Types & classes — github.com/Yang-YiFan/DiracDeltaNet

CodeHub MCPcopy Create free account

hub / github.com/Yang-YiFan/DiracDeltaNet / types & classes

Types & classes17 in github.com/Yang-YiFan/DiracDeltaNet

⨍ Functions 52 ◇ Types & classes 17

↓ 14 callersClassQuantConv_init

models/shufflenetv2.py:23

↓ 12 callersClassQuantConv_init

models/diracdeltanet.py:67

↓ 6 callersClassActQuant_init

models/diracdeltanet.py:23

↓ 6 callersClassShift3x3

models/diracdeltanet.py:135

↓ 4 callersClassActQuant_init_fixed

models/diracdeltanet.py:44

↓ 2 callersClassModelRefineryWrapper

Convenient wrapper class to train a model with a label refinery.

extensions/model_refinery_wrapper.py:5

↓ 2 callersClassQuantLinear_init

models/diracdeltanet.py:103

↓ 2 callersClassRefineryLoss

The KL-Divergence loss for the model and refined labels output. output must be a pair of (model_output, refined_labels), both NxC tensors.

extensions/refinery_loss.py:8

↓ 1 callersClassBottleneck

models/resnet50.py:67

↓ 1 callersClassDiracDeltaBlock

models/diracdeltanet.py:168

↓ 1 callersClassDiracDeltaNet

models/diracdeltanet.py:276

↓ 1 callersClassShuffleBlock

models/shufflenetv2.py:56

↓ 1 callersClassShuffleNetv2

models/shufflenetv2.py:166

Randomly mask out one or more patches from an image. Args: n_holes (int): Number of patches to cut out of each image. length

extensions/utils.py:130

models/resnet50.py:7

models/diracdeltanet.py:13

models/shufflenetv2.py:12