Update accuracy checker to support --disable-offload-copy

[kahmed10]

Without this change, the accuracy checker with --disable-offload-copy will fail.

[codecov]

Codecov Report

Merging #2348 (dc3243d) into develop (c399062) will not change coverage.
The diff coverage is n/a.

❗ Current head dc3243d differs from pull request most recent head e8e1426. Consider uploading reports for the commit e8e1426 to get more accurate results

@@           Coverage Diff            @@
##           develop    #2348   +/-   ##
========================================
  Coverage    91.36%   91.36%           
========================================
  Files          439      439           
  Lines        16493    16493           
========================================
  Hits         15069    15069           
  Misses        1424     1424           

[CharlieL7]

LGTM

[migraphx-bot]

Test	Batch	Rate new e8e142	Rate old 5139b9	Diff	Compare
torchvision-resnet50	64	2,850.87	2,854.10	-0.11%	✅
torchvision-resnet50_fp16	64	6,483.76	6,483.03	0.01%	✅
torchvision-densenet121	32	2,107.54	2,097.00	0.50%	✅
torchvision-densenet121_fp16	32	3,673.03	3,671.51	0.04%	✅
torchvision-inceptionv3	32	1,594.82	1,596.36	-0.10%	✅
torchvision-inceptionv3_fp16	32	2,592.86	2,593.28	-0.02%	✅
cadene-inceptionv4	16	707.31	707.70	-0.05%	✅
cadene-resnext64x4	16	697.36	697.45	-0.01%	✅
slim-mobilenet	64	8,344.55	8,362.00	-0.21%	✅
slim-nasnetalarge	64	226.95	227.09	-0.06%	✅
slim-resnet50v2	64	2,676.49	2,678.49	-0.07%	✅
bert-mrpc-onnx	8	824.50	824.15	0.04%	✅
bert-mrpc-tf	1	388.61	387.64	0.25%	✅
pytorch-examples-wlang-gru	1	299.61	302.78	-1.05%	✅
pytorch-examples-wlang-lstm	1	316.43	315.71	0.23%	✅
torchvision-resnet50_1	1	597.52	598.65	-0.19%	✅
torchvision-inceptionv3_1	1	340.06	338.96	0.33%	✅
cadene-dpn92_1	1	399.86	394.33	1.40%	✅
cadene-resnext101_1	1	329.54	328.69	0.26%	✅
slim-vgg16_1	1	463.53	465.01	-0.32%	✅
slim-mobilenet_1	1	2,046.07	2,040.61	0.27%	✅
slim-inceptionv4_1	1	214.62	217.81	-1.46%	✅
onnx-taau-downsample	1	307.04	306.34	0.23%	✅
dlrm-criteoterabyte	1	21.71	21.67	0.19%	✅
dlrm-criteoterabyte_fp16	1	40.69	40.75	-0.15%	✅
agentmodel	1	5,783.52	5,826.96	-0.75%	✅
unet_fp16	2	55.96	56.00	-0.08%	✅
resnet50v1_fp16	1	948.45	931.01	1.87%	✅
bert_base_cased_fp16	64	970.32	970.67	-0.04%	✅
bert_large_uncased_fp16	32	304.83	305.11	-0.09%	✅
bert_large_fp16	1	166.60	166.86	-0.16%	✅
distilgpt2_fp16	16	1,279.20	1,279.97	-0.06%	✅

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

    :white_check_mark:cadene-dpn92_1: PASSED: MIGraphX meets tolerance

    :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

    :white_check_mark:resnet50v1: PASSED: MIGraphX meets tolerance

🔴bert_base_cased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

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

    :white_check_mark:bert_large: PASSED: MIGraphX meets tolerance

🔴distilgpt2_fp16: FAILED: MIGraphX is not within tolerance - check verbose output