IndexError : index 255 is out of bounds for dimension 0 with size 255

[Sarthak-22]

I am trying to prune the Restormer model using Torch-pruning library but I stumbled upon the following error :

File "/home/sarthak.vora/Documents/pt-text-enhancement/Restormer_IE/Denoising/test_pruning_simple.py", line 103, in <module>
    for g in pruner.step(interactive=True):
  File "/home/sarthak.vora/miniconda3/envs/pytorch181/lib/python3.11/site-packages/torch_pruning/pruner/algorithms/metapruner.py", line 380, in prune_local
    imp = self.estimate_importance(group)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/sarthak.vora/miniconda3/envs/pytorch181/lib/python3.11/site-packages/torch_pruning/pruner/algorithms/metapruner.py", line 251, in estimate_importance
    return self.importance(group)
           ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/sarthak.vora/miniconda3/envs/pytorch181/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/sarthak.vora/miniconda3/envs/pytorch181/lib/python3.11/site-packages/torch_pruning/pruner/importance.py", line 221, in __call__
    local_imp = local_imp[idxs]
                ~~~~~~~~~^^^^^^
IndexError: index 255 is out of bounds for dimension 0 with size 255

I observed that many people faced this issue, evidently seen in the open issues covering this topic. However, none of the workarounds seem to work for me. I believe the concat and split operation might have been an issue but these operations were fixed in the latest version of the library. The inbuilt helper modules don't seem to reduce or split the indices, specifically in the feedforward module where there is a split operation present. Any help would be appreciated !

Here is the model code:

import torch
import torch.nn as nn
import torch.nn.functional as F
from pdb import set_trace as stx
import numbers

from einops import rearrange

##########################################################################
## Layer Norm

def to_3d(x):
    return rearrange(x, 'b c h w -> b (h w) c')

def to_4d(x,h,w):
    return rearrange(x, 'b (h w) c -> b c h w',h=h,w=w)

class BiasFree_LayerNorm(nn.Module):
    def __init__(self, normalized_shape):
        super(BiasFree_LayerNorm, self).__init__()
        if isinstance(normalized_shape, numbers.Integral):
            normalized_shape = (normalized_shape,)
        normalized_shape = torch.Size(normalized_shape)

        assert len(normalized_shape) == 1

        self.weight = nn.Parameter(torch.ones(normalized_shape))
        self.normalized_shape = normalized_shape

    def forward(self, x):
        sigma = x.var(-1, keepdim=True, unbiased=False)
        return x / torch.sqrt(sigma+1e-5) * self.weight

class WithBias_LayerNorm(nn.Module):
    def __init__(self, normalized_shape):
        super(WithBias_LayerNorm, self).__init__()
        if isinstance(normalized_shape, numbers.Integral):
            normalized_shape = (normalized_shape,)
        normalized_shape = torch.Size(normalized_shape)

        assert len(normalized_shape) == 1

        self.weight = nn.Parameter(torch.ones(normalized_shape))
        self.bias = nn.Parameter(torch.zeros(normalized_shape))
        self.normalized_shape = normalized_shape

    def forward(self, x):
        mu = x.mean(-1, keepdim=True)
        sigma = x.var(-1, keepdim=True, unbiased=False)
        return (x - mu) / torch.sqrt(sigma+1e-5) * self.weight + self.bias

class LayerNorm(nn.Module):
    def __init__(self, dim, LayerNorm_type):
        super(LayerNorm, self).__init__()
        if LayerNorm_type =='BiasFree':
            self.body = BiasFree_LayerNorm(dim)
        else:
            self.body = WithBias_LayerNorm(dim)

    def forward(self, x):
        h, w = x.shape[-2:]
        return to_4d(self.body(to_3d(x)), h, w)

##########################################################################
## Gated-Dconv Feed-Forward Network (GDFN)
class FeedForward(nn.Module):
    def __init__(self, dim, ffn_expansion_factor, bias):
        super(FeedForward, self).__init__()

        hidden_features = int(dim*ffn_expansion_factor)

        self.project_in = nn.Conv2d(dim, hidden_features*2, kernel_size=1, bias=bias)

        self.dwconv = nn.Conv2d(hidden_features*2, hidden_features*2, kernel_size=3, stride=1, padding=1, groups=hidden_features*2, bias=bias)

        self.project_out = nn.Conv2d(hidden_features, dim, kernel_size=1, bias=bias)

    def forward(self, x):
        x = self.project_in(x)
        x1, x2 = self.dwconv(x).chunk(2, dim=1)
        x = F.gelu(x1) * x2
        x = self.project_out(x)
        return x

