problem in assigning different pruning indices to different layers in RESNET-56

[Allhailankurgupta]

I was trying to prune Resnet56

Code given below for the model

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn import init
import math

class DownsampleA(nn.Module):  

  def __init__(self, nIn, nOut, stride):
    super(DownsampleA, self).__init__() 
    self.avg = nn.AvgPool2d(kernel_size=1, stride=stride)   

  def forward(self, x):   
    x = self.avg(x)  
    return torch.cat((x, x.mul(0)), 1)  

class DownsampleC(nn.Module):     

  def __init__(self, nIn, nOut, stride):
    super(DownsampleC, self).__init__()
    assert stride != 1 or nIn != nOut
    self.conv = nn.Conv2d(nIn, nOut, kernel_size=1, stride=stride, padding=0, bias=False)

  def forward(self, x):
    x = self.conv(x)
    return x

class ResNetBasicblock(nn.Module):
  expansion = 1
  """
  RexNet basicblock (https://github.com/facebook/fb.resnet.torch/blob/master/models/resnet.lua)
  """
  def __init__(self, inplanes, planes, stride=1, downsample=None):
    super(ResNetBasicblock, self).__init__()

    self.conv_a = nn.Conv2d(inplanes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
    self.bn_a = nn.BatchNorm2d(planes)

    self.conv_b = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
    self.bn_b = nn.BatchNorm2d(planes)

    self.downsample = downsample

  def forward(self, x):
    residual = x

    basicblock = self.conv_a(x)
    basicblock = self.bn_a(basicblock)
    basicblock = F.relu(basicblock, inplace=True)

    basicblock = self.conv_b(basicblock)
    basicblock = self.bn_b(basicblock)

    if self.downsample is not None:
      residual = self.downsample(x)
    
    return F.relu(residual + basicblock, inplace=True)

class CifarResNet(nn.Module):
  """
  ResNet optimized for the Cifar dataset, as specified in
  https://arxiv.org/abs/1512.03385.pdf
  """
  def __init__(self, block, depth, num_classes):
    """ Constructor
    Args:
      depth: number of layers.
      num_classes: number of classes
      base_width: base width
    """
    super(CifarResNet, self).__init__()

    #Model type specifies number of layers for CIFAR-10 and CIFAR-100 model
    assert (depth - 2) % 6 == 0, 'depth should be one of 20, 32, 44, 56, 110'
    layer_blocks = (depth - 2) // 6
    print ('CifarResNet : Depth : {} , Layers for each block : {}'.format(depth, layer_blocks))

    self.num_classes = num_classes

    self.conv_1_3x3 = nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1, bias=False)
    self.bn_1 = nn.BatchNorm2d(16)

    self.inplanes = 16
    self.stage_1 = self._make_layer(block, 16, layer_blocks, 1)
    self.stage_2 = self._make_layer(block, 32, layer_blocks, 2)
    self.stage_3 = self._make_layer(block, 64, layer_blocks, 2)
    self.avgpool = nn.AvgPool2d(8)
    self.classifier = nn.Linear(64*block.expansion, num_classes)

    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))
        #m.bias.data.zero_()
      elif isinstance(m, nn.BatchNorm2d):
        m.weight.data.fill_(1)
        # m.bias.data.zero_()
      elif isinstance(m, nn.Linear):
        init.kaiming_normal(m.weight)
        # m.bias.data.zero_()

  def _make_layer(self, block, planes, blocks, stride=1):
    downsample = None
    if stride != 1 or self.inplanes != planes * block.expansion:
      downsample = DownsampleA(self.inplanes, planes * block.expansion, stride)

    layers = []
    layers.append(block(self.inplanes, planes, stride, downsample))
    self.inplanes = planes * block.expansion
    for i in range(1, blocks):
      layers.append(block(self.inplanes, planes))

    return nn.Sequential(*layers)

  def forward(self, x):
    x = self.conv_1_3x3(x)
    x = F.relu(self.bn_1(x), inplace=True)
    x = self.stage_1(x)
    x = self.stage_2(x)
    x = self.stage_3(x)
    x = self.avgpool(x)
    x = x.view(x.size(0), -1)
    return self.classifier(x)

def resnet56(num_classes=10):
  """Constructs a ResNet-56 model for CIFAR-10 (by default)
  Args:
    num_classes (uint): number of classes
  """
  model = CifarResNet(ResNetBasicblock, 56, num_classes)
  return model

When we prune the first ever layer of RESNET layer name here being 'conv_1_3x3 ' before the resnet blocks the, As the layer is connected to second Conv layer of every resnet block so they also get pruned with 'conv_1_3x3' but when I try to assign different indices to different conv layers they get assigned the same index

what I mean is let say we have conv-layer-2 of resnet block-1 -> LYR_X (name to refer later in description) and conv-layer-2 of resnet block-2 -> LYR_Y (name to refer later in description) also they both are connected with skip connection as this is resnet

I generate pruning plan for pruning 'conv_1_3x3' let say at indices [2,3,4]

so due to dependency graph the LYR_X and LYR_Y also get assigned the same pruning indices [2,3,4] BUT I want to assign different pruning indices to LYR_X and LYR_Y LYR_X -> [3,5,9] LYR_Y -> [2,6,8]

Earlier you suggested to manually change the indices

A temporary fix: You can create a pruning plan, and modify the index of pruning_conv and pruning_related_xxx manually.

so i tried doing this

pruning_plan.plan[0][1][:] = [2,8] # -> conv_1_3x3
pruning_plan.plan[5][1][:] = [3,6] # -> LYR_X 

print(pruning_plan.plan[0], pruning_plan.plan[5])

but for both the layers i was getting [3,6]. instead of getting different indices for different layers

what i have observed is that it assigns the last assigned indices to all the layers. here its [3,6]

Can you please tell me how can I assign different indices for different layers.