mirror of
https://github.com/nod-ai/AMD-SHARK-Studio.git
synced 2026-02-19 11:56:43 -05:00
cb509343d9
- fix setup_venv.sh for benchmarks/imports etc. - fix torch benchmarks in SharkBenchmarkRunner - generate SD artifacts using build_tools/stable_diffusion_testing.py and --import_mlir - decouple SD gen from tank/generate_sharktank for now
26 lines
3.3 KiB
CSV
26 lines
3.3 KiB
CSV
model_name, use_tracing, model_type, dynamic, mlir_type, decompose, param_count, tags, notes
|
|
efficientnet_b0,True,vision,False,linalg,False,5.3M,"image-classification;cnn;conv2d;depthwise-conv","Smallest EfficientNet variant with 224x224 input"
|
|
efficientnet_b7,True,vision,False,linalg,False,66M,"image-classification;cnn;conv2d;depthwise-conv","Largest EfficientNet variant with 600x600 input"
|
|
microsoft/MiniLM-L12-H384-uncased,True,hf,True,linalg,False,66M,"nlp;bert-variant;transformer-encoder","Large version has 12 layers; 384 hidden size; Smaller than BERTbase (66M params vs 109M params)"
|
|
bert-base-uncased,True,hf,True,linalg,False,109M,"nlp;bert-variant;transformer-encoder","12 layers; 768 hidden; 12 attention heads"
|
|
bert-base-cased,True,hf,True,linalg,False,109M,"nlp;bert-variant;transformer-encoder","12 layers; 768 hidden; 12 attention heads"
|
|
google/mobilebert-uncased,True,hf,True,linalg,False,25M,"nlp,bert-variant,transformer-encoder,mobile","24 layers, 512 hidden size, 128 embedding"
|
|
resnet18,False,vision,True,linalg,False,11M,"cnn,image-classification,residuals,resnet-variant","1 7x7 conv2d and the rest are 3x3 conv2d"
|
|
resnet50,False,vision,True,linalg,False,23M,"cnn,image-classification,residuals,resnet-variant","Bottlenecks with only conv2d (1x1 conv -> 3x3 conv -> 1x1 conv blocks)"
|
|
resnet101,False,vision,True,linalg,False,29M,"cnn,image-classification,residuals,resnet-variant","Bottlenecks with only conv2d (1x1 conv -> 3x3 conv -> 1x1 conv blocks)"
|
|
squeezenet1_0,False,vision,True,linalg,False,1.25M,"cnn,image-classification,mobile,parallel-layers","Parallel conv2d (1x1 conv to compress -> (3x3 expand | 1x1 expand) -> concat)"
|
|
wide_resnet50_2,False,vision,True,linalg,False,69M,"cnn,image-classification,residuals,resnet-variant","Resnet variant where model depth is decreased and width is increased."
|
|
mobilenet_v3_small,False,vision,True,linalg,False,2.5M,"image-classification,cnn,mobile",N/A
|
|
google/vit-base-patch16-224,True,hf_img_cls,False,linalg,False,86M,"image-classification,vision-transformer,transformer-encoder",N/A
|
|
microsoft/resnet-50,True,hf_img_cls,False,linalg,False,23M,"image-classification,cnn,residuals,resnet-variant","Bottlenecks with only conv2d (1x1 conv -> 3x3 conv -> 1x1 conv blocks)"
|
|
facebook/deit-small-distilled-patch16-224,True,hf_img_cls,False,linalg,False,22M,"image-classification,vision-transformer,cnn",N/A
|
|
microsoft/beit-base-patch16-224-pt22k-ft22k,True,hf_img_cls,False,linalg,False,86M,"image-classification,transformer-encoder,bert-variant,vision-transformer",N/A
|
|
nvidia/mit-b0,True,hf_img_cls,False,linalg,False,3.7M,"image-classification,transformer-encoder",SegFormer
|
|
mnasnet1_0,False,vision,True,linalg,False,-,"cnn, torchvision, mobile, architecture-search","Outperforms other mobile CNNs on Accuracy vs. Latency"
|
|
bert-large-uncased,True,hf,True,linalg,False,330M,"nlp;bert-variant;transformer-encoder","24 layers, 1024 hidden units, 16 attention heads"
|
|
bert-base-uncased,True,hf,False,stablehlo,False,109M,"nlp;bert-variant;transformer-encoder","12 layers; 768 hidden; 12 attention heads"
|
|
gpt2,True,hf_causallm,False,stablehlo,True,125M,"nlp;transformer-encoder","-"
|
|
facebook/opt-125m,True,hf,False,stablehlo,True,125M,"nlp;transformer-encoder","-"
|
|
distilgpt2,True,hf,False,stablehlo,True,88M,"nlp;transformer-encoder","-"
|
|
microsoft/deberta-v3-base,True,hf,False,stablehlo,True,88M,"nlp;transformer-encoder","-"
|