Add Metadata
Your model lacks metadata. Adding metadata gives context on how your model was trained.
Take the following JSON template, fill it in with your model's correct values:
{ "Parameters": 62000000 "FLOPs": 524000000 "Training Time": "24 hours", "Training Resources": "8 NVIDIA V100 GPUs", "Training Data": ["ImageNet, Instagram"], "Training Techniques": ["AdamW, CutMix"]}
[INSERT ADVICE HERE]
rwightman / pytorch-image-models
Last updated on Feb 14, 2021
resnet18
Parameters 12 Million
FLOPs 2 Billion
File Size 44.66 MB
Training Data ImageNet
Training Resources
Training Time
Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
---|---|
ID | resnet18 |
Crop Pct | 0.875 |
Image Size | 224 |
Interpolation | bilinear |
SHOW MORE | |
SHOW LESS |
resnet26
Parameters 16 Million
FLOPs 3 Billion
File Size 61.16 MB
Training Data ImageNet
Training Resources
Training Time
Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
---|---|
ID | resnet26 |
Crop Pct | 0.875 |
Image Size | 224 |
Interpolation | bicubic |
SHOW MORE | |
SHOW LESS |
resnet34
Parameters 22 Million
FLOPs 5 Billion
File Size 83.25 MB
Training Data ImageNet
Training Resources
Training Time
Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
---|---|
ID | resnet34 |
Crop Pct | 0.875 |
Image Size | 224 |
Interpolation | bilinear |
SHOW MORE | |
SHOW LESS |
resnet50
Parameters 26 Million
FLOPs 5 Billion
File Size 97.74 MB
Training Data ImageNet
Training Resources
Training Time
Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
---|---|
ID | resnet50 |
Crop Pct | 0.875 |
Image Size | 224 |
Interpolation | bicubic |
SHOW MORE | |
SHOW LESS |
resnetblur50
Parameters 26 Million
FLOPs 7 Billion
File Size 97.74 MB
Training Data ImageNet
Training Resources
Training Time
Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax, Blur Pooling |
---|---|
ID | resnetblur50 |
Crop Pct | 0.875 |
Image Size | 224 |
Interpolation | bicubic |
SHOW MORE | |
SHOW LESS |
tv_resnet101
Parameters 45 Million
FLOPs 10 Billion
File Size 170.45 MB
Training Data ImageNet
Training Resources
Training Time
Training Techniques | SGD with Momentum, Weight Decay |
---|---|
Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
ID | tv_resnet101 |
LR | 0.1 |
Epochs | 90 |
Crop Pct | 0.875 |
LR Gamma | 0.1 |
Momentum | 0.9 |
Batch Size | 32 |
Image Size | 224 |
LR Step Size | 30 |
Weight Decay | 0.0001 |
Interpolation | bilinear |
SHOW MORE | |
SHOW LESS |
tv_resnet152
Parameters 60 Million
FLOPs 15 Billion
File Size 230.34 MB
Training Data ImageNet
Training Resources
Training Time
Training Techniques | SGD with Momentum, Weight Decay |
---|---|
Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
ID | tv_resnet152 |
LR | 0.1 |
Epochs | 90 |
Crop Pct | 0.875 |
LR Gamma | 0.1 |
Momentum | 0.9 |
Batch Size | 32 |
Image Size | 224 |
LR Step Size | 30 |
Weight Decay | 0.0001 |
Interpolation | bilinear |
SHOW MORE | |
SHOW LESS |
tv_resnet34
Parameters 22 Million
FLOPs 5 Billion
File Size 83.26 MB
Training Data ImageNet
Training Resources
Training Time
Training Techniques | SGD with Momentum, Weight Decay |
---|---|
Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
ID | tv_resnet34 |
LR | 0.1 |
Epochs | 90 |
Crop Pct | 0.875 |
LR Gamma | 0.1 |
Momentum | 0.9 |
Batch Size | 32 |
Image Size | 224 |
LR Step Size | 30 |
Weight Decay | 0.0001 |
Interpolation | bilinear |
SHOW MORE | |
SHOW LESS |
tv_resnet50
Parameters 26 Million
FLOPs 5 Billion
File Size 97.75 MB
Training Data ImageNet
Training Resources
Training Time
Training Techniques | SGD with Momentum, Weight Decay |
---|---|
Architecture | 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax |
ID | tv_resnet50 |
LR | 0.1 |
Epochs | 90 |
Crop Pct | 0.875 |
LR Gamma | 0.1 |
Momentum | 0.9 |
Batch Size | 32 |
Image Size | 224 |
LR Step Size | 30 |
Weight Decay | 0.0001 |
Interpolation | bilinear |
SHOW MORE | |
SHOW LESS |
README.md
Residual Networks, or ResNets, learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. Instead of hoping each few stacked layers directly fit a desired underlying mapping, residual nets let these layers fit a residual mapping. They stack residual blocks ontop of each other to form network: e.g. a ResNet-50 has fifty layers using these blocks.
How do I load this model?
To load a pretrained model:
import timmm = timm.create_model('resnet18', pretrained=True)m.eval()
Replace the model name with the variant you want to use, e.g. resnet18
. You can find the IDs in the model summaries at the top of this page.
How do I train this model?
You can follow the timm recipe scripts for training a new model afresh.
Citation
@article{DBLP:journals/corr/HeZRS15, author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun}, title = {Deep Residual Learning for Image Recognition}, journal = {CoRR}, volume = {abs/1512.03385}, year = {2015}, url = {http://arxiv.org/abs/1512.03385}, archivePrefix = {arXiv}, eprint = {1512.03385}, timestamp = {Wed, 17 Apr 2019 17:23:45 +0200}, biburl = {https://dblp.org/rec/journals/corr/HeZRS15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org}}
Image Classification on ImageNet
Image Classification on ImageNetMODEL | TOP 1 ACCURACY | TOP 5 ACCURACY |
---|---|---|
resnetblur50 | 79.29% | 94.64% |
resnet50 | 79.04% | 94.39% |
tv_resnet152 | 78.32% | 94.05% |
tv_resnet101 | 77.37% | 93.56% |
tv_resnet50 | 76.16% | 92.88% |
resnet26 | 75.29% | 92.57% |
resnet34 | 75.11% | 92.28% |
tv_resnet34 | 73.3% | 91.42% |
resnet18 | 69.74% | 89.09% |