microsoft/resnet-18
Original11.7Mparameters
Fixture11.7Mparameters
Layer stacks1compared
Findings0to review
✓ Same architecture, smaller
Every module class, layer kind and checked property of the original is in the fixture.
Layer stacks
One square per layer, colored by kind: the layer's module classes and type attributes. Hover a square for its index and kind.
resnet.encoder.stages
Original · 4
Fixture · 4
| Kind | Original | Fixture | |
|---|---|---|---|
| no ShortCut | 1 | 1 | ✓ kept |
| ShortCut | 3 | 3 | ✓ kept |
Where the parameters are
Share of each model's parameters per component. Vocabulary and patch sizes are kept, so embeddings usually take a larger share of the fixture.
Original
Fixture
| Component | Original | Share | Fixture | Share |
|---|---|---|---|---|
| resnet.encoder.stages | 11.2M | 95.5% | 11.2M | 95.5% |
| classifier.1 | 513.0K | 4.4% | 513.0K | 4.4% |
| resnet.embedder | 9.5K | 0.1% | 9.5K | 0.1% |
Preserved properties
| Config | Property | Original | Fixture | |
|---|---|---|---|---|
| model | model_type | resnet | resnet | ✓ kept |
| model | hidden_act | relu | relu | ✓ kept |
| model | num_channels | 3 | 3 | ✓ kept |
Module classes
Instances of each class in the built model (prefix ResNet omitted).
| Class | Original | Fixture |
|---|---|---|
| BatchNorm2d | 20 | 20 |
| Conv2d | 20 | 20 |
| ReLU | 17 | 17 |
| ConvLayer | 17 | 17 |
| Identity | 13 | 13 |
| Sequential | 13 | 13 |
| BasicLayer | 8 | 8 |
| Stage | 4 | 4 |
| ShortCut | 3 | 3 |
| AdaptiveAvgPool2d | 1 | 1 |
| Flatten | 1 | 1 |
| Linear | 1 | 1 |
| MaxPool2d | 1 | 1 |
| ModuleList | 1 | 1 |
| Embeddings | 1 | 1 |
| Encoder | 1 | 1 |
| ForImageClassification | 1 | 1 |
| Model | 1 | 1 |
Config changes
0 fields changed, 20 unchanged.
| Field | Original | Fixture |
|---|