Spaces:
Running
Running
| # For more details on models, see https://pytorch.org/vision/main/models.html | |
| # EfficientNet models: Designed for efficiency with compound scaling of depth, width, and resolution. | |
| # These models balance accuracy and computational efficiency, ideal for resource-constrained environments. | |
| efficientnet_b0: | |
| metrics: | |
| Acc@1: 77.692 # Top-1 accuracy on ImageNet | |
| Acc@5: 93.532 # Top-5 accuracy on ImageNet | |
| GFLOPS: 0.39 # Computational complexity | |
| Params: 5.3M # Number of parameters | |
| model_fn: models.efficientnet_b0 | |
| resolution: 224 # Input image resolution | |
| weights: models.EfficientNet_B0_Weights.IMAGENET1K_V1 # Pretrained weights on ImageNet | |
| efficientnet_b1: | |
| metrics: | |
| Acc@1: 78.642 | |
| Acc@5: 94.186 | |
| GFLOPS: 0.69 | |
| Params: 7.8M | |
| model_fn: models.efficientnet_b1 | |
| resolution: 240 | |
| weights: models.EfficientNet_B1_Weights.IMAGENET1K_V1 | |
| efficientnet_b2: | |
| metrics: | |
| Acc@1: 80.608 | |
| Acc@5: 95.31 | |
| GFLOPS: 1.09 | |
| Params: 9.1M | |
| model_fn: models.efficientnet_b2 | |
| resolution: 260 | |
| weights: models.EfficientNet_B2_Weights.IMAGENET1K_V1 | |
| efficientnet_b3: | |
| metrics: | |
| Acc@1: 82.008 | |
| Acc@5: 96.054 | |
| GFLOPS: 1.83 | |
| Params: 12.2M | |
| model_fn: models.efficientnet_b3 | |
| resolution: 300 | |
| weights: models.EfficientNet_B3_Weights.IMAGENET1K_V1 | |
| efficientnet_b4: | |
| metrics: | |
| Acc@1: 83.384 | |
| Acc@5: 96.594 | |
| GFLOPS: 4.39 | |
| Params: 19.3M | |
| model_fn: models.efficientnet_b4 | |
| resolution: 380 | |
| weights: models.EfficientNet_B4_Weights.IMAGENET1K_V1 | |
| efficientnet_b5: | |
| metrics: | |
| Acc@1: 83.444 | |
| Acc@5: 96.628 | |
| GFLOPS: 10.27 | |
| Params: 30.4M | |
| model_fn: models.efficientnet_b5 | |
| resolution: 456 | |
| weights: models.EfficientNet_B5_Weights.IMAGENET1K_V1 | |
| efficientnet_b6: | |
| metrics: | |
| Acc@1: 84.008 | |
| Acc@5: 96.916 | |
| GFLOPS: 19.07 | |
| Params: 43.0M | |
| model_fn: models.efficientnet_b6 | |
| resolution: 528 | |
| weights: models.EfficientNet_B6_Weights.IMAGENET1K_V1 | |
| efficientnet_b7: | |
| metrics: | |
| Acc@1: 84.122 | |
| Acc@5: 96.908 | |
| GFLOPS: 37.75 | |
| Params: 66.3M | |
| model_fn: models.efficientnet_b7 | |
| resolution: 600 | |
| weights: models.EfficientNet_B7_Weights.IMAGENET1K_V1 | |
| # EfficientNet V2 models: Improved training efficiency and performance over V1. | |
| # These models use progressive learning and optimized scaling for better accuracy. | |
| efficientnet_v2_l: | |
| metrics: | |
| Acc@1: 85.808 | |
| Acc@5: 97.788 | |
| GFLOPS: 56.08 | |
| Params: 118.5M | |
| model_fn: models.efficientnet_v2_l | |
| resolution: 480 | |
| weights: models.EfficientNet_V2_L_Weights.IMAGENET1K_V1 | |
| efficientnet_v2_m: | |
| metrics: | |
| Acc@1: 85.112 | |
| Acc@5: 97.156 | |
| GFLOPS: 24.58 | |
| Params: 54.1M | |
| model_fn: models.efficientnet_v2_m | |
| resolution: 480 | |
| weights: models.EfficientNet_V2_M_Weights.IMAGENET1K_V1 | |
| efficientnet_v2_s: | |
| metrics: | |
| Acc@1: 84.228 | |
| Acc@5: 96.878 | |
| GFLOPS: 8.37 | |
| Params: 21.5M | |
| model_fn: models.efficientnet_v2_s | |
| resolution: 384 | |
| weights: models.EfficientNet_V2_S_Weights.IMAGENET1K_V1 | |
| # RegNet models: Designed for scalability and efficiency with a focus on network design. | |
| # These models optimize for both accuracy and computational efficiency. | |
| regnet_y_128gf: | |
| metrics: | |
| Acc@1: 86.068 # High accuracy but computationally expensive | |
| Acc@5: 97.844 | |
| GFLOPS: 127.52 | |
| Params: 644.8M | |
| model_fn: models.regnet_y_128gf | |
| resolution: 224 | |
| weights: models.RegNet_Y_128GF_Weights.IMAGENET1K_SWAG_LINEAR_V1 | |
| regnet_y_16gf: | |
| metrics: | |
| Acc@1: 82.886 | |
| Acc@5: 96.328 | |
| GFLOPS: 15.91 | |
| Params: 83.6M | |
| model_fn: models.regnet_y_16gf | |
| resolution: 224 | |
| weights: models.RegNet_Y_16GF_Weights.IMAGENET1K_V2 | |
| regnet_y_1_6gf: | |
| metrics: | |
| Acc@1: 80.876 | |
| Acc@5: 95.444 | |
| GFLOPS: 1.61 | |
| Params: 11.2M | |
| model_fn: models.regnet_y_1_6gf | |
| resolution: 224 | |
| weights: models.RegNet_Y_1_6GF_Weights.IMAGENET1K_V2 | |
| regnet_y_32gf: | |
| metrics: | |
| Acc@1: 83.368 | |
| Acc@5: 96.498 | |
| GFLOPS: 32.28 | |
| Params: 145.0M | |
| model_fn: models.regnet_y_32gf | |
| resolution: 224 | |
| weights: models.RegNet_Y_32GF_Weights.IMAGENET1K_V2 | |
| regnet_y_3_2gf: | |
| metrics: | |
| Acc@1: 81.982 | |
| Acc@5: 95.972 | |
| GFLOPS: 3.18 | |
| Params: 19.4M | |
| model_fn: models.regnet_y_3_2gf | |
| resolution: 224 | |
| weights: models.RegNet_Y_3_2GF_Weights.IMAGENET1K_V2 | |
| regnet_y_400mf: | |
| metrics: | |
| Acc@1: 75.804 | |
| Acc@5: 92.742 | |
| GFLOPS: 0.4 | |
| Params: 4.3M | |
| model_fn: models.regnet_y_400mf | |
| resolution: 224 | |
| weights: models.RegNet_Y_400MF_Weights.IMAGENET1K_V2 | |
| regnet_y_800mf: | |
| metrics: | |
| Acc@1: 78.828 | |
| Acc@5: 94.502 | |
| GFLOPS: 0.83 | |
| Params: 6.4M | |
| model_fn: models.regnet_y_800mf | |
| resolution: 224 | |
| weights: models.RegNet_Y_800MF_Weights.IMAGENET1K_V2 | |
| regnet_y_8gf: | |
| metrics: | |
| Acc@1: 82.828 | |
| Acc@5: 96.33 | |
| GFLOPS: 8.47 | |
| Params: 39.4M | |
| model_fn: models.regnet_y_8gf | |
| resolution: 224 | |
| weights: models.RegNet_Y_8GF_Weights.IMAGENET1K_V2 | |
| # Vision Transformer (ViT) models: Transformer-based architecture for image classification. | |
| # These models excel in capturing long-range dependencies but require significant compute for larger variants. | |
| vit_b_16: | |
| metrics: | |
| Acc@1: 81.072 # Base ViT model with balanced accuracy and efficiency | |
| Acc@5: 95.318 | |
| GFLOPS: 17.56 | |
| Params: 86.6M | |
| model_fn: models.vit_b_16 | |
| resolution: 224 | |
| weights: models.ViT_B_16_Weights.IMAGENET1K_V1 | |
| vit_b_32: | |
| metrics: | |
| Acc@1: 75.912 # Smaller patch size version of ViT, lower accuracy but fewer computations | |
| Acc@5: 92.466 | |
| GFLOPS: 4.41 | |
| Params: 88.2M | |
| model_fn: models.vit_b_32 | |
| resolution: 224 | |
| weights: models.ViT_B_32_Weights.IMAGENET1K_V1 | |
| vit_h_14: | |
| metrics: | |
| Acc@1: 88.552 # High-performance ViT model with very high accuracy and computational cost | |
| Acc@5: 98.694 | |
| GFLOPS: 1016.72 | |
| Params: 633.5M | |
| model_fn: models.vit_h_14 | |
| resolution: 224 | |
| weights: models.ViT_H_14_Weights.IMAGENET1K_SWAG_E2E_V1 | |
| vit_l_16: | |
| metrics: | |
| Acc@1: 79.662 # Larger ViT model with improved accuracy over base models | |
| Acc@5: 94.638 | |
| GFLOPS: 61.55 | |
| Params: 304.3M | |
| model_fn: models.vit_l_16 | |
| resolution: 224 | |
| weights: models.ViT_L_16_Weights.IMAGENET1K_V1 | |
| vit_l_32: | |
| metrics: | |
| Acc@1: 76.972 # Larger ViT with larger patch size, trading accuracy for reduced compute | |
| Acc@5: 93.07 | |
| GFLOPS: 15.38 | |
| Params: 306.5M | |
| model_fn: models.vit_l_32 | |
| resolution: 224 | |
| weights: models.ViT_L_32_Weights.IMAGENET1K_V1 | |