvision-inceptionv3_1	1	306.90	308.88	-0.64%	✅
cadene-dpn92_1	1	350.19	352.69	-0.71%	✅
cadene-resnext101_1	1	220.51	220.74	-0.10%	✅
slim-vgg16_1	1	224.26	224.38	-0.05%	✅
slim-mobilenet_1	1	1,462.52	1,495.73	-2.22%	✅
slim-inceptionv4_1	1	220.69	220.61	0.04%	✅
onnx-taau-downsample	1	323.08	322.60	0.15%	✅
dlrm-criteoterabyte	1	21.67	21.68	-0.05%	✅
dlrm-criteoterabyte_fp16	1	40.61	40.45	0.38%	✅
agentmodel	1	5,830.50	5,812.23	0.31%	✅
unet_fp16	2	55.06	55.07	-0.01%	✅

This build is OK for merge ✅

[migraphx-bot]

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

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

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

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

    :white_check_mark:torchvision-resnet50_1: PASSED: MIGraphX meets tolerance

🔴torchvision-inceptionv3_1: FAILED: MIGraphX is not within tolerance - check verbose output

🔴cadene-dpn92_1: FAILED: MIGraphX is not within tolerance - check verbose output

    :white_check_mark:cadene-resnext101_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:slim-vgg16_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:slim-mobilenet_1: PASSED: MIGraphX meets tolerance

🔴slim-inceptionv4_1: FAILED: MIGraphX is not within tolerance - check verbose output

    :white_check_mark:dlrm-criteoterabyte: PASSED: MIGraphX meets tolerance

    :white_check_mark:agentmodel: PASSED: MIGraphX meets tolerance

    :white_check_mark:unet: PASSED: MIGraphX meets tolerance