##########################################################################
## Multi-DConv Head Transposed Self-Attention (MDTA)
class Attention(nn.Module):
    def __init__(self, dim, num_heads, bias):
        super(Attention, self).__init__()
        self.num_heads = num_heads
        self.temperature = nn.Parameter(torch.ones(num_heads, 1, 1))

        self.qkv = nn.Conv2d(dim, dim*3, kernel_size=1, bias=bias)
        self.qkv_dwconv = nn.Conv2d(dim*3, dim*3, kernel_size=3, stride=1, padding=1, groups=dim*3, bias=bias)
        self.project_out = nn.Conv2d(dim, dim, kernel_size=1, bias=bias)

    def forward(self, x):
        b,c,h,w = x.shape

        qkv = self.qkv_dwconv(self.qkv(x))
        q,k,v = qkv.chunk(3, dim=1)   

        q = rearrange(q, 'b (head c) h w -> b head c (h w)', head=self.num_heads)
        k = rearrange(k, 'b (head c) h w -> b head c (h w)', head=self.num_heads)
        v = rearrange(v, 'b (head c) h w -> b head c (h w)', head=self.num_heads)

        q = torch.nn.functional.normalize(q, dim=-1)
        k = torch.nn.functional.normalize(k, dim=-1)

        attn = (q @ k.transpose(-2, -1)) * self.temperature
        attn = attn.softmax(dim=-1)

        out = (attn @ v)

        out = rearrange(out, 'b head c (h w) -> b (head c) h w', head=self.num_heads, h=h, w=w)

        out = self.project_out(out)
        return out

##########################################################################
class TransformerBlock(nn.Module):
    def __init__(self, dim, num_heads, ffn_expansion_factor, bias, LayerNorm_type):
        super(TransformerBlock, self).__init__()

        self.norm1 = LayerNorm(dim, LayerNorm_type)
        self.attn = Attention(dim, num_heads, bias)
        self.norm2 = LayerNorm(dim, LayerNorm_type)
        self.ffn = FeedForward(dim, ffn_expansion_factor, bias)

    def forward(self, x):
        x = x + self.attn(self.norm1(x))
        x = x + self.ffn(self.norm2(x))

        return x

##########################################################################
## Overlapped image patch embedding with 3x3 Conv
class OverlapPatchEmbed(nn.Module):
    def __init__(self, in_c=3, embed_dim=48, bias=False):
        super(OverlapPatchEmbed, self).__init__()

        self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=3, stride=1, padding=1, bias=bias)

    def forward(self, x):
        x = self.proj(x)

        return x

##########################################################################
## Resizing modules
class Downsample(nn.Module):
    def __init__(self, n_feat):
        super(Downsample, self).__init__()

        self.body = nn.Sequential(nn.Conv2d(n_feat, n_feat//2, kernel_size=3, stride=1, padding=1, bias=False),
                                  nn.PixelUnshuffle(2))

    def forward(self, x):
        return self.body(x)

class Upsample(nn.Module):
    def __init__(self, n_feat):
        super(Upsample, self).__init__()

        self.body = nn.Sequential(nn.Conv2d(n_feat, n_feat*2, kernel_size=3, stride=1, padding=1, bias=False),
                                  nn.PixelShuffle(2))

    def forward(self, x):
        return self.body(x)

##########################################################################
##---------- Restormer -----------------------
class Restormer(nn.Module):
    def __init__(self, 
        inp_channels=3, 
        out_channels=3, 
        dim = 48,
        num_blocks = [4,6,6,8], 
        num_refinement_blocks = 4,
        heads = [1,2,4,8],
        ffn_expansion_factor = 2.66,
        bias = False,
        LayerNorm_type = 'WithBias',   ## Other option 'BiasFree'
        dual_pixel_task = False        ## True for dual-pixel defocus deblurring only. Also set inp_channels=6
    ):

        super(Restormer, self).__init__()

        self.patch_embed = OverlapPatchEmbed(inp_channels, dim)

        self.encoder_level1 = nn.Sequential(*[TransformerBlock(dim=dim, num_heads=heads[0], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[0])])

        self.down1_2 = Downsample(dim) ## From Level 1 to Level 2
        self.encoder_level2 = nn.Sequential(*[TransformerBlock(dim=int(dim*2**1), num_heads=heads[1], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[1])])

        self.down2_3 = Downsample(int(dim*2**1)) ## From Level 2 to Level 3
        self.encoder_level3 = nn.Sequential(*[TransformerBlock(dim=int(dim*2**2), num_heads=heads[2], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[2])])

        self.down3_4 = Downsample(int(dim*2**2)) ## From Level 3 to Level 4
        self.latent = nn.Sequential(*[TransformerBlock(dim=int(dim*2**3), num_heads=heads[3], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[3])])

        self.up4_3 = Upsample(int(dim*2**3)) ## From Level 4 to Level 3
        self.reduce_chan_level3 = nn.Conv2d(int(dim*2**3), int(dim*2**2), kernel_size=1, bias=bias)
        self.decoder_level3 = nn.Sequential(*[TransformerBlock(dim=int(dim*2**2), num_heads=heads[2], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[2])])

        self.up3_2 = Upsample(int(dim*2**2)) ## From Level 3 to Level 2
        self.reduce_chan_level2 = nn.Conv2d(int(dim*2**2), int(dim*2**1), kernel_size=1, bias=bias)
        self.decoder_level2 = nn.Sequential(*[TransformerBlock(dim=int(dim*2**1), num_heads=heads[1], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[1])])

        self.up2_1 = Upsample(int(dim*2**1))  ## From Level 2 to Level 1  (NO 1x1 conv to reduce channels)

        self.decoder_level1 = nn.Sequential(*[TransformerBlock(dim=int(dim*2**1), num_heads=heads[0], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[0])])

        self.refinement = nn.Sequential(*[TransformerBlock(dim=int(dim*2**1), num_heads=heads[0], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_refinement_blocks)])

