Swin Transformer for Facial expression recognition - deep-learning

Question

I am using Swin transformer to build a Facial expression recognition model. The complete code is shared by Author: Rishit Dagli on 'https://keras.io/examples/vision/swin_transformers/'.
In Swin transformer class, the authors have used two Dense layers and I want to replace it with ResNet50. I came to know that the input to Resnet50 needs to be of the shape (none, none, 3). But when the images of shape (96, 96, 3) in the model are flowing through the initial layers -'PatchExtract' and 'PatchEmbedding', its getting converted to shape (576, 64). Then, when its getting passed to SwinTransformer with ResNet50, its giving an error:
Please suggest how can I embed Resnet model as a layer in SwinTransformer.
Swin Transformer class:
class SwinTransformer(layers.Layer):
def __init__(
self,
dim,
num_patch,
num_heads,
window_size=7,
shift_size=0,
num_mlp=1024,
qkv_bias=True,
dropout_rate=0.0,
**kwargs,
):
super(SwinTransformer, self).__init__(**kwargs)
self.dim = dim # number of input dimensions
self.num_patch = num_patch # number of embedded patches
self.num_heads = num_heads # number of attention heads
self.window_size = window_size # size of window
self.shift_size = shift_size # size of window shift
self.num_mlp = num_mlp # number of MLP nodes
self.norm1 = layers.LayerNormalization(epsilon=1e-5)
self.attn = WindowAttention(
dim,
window_size=(self.window_size, self.window_size),
num_heads=num_heads,
qkv_bias=qkv_bias,
dropout_rate=dropout_rate,
)
self.drop_path = DropPath(dropout_rate)
self.norm2 = layers.LayerNormalization(epsilon=1e-5)
self.mlp = keras.Sequential(
[
# I am trying to add pretrained ResNet50 here
layers.Dense(num_mlp),
layers.Activation(keras.activations.gelu),
layers.Dropout(dropout_rate),
layers.Dense(dim),
layers.Dropout(dropout_rate),
]
)
if min(self.num_patch) < self.window_size:
self.shift_size = 0
self.window_size = min(self.num_patch)
def build(self, input_shape):
if self.shift_size == 0:
self.attn_mask = None
else:
height, width = self.num_patch
h_slices = (
slice(0, -self.window_size),
slice(-self.window_size, -self.shift_size),
slice(-self.shift_size, None),
)
w_slices = (
slice(0, -self.window_size),
slice(-self.window_size, -self.shift_size),
slice(-self.shift_size, None),
)
mask_array = np.zeros((1, height, width, 1))
count = 0
for h in h_slices:
for w in w_slices:
mask_array[:, h, w, :] = count
count += 1
mask_array = tf.convert_to_tensor(mask_array)
# mask array to windows
mask_windows = window_partition(mask_array, self.window_size)
mask_windows = tf.reshape(
mask_windows, shape=[-1, self.window_size * self.window_size]
)
attn_mask = tf.expand_dims(mask_windows, axis=1) - tf.expand_dims(
mask_windows, axis=2
)
attn_mask = tf.where(attn_mask != 0, -100.0, attn_mask)
attn_mask = tf.where(attn_mask == 0, 0.0, attn_mask)
self.attn_mask = tf.Variable(initial_value=attn_mask, trainable=False)
def call(self, x):
height, width = self.num_patch
_, num_patches_before, channels = x.shape
x_skip = x
x = self.norm1(x)
x = tf.reshape(x, shape=(-1, height, width, channels))
if self.shift_size > 0:
shifted_x = tf.roll(
x, shift=[-self.shift_size, -self.shift_size], axis=[1, 2]
)
else:
shifted_x = x
x_windows = window_partition(shifted_x, self.window_size)
x_windows = tf.reshape(
x_windows, shape=(-1, self.window_size * self.window_size, channels)
)
attn_windows = self.attn(x_windows, mask=self.attn_mask)
attn_windows = tf.reshape(
attn_windows, shape=(-1, self.window_size, self.window_size, channels)
)
shifted_x = window_reverse(
attn_windows, self.window_size, height, width, channels
)
if self.shift_size > 0:
x = tf.roll(
shifted_x, shift=[self.shift_size, self.shift_size], axis=[1, 2]
)
else:
x = shifted_x
x = tf.reshape(x, shape=(-1, height * width, channels))
x = self.drop_path(x)
x = x_skip + x
x_skip = x
x = self.norm2(x)
x = self.mlp(x)
x = self.drop_path(x)
x = x_skip + x
return x
Model:
input = layers.Input(input_shape)
x = layers.RandomCrop(image_dimension, image_dimension)(input)
x = layers.RandomFlip("horizontal")(x)
x = PatchExtract(patch_size)(x)
x = PatchEmbedding(num_patch_x * num_patch_y, embed_dim)(x)
x = SwinTransformer(
dim=embed_dim,
num_patch=(num_patch_x, num_patch_y),
num_heads=num_heads,
window_size=window_size,
shift_size=0,
num_mlp=num_mlp,
qkv_bias=qkv_bias,
dropout_rate=dropout_rate,
)(x)
x = SwinTransformer(
dim=embed_dim,
num_patch=(num_patch_x, num_patch_y),
num_heads=num_heads,
window_size=window_size,
shift_size=shift_size,
num_mlp=num_mlp,
qkv_bias=qkv_bias,
dropout_rate=dropout_rate,
)(x)
x = PatchMerging((num_patch_x, num_patch_y), embed_dim=embed_dim)(x)
x = layers.GlobalAveragePooling1D()(x)
output = layers.Dense(num_classes, activation="softmax")(x)
I added ResNet50 layer but got the below error:
ValueError: Exception encountered when calling layer "swin_transformer_2" (type SwinTransformer).
in user code:
File "<ipython-input-12-4a18cac0b25c>", line 121, in call *
x = self.mlp(x)
File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler **
raise e.with_traceback(filtered_tb) from None
File "/usr/local/lib/python3.7/dist-packages/keras/engine/input_spec.py", line 214, in assert_input_compatibility
raise ValueError(f'Input {input_index} of layer "{layer_name}" '
ValueError: Exception encountered when calling layer "resnet50" (type Functional).
Input 0 of layer "conv1_pad" is incompatible with the layer: expected ndim=4, found ndim=3. Full shape received: (None, 576, 64)
Call arguments received by layer "resnet50" (type Functional):
• inputs=tf.Tensor(shape=(None, 576, 64), dtype=float32)
• training=False
• mask=None
Call arguments received by layer "swin_transformer_2" (type SwinTransformer):
• x=tf.Tensor(shape=(None, 576, 64), dtype=float32)