Model card for resnet101.tv in1k A ResNet B image classification model. This model features: ReLU activations single layer 7x7 convolution with pooling 1x1 convolution shortcut downsample Trained on ImageNet 1k, original torchvision model weight. Model Details Model Type: Image classification / feature backbone Model Stats: Params (M): 44.5 GMACs: 7.8 Activations (M): 16.2 Image size: 224 x 224 Papers: Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 Original: https://github.com/pytorch/vision Model Usage Image Classification Feature Map Extraction Image Embeddings Model Comparison Explore the dataset and runtime metrics of this model in timm model results. model img size top1 top5 param count gmacs macts img/sec seresnextaa101d 32x8d.sw in12k ft in1k 288 320 86.72 98.17 93.6 35.2 69.7 451 seresnextaa101d 32x8d.sw in12k ft in1k 288 288 86.51 98.08 93.6 28.5 56.4 560 seresnextaa101d 32x8d.sw in12k ft in1k 288 86.49 98.03 93.6 28.5 56.4 557 seresnextaa101d 32x8d.sw in12k ft in1k 224 85.96 97.82 93.6 17.2 34.2 923 resnext101 32x32d.fb wsl ig1b ft in1k 224 85.11 97.44 468.5 87.3 91.1 254 resnetrs420.tf in1k 416 85.0 97.12 191.9 108.4 213.8 134 ecaresnet269…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy