Tensor size mismatch while running SHAP DeepExplainer

Question

I'm trying to run a SHAP DeepExplainer on my image classification model (an adaptation of ResNet-50 for the CelebA dataset), but keep running into this issue. I'm not sure if it has to do with my model architecture (code shown below) or with something, because I think there's nothing wrong with the input data here. enter image description here

Here's my code for setting up the model:

import os
import time

import numpy as np
import pandas as pd

import torch
import torch.nn as nn
import torch.nn.functional as F

from torch.utils.data import Dataset
from torch.utils.data import DataLoader

from torchvision import datasets
from torchvision import transforms

import matplotlib.pyplot as plt
from PIL import Image


if torch.cuda.is_available():
    torch.backends.cudnn.deterministic = True

##########################
### SETTINGS
##########################

# Hyperparameters
RANDOM_SEED = 1
LEARNING_RATE = 0.001
NUM_EPOCHS = 1

# Architecture
NUM_FEATURES = 128*128
NUM_CLASSES = 2
BATCH_SIZE = 256
#*torch.cuda.device_count()
#DEVICE = torch.device("cuda:0" if torch.cuda.is_available() else "gpu")
GRAYSCALE = False


if torch.cuda.is_available():
    torch.backends.cudnn.deterministic = True

custom_transform = transforms.Compose([transforms.CenterCrop((178, 178)),
                                       transforms.Resize((128, 128)),
                                       #transforms.Grayscale(),
                                       #transforms.Lambda(lambda x: x/255.),
                                       transforms.ToTensor()])

train_dataset = CelebaDataset(csv_path='celeba-gender-train.csv',
                              img_dir='img_align_celeba/',
                              transform=custom_transform)

valid_dataset = CelebaDataset(csv_path='celeba-gender-valid.csv',
                              img_dir='img_align_celeba/',
                              transform=custom_transform)

test_dataset = CelebaDataset(csv_path='celeba-gender-test.csv',
                             img_dir='img_align_celeba/',
                             transform=custom_transform)


train_loader = DataLoader(dataset=train_dataset,
                          batch_size=BATCH_SIZE,
                          shuffle=True,
                          num_workers=0)

valid_loader = DataLoader(dataset=valid_dataset,
                          batch_size=BATCH_SIZE,
                          shuffle=False,
                          num_workers=0)

test_loader = DataLoader(dataset=test_dataset,
                         batch_size=BATCH_SIZE,
                         shuffle=False,
                         num_workers=0)


# Model

def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                               padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class ResNet(nn.Module):

    def __init__(self, block, layers, num_classes, grayscale):
        self.inplanes = 64
        if grayscale:
            in_dim = 1
        else:
            in_dim = 3
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(in_dim, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = nn.AvgPool2d(7, stride=1, padding=2)
        self.fc = nn.Linear(2048 * 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, (2. / n)**.5)
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                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 = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )

        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.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        logits = self.fc(x)
        probas = F.softmax(logits, dim=1)
        return logits
        #, probas



def resnet50(num_classes, grayscale):
    """Constructs a ResNet-50 model."""
    model = ResNet(block=Bottleneck,
                   layers=[3, 4, 6, 3],
                   num_classes=NUM_CLASSES,
                   grayscale=grayscale)
    return model

torch.manual_seed(RANDOM_SEED)

##########################
### COST AND OPTIMIZER
##########################



model = resnet50(NUM_CLASSES, GRAYSCALE)


#### DATA PARALLEL START ####
if torch.cuda.device_count() > 1:
    print("Using", torch.cuda.device_count(), "GPUs")
    model = nn.DataParallel(model)
#### DATA PARALLEL END ####



optimizer = torch.optim.Adam(model.parameters(), lr=LEARNING_RATE)

Here's the code for the explainer. The assumption here is that I already have a trained model (hence the line for loading 'celeba_resnet'):

model = resnet50(NUM_CLASSES, GRAYSCALE)
model.load_state_dict(torch.load('celeba_resnet'))
model.eval()

import numpy as np
import shap
import tensorflow as tf

# shap.explainers._deep.deep_tf.op_handlers["FusedBatchNormV3"] = shap.explainers._deep.deep_tf.linearity_1d(0)
# the line above is a potential workaround for a problem with Deep Explainer architecture
#print("Successful handling of batch normalization.")

background, _ = next(iter(train_loader))
# background = np.swapaxes(background, 1, -1)
# background = np.swapaxes(background, 1, 2)
print("Background shape: ", background.shape)

e = shap.DeepExplainer(model, background)

for batch_idx, (features, targets) in enumerate(train_loader):

    features = features
    targets = targets

    # features = np.swapaxes(features, 1, -1)
    # features = np.swapaxes(features, 1, 2)

    print("Features shape: ", features.shape)
    shap_values = np.array(e.shap_values(features))
    if batch_idx == 0:
        agg_shap_values = shap_values
    else:
        agg_shap_values = np.append(agg_shap_values, shap_values, axis=0)

The error occurs at the line where I'm trying to get the SHAP values from "features".