        #### For Dual-Pixel Defocus Deblurring Task ####
        self.dual_pixel_task = dual_pixel_task
        if self.dual_pixel_task:
            self.skip_conv = nn.Conv2d(dim, int(dim*2**1), kernel_size=1, bias=bias)
        ###########################

        self.output = nn.Conv2d(int(dim*2**1), out_channels, kernel_size=3, stride=1, padding=1, bias=bias)

    def forward(self, inp_img):

        inp_enc_level1 = self.patch_embed(inp_img)
        out_enc_level1 = self.encoder_level1(inp_enc_level1)

        inp_enc_level2 = self.down1_2(out_enc_level1)
        out_enc_level2 = self.encoder_level2(inp_enc_level2)

        inp_enc_level3 = self.down2_3(out_enc_level2)
        out_enc_level3 = self.encoder_level3(inp_enc_level3) 

        inp_enc_level4 = self.down3_4(out_enc_level3)        
        latent = self.latent(inp_enc_level4) 

        inp_dec_level3 = self.up4_3(latent)
        inp_dec_level3 = torch.cat([inp_dec_level3, out_enc_level3], 1)
        inp_dec_level3 = self.reduce_chan_level3(inp_dec_level3)
        out_dec_level3 = self.decoder_level3(inp_dec_level3) 

        inp_dec_level2 = self.up3_2(out_dec_level3)
        inp_dec_level2 = torch.cat([inp_dec_level2, out_enc_level2], 1)
        inp_dec_level2 = self.reduce_chan_level2(inp_dec_level2)
        out_dec_level2 = self.decoder_level2(inp_dec_level2) 

        inp_dec_level1 = self.up2_1(out_dec_level2)
        inp_dec_level1 = torch.cat([inp_dec_level1, out_enc_level1], 1)
        out_dec_level1 = self.decoder_level1(inp_dec_level1)

        out_dec_level1 = self.refinement(out_dec_level1)

        #### For Dual-Pixel Defocus Deblurring Task ####
        if self.dual_pixel_task:
            out_dec_level1 = out_dec_level1 + self.skip_conv(inp_enc_level1)
            out_dec_level1 = self.output(out_dec_level1)
        ###########################
        else:
            out_dec_level1 = self.output(out_dec_level1) + inp_img

        return out_dec_level1

[Sarthak-22]

Minimum code snippet to reproduce the error :

model = Restormer()

example_inputs = torch.randn(1, 3, 512, 512)#.to(device='cuda')
imp = tp.importance.GroupNormImportance(p=2)

# Ignore some layers, e.g., the output layer
ignored_layers = [model.output, model.refinement]

in_channel_groups = {}
for name, module in model.named_modules():
    if isinstance(module, nn.Conv2d) and module.groups > 1:
        in_channel_groups[name] = module.groups

# Initialize a pruner
pruner = tp.pruner.MetaPruner(
    model,
    example_inputs,
    importance=imp,
    pruning_ratio=0.5,
    in_channel_groups=in_channel_groups,
    out_channel_groups=in_channel_groups,
    ignored_layers=ignored_layers,
)

for g in pruner.step(interactive=True): # Error faced in pruner.step()
    g.prune() 

[cactusgame]

Hello, may I ask if there has been any progress? I used this piece of code and encountered the following error. My environment is Ubuntu22, python3.10

RuntimeError: CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [0,0,0], thread: [127,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [0,0,0], thread: [0,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [0,0,0], thread: [1,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.

example_inputs = torch.randn(1, 3, 512, 512)#.to(device='cuda') imp = tp.importance.GroupNormImportance(p=2)

Ignore some layers, e.g., the output layer

ignored_layers = [model.output, model.refinement]

in_channel_groups = {} for name, module in model.named_modules(): if isinstance(module, nn.Conv2d) and module.groups > 1: in_channel_groups[name] = module.groups

Initialize a pruner

pruner = tp.pruner.MetaPruner( model, example_inputs, importance=imp, pruning_ratio=0.5, in_channel_groups=in_channel_groups, out_channel_groups=in_channel_groups, ignored_layers=ignored_layers, )

for g in pruner.step(interactive=True): # Error faced in pruner.step() g.prune()

[EzcodingSen]

same