pip install -r requirements.txtTested environment:
Pytorch==1.12.1
Torchvision==0.13.1
python torchvision_pruning.pySuccessful Pruning: 77 Models
['ssdlite320_mobilenet_v3_large', 'ssd300_vgg16', 'fasterrcnn_resnet50_fpn', 'fasterrcnn_resnet50_fpn_v2', 'fasterrcnn_mobilenet_v3_large_320_fpn', 'fasterrcnn_mobilenet_v3_large_fpn', 'fcos_resnet50_fpn', 'keypointrcnn_resnet50_fpn', 'maskrcnn_resnet50_fpn_v2', 'retinanet_resnet50_fpn_v2', 'alexnet', 'vit_b_16', 'vit_b_32', 'vit_l_16', 'vit_l_32', 'vit_h_14', 'convnext_tiny', 'convnext_small', 'convnext_base', 'convnext_large', 'densenet121', 'densenet169', 'densenet201', 'densenet161', 'efficientnet_b0', 'efficientnet_b1', 'efficientnet_b2', 'efficientnet_b3', 'efficientnet_b4', 'efficientnet_b5', 'efficientnet_b6', 'efficientnet_b7', 'efficientnet_v2_s', 'efficientnet_v2_m', 'efficientnet_v2_l', 'googlenet', 'inception_v3', 'mnasnet0_5', 'mnasnet0_75', 'mnasnet1_0', 'mnasnet1_3', 'mobilenet_v2', 'mobilenet_v3_large', 'mobilenet_v3_small', 'regnet_y_400mf', 'regnet_y_800mf', 'regnet_y_1_6gf', 'regnet_y_3_2gf', 'regnet_y_8gf', 'regnet_y_16gf', 'regnet_y_32gf', 'regnet_y_128gf', 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152', 'resnext50_32x4d', 'resnext101_32x8d', 'wide_resnet50_2', 'wide_resnet101_2', 'fcn_resnet50', 'fcn_resnet101', 'deeplabv3_resnet50', 'deeplabv3_resnet101', 'deeplabv3_mobilenet_v3_large', 'lraspp_mobilenet_v3_large', 'squeezenet1_0', 'squeezenet1_1', 'vgg11', 'vgg13', 'vgg16', 'vgg19', 'vgg11_bn', 'vgg13_bn', 'vgg16_bn', 'vgg19_bn']
Unsuccessful Pruning: 8 Models
['raft_large', 'swin_t', 'swin_s', 'swin_b', 'shufflenet_v2_x0_5', 'shufflenet_v2_x1_0', 'shufflenet_v2_x1_5', 'shufflenet_v2_x2_0']
==============Before pruning=================
Model Name: vit_b_32
VisionTransformer(
(conv_proj): Conv2d(3, 768, kernel_size=(32, 32), stride=(32, 32))
(encoder): Encoder(
(dropout): Dropout(p=0.0, inplace=False)
(layers): Sequential(
(encoder_layer_0): EncoderBlock(
(ln_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(self_attention): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(dropout): Dropout(p=0.0, inplace=False)
(ln_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(mlp): MLPBlock(
(0): Linear(in_features=768, out_features=3072, bias=True)
(1): GELU(approximate=none)
(2): Dropout(p=0.0, inplace=False)
(3): Linear(in_features=3072, out_features=768, bias=True)
(4): Dropout(p=0.0, inplace=False)
)
)
...
(encoder_layer_10): EncoderBlock(
(ln_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(self_attention): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(dropout): Dropout(p=0.0, inplace=False)
(ln_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(mlp): MLPBlock(
(0): Linear(in_features=768, out_features=3072, bias=True)
(1): GELU(approximate=none)
(2): Dropout(p=0.0, inplace=False)
(3): Linear(in_features=3072, out_features=768, bias=True)
(4): Dropout(p=0.0, inplace=False)
)
)
(encoder_layer_11): EncoderBlock(
(ln_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(self_attention): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
)
(dropout): Dropout(p=0.0, inplace=False)
(ln_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
(mlp): MLPBlock(
(0): Linear(in_features=768, out_features=3072, bias=True)
(1): GELU(approximate=none)
(2): Dropout(p=0.0, inplace=False)
(3): Linear(in_features=3072, out_features=768, bias=True)
(4): Dropout(p=0.0, inplace=False)
)
)
)
(ln): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
)
(heads): Sequential(
(head): Linear(in_features=768, out_features=1000, bias=True)
)
)
torch.Size([1, 1, 384]) torch.Size([1, 50, 384])
==============After pruning=================
VisionTransformer(
(conv_proj): Conv2d(3, 384, kernel_size=(32, 32), stride=(32, 32))
(encoder): Encoder(
(dropout): Dropout(p=0.0, inplace=False)
(layers): Sequential(
(encoder_layer_0): EncoderBlock(
(ln_1): LayerNorm((384,), eps=1e-06, elementwise_affine=True)
(self_attention): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=384, out_features=384, bias=True)
)
(dropout): Dropout(p=0.0, inplace=False)
(ln_2): LayerNorm((384,), eps=1e-06, elementwise_affine=True)
(mlp): MLPBlock(
(0): Linear(in_features=384, out_features=1536, bias=True)
(1): GELU(approximate=none)
(2): Dropout(p=0.0, inplace=False)
(3): Linear(in_features=1536, out_features=384, bias=True)
(4): Dropout(p=0.0, inplace=False)
)
)
...
(encoder_layer_10): EncoderBlock(
(ln_1): LayerNorm((384,), eps=1e-06, elementwise_affine=True)
(self_attention): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=384, out_features=384, bias=True)
)
(dropout): Dropout(p=0.0, inplace=False)
(ln_2): LayerNorm((384,), eps=1e-06, elementwise_affine=True)
(mlp): MLPBlock(
(0): Linear(in_features=384, out_features=1536, bias=True)
(1): GELU(approximate=none)
(2): Dropout(p=0.0, inplace=False)
(3): Linear(in_features=1536, out_features=384, bias=True)
(4): Dropout(p=0.0, inplace=False)
)
)
(encoder_layer_11): EncoderBlock(
(ln_1): LayerNorm((384,), eps=1e-06, elementwise_affine=True)
(self_attention): MultiheadAttention(
(out_proj): NonDynamicallyQuantizableLinear(in_features=384, out_features=384, bias=True)
)
(dropout): Dropout(p=0.0, inplace=False)
(ln_2): LayerNorm((384,), eps=1e-06, elementwise_affine=True)
(mlp): MLPBlock(
(0): Linear(in_features=384, out_features=1536, bias=True)
(1): GELU(approximate=none)
(2): Dropout(p=0.0, inplace=False)
(3): Linear(in_features=1536, out_features=384, bias=True)
(4): Dropout(p=0.0, inplace=False)
)
)
)
(ln): LayerNorm((384,), eps=1e-06, elementwise_affine=True)
)
(heads): Sequential(
(head): Linear(in_features=384, out_features=1000, bias=True)
)
)
Pruning vit_b_32:
Params: 88224232 => 22878952
Output: torch.Size([1, 1000])
------------------------------------------------------