VGG(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(0_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)
** (1): ReLU(inplace=True)**
** (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (2_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (3): ReLU(inplace=True)**
** (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)**
** (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (5_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (6): ReLU(inplace=True)**
** (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (7_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (8): ReLU(inplace=True)**
** (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)**
** (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (10_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (11): ReLU(inplace=True)**
** (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (12_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (13): ReLU(inplace=True)**
** (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (14_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (15): ReLU(inplace=True)**
** (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)**
** (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (17_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (18): ReLU(inplace=True)**
** (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (19_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (20): ReLU(inplace=True)**
** (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (21_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (22): ReLU(inplace=True)**
** (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)**
** (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (24_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (25): ReLU(inplace=True)**
** (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (26_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (27): ReLU(inplace=True)**
** (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))**
** (28_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (29): ReLU(inplace=True)**
** (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)**
** )**
** (classifier): Sequential(**
** (0): Linear(in_features=25088, out_features=4096, bias=True)**
** (0_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (1): ReLU(inplace=True)**
** (2): Dropout(p=0.5, inplace=False)**
** (3): Linear(in_features=4096, out_features=4096, bias=True)**
** (3_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** (4): ReLU(inplace=True)**
** (5): Dropout(p=0.5, inplace=False)**
** (6): Linear(in_features=4096, out_features=1000, bias=True)**
** (6_linear_quant): LinearQuant(sf=None, bits=8, overflow_rate=0.000, counter=20)**
** )**
)
-
My model’s shape is like this.
-
I saw that hook is not work inner nn.seq module
-
and also when I tried that thing, the ofmap of feature.0 layer and ifmap of feature.0_linear_quant is different
-
Then, If I want conv2d or 0_linear_quant layer’s output feature map, what can I do?
import torch.nn as nn
import torch.utils.model_zoo as model_zoo
import math
all = [
** ‘VGG’, ‘vgg11’, ‘vgg11_bn’, ‘vgg13’, ‘vgg13_bn’, ‘vgg16’, ‘vgg16_bn’,**
** ‘vgg19_bn’, ‘vgg19’,**
]
model_urls = {
** ‘vgg11’: ‘https://download.pytorch.org/models/vgg11-bbd30ac9.pth’,**
** ‘vgg13’: ‘https://download.pytorch.org/models/vgg13-c768596a.pth’,**
** ‘vgg16’: ‘https://download.pytorch.org/models/vgg16-397923af.pth’,**
** ‘vgg19’: ‘https://download.pytorch.org/models/vgg19-dcbb9e9d.pth’,**
}
class VGG(nn.Module):
** def init(self, features, num_classes=1000):**
** super(VGG, self).init()**
** self.features = features**
** self.classifier = nn.Sequential(**
** nn.Linear(512 * 7 * 7, 4096),**
** nn.ReLU(inplace=True),**
** nn.Dropout(),**
** nn.Linear(4096, 4096),**
** nn.ReLU(inplace=True),**
** nn.Dropout(),**
** nn.Linear(4096, num_classes),**
** )**
** self._initialize_weights()**
** def forward(self, x):**
** x = self.features(x)**
** x = x.view(x.size(0), -1)**
** x = self.classifier(x)**
** return x**
** def initialize_weights(self):**
** for m in self.modules():**
** if isinstance(m, nn.Conv2d):**
** n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels**
** m.weight.data.normal(0, math.sqrt(2. / n))**
** if m.bias is not None:**
** m.bias.data.zero_()**
** elif isinstance(m, nn.BatchNorm2d):**
** m.weight.data.fill_(1)**
** m.bias.data.zero_()**
** elif isinstance(m, nn.Linear):**
** n = m.weight.size(1)**
** m.weight.data.normal_(0, 0.01)**
** m.bias.data.zero_()**
def make_layers(cfg, batch_norm=False):
** layers = []**
** in_channels = 3**
** for v in cfg:**
** if v == ‘M’:**
** layers += [nn.MaxPool2d(kernel_size=2, stride=2)]**
** else:**
** conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)**
** if batch_norm:**
** layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]**
** else:**
** layers += [conv2d, nn.ReLU(inplace=True)]**
** in_channels = v**
** return nn.Sequential(layers)*
cfg = {
** ‘A’: [64, ‘M’, 128, ‘M’, 256, 256, ‘M’, 512, 512, ‘M’, 512, 512, ‘M’],**
** ‘B’: [64, 64, ‘M’, 128, 128, ‘M’, 256, 256, ‘M’, 512, 512, ‘M’, 512, 512, ‘M’],**
** ‘D’: [64, 64, ‘M’, 128, 128, ‘M’, 256, 256, 256, ‘M’, 512, 512, 512, ‘M’, 512, 512, 512, ‘M’],**
** ‘E’: [64, 64, ‘M’, 128, 128, ‘M’, 256, 256, 256, 256, ‘M’, 512, 512, 512, 512, ‘M’, 512, 512, 512, 512, ‘M’],**
}
def vgg11(pretrained=False, model_root=None, kwargs):
** “”“VGG 11-layer model (configuration “A”)”""
** model = VGG(make_layers(cfg[‘A’]), kwargs)
** if pretrained:**
** model.load_state_dict(model_zoo.load_url(model_urls[‘vgg11’], model_root))**
** return model**
def vgg11_bn(kwargs):
** “”“VGG 11-layer model (configuration “A”) with batch normalization”""
** kwargs.pop(‘model_root’, None)**
** return VGG(make_layers(cfg[‘A’], batch_norm=True), kwargs)
def vgg13(pretrained=False, model_root=None, kwargs):
** “”“VGG 13-layer model (configuration “B”)”""
** model = VGG(make_layers(cfg[‘B’]), kwargs)
** if pretrained:**
** model.load_state_dict(model_zoo.load_url(model_urls[‘vgg13’], model_root))**
** return model**
def vgg13_bn(kwargs):
** “”“VGG 13-layer model (configuration “B”) with batch normalization”""
** kwargs.pop(‘model_root’, None)**
** return VGG(make_layers(cfg[‘B’], batch_norm=True), kwargs)
def vgg16(pretrained=False, model_root=None, kwargs):
** “”“VGG 16-layer model (configuration “D”)”""
** model = VGG(make_layers(cfg[‘D’]), kwargs)
** if pretrained:**
** model.load_state_dict(model_zoo.load_url(model_urls[‘vgg16’], model_root))**
** return model**
def vgg16_bn(kwargs):
** “”“VGG 16-layer model (configuration “D”) with batch normalization”""
** kwargs.pop(‘model_root’, None)**
** return VGG(make_layers(cfg[‘D’], batch_norm=True), kwargs)
def vgg19(pretrained=False, model_root=None, kwargs):
** “”“VGG 19-layer model (configuration “E”)”""
** model = VGG(make_layers(cfg[‘E’]), kwargs)
** if pretrained:**
** model.load_state_dict(model_zoo.load_url(model_urls[‘vgg19’], model_root))**
** return model**
def vgg19_bn(kwargs):
** “”“VGG 19-layer model (configuration ‘E’) with batch normalization”""
** kwargs.pop(‘model_root’, None)**
** return VGG(make_layers(cfg[‘E’], batch_norm=True), kwargs)
- base model is like this and
def duplicate_model_with_quant(model, bits, overflow_rate=0.0, counter=10, type=‘linear’):
** “”“assume that original model has at least a nn.Sequential”""**
** assert type in [‘linear’, ‘minmax’, ‘log’, ‘tanh’]**
** if isinstance(model, nn.Sequential):**
** l = OrderedDict()**
** for k, v in model._modules.items():**
** if isinstance(v, (nn.Conv2d, nn.Linear, nn.BatchNorm1d, nn.BatchNorm2d, nn.AvgPool2d)):**
** l[k] = v**
** if type == ‘linear’:**
** quant_layer = LinearQuant(’{}_quant’.format(k), bits=bits, overflow_rate=overflow_rate, counter=counter)**
** elif type == ‘log’:**
** # quant_layer = LogQuant(’{}_quant’.format(k), bits=bits, overflow_rate=overflow_rate, counter=counter)**
** quant_layer = NormalQuant(’{}_quant’.format(k), bits=bits, quant_func=log_minmax_quantize)**
** elif type == ‘minmax’:**
** quant_layer = NormalQuant(’{}_quant’.format(k), bits=bits, quant_func=min_max_quantize)**
** else:**
** quant_layer = NormalQuant(’{}quant’.format(k), bits=bits, quant_func=tanh_quantize)**
** l[’{}{}_quant’.format(k, type)] = quant_layer**
** else:**
** l[k] = duplicate_model_with_quant(v, bits, overflow_rate, counter, type)**
** m = nn.Sequential(l)**
** return m**
** else:**
** for k, v in model._modules.items():**
** model._modules[k] = duplicate_model_with_quant(v, bits, overflow_rate, counter, type)**
** return model**
- this is how LinearQuant layer generated