app.py

import gradio as gr
import tensorflow as tf
import keras 
import numpy as np
import sklearn
from sklearnex import patch_sklearn, unpatch_sklearn
patch_sklearn()
import xgboost as xgb

from keras import Model, Sequential
from keras.layers import Layer
import keras.layers as nn

class ChannelAttn(Layer):
    def __init__(self, c=512) -> None:
        super(ChannelAttn,self).__init__()
        self.gap = nn.AveragePooling2D(7)
        self.attention = Sequential([
            nn.Dense(32),
            nn.BatchNormalization(),
            nn.ReLU(),
            nn.Dense(c,activation='sigmoid')]
        )

    def call(self, x):

        x = self.gap(x)
        x = nn.Flatten()(x)
        y = self.attention(x)
        return x * y


class SpatialAttn(Layer):
    def __init__(self, c=512):
        super(SpatialAttn,self).__init__()
        self.conv1x1 = Sequential([
            nn.Conv2D(256, 1),
            nn.BatchNormalization()]
        )
        self.conv_3x3 = Sequential([
            nn.ZeroPadding2D(padding=(1, 1)),
            nn.Conv2D(512, 3,1),
            nn.BatchNormalization()]
        )
        self.conv_1x3 = Sequential([
            nn.ZeroPadding2D(padding=(0, 1)),
            nn.Conv2D(512, (1,3)),
            nn.BatchNormalization()]
        )
        self.conv_3x1 = Sequential([
            nn.ZeroPadding2D(padding=(1, 0)),
            nn.Conv2D(512,(3,1)),
            nn.BatchNormalization()]
        )
        self.norm = nn.ReLU()

    def call(self, x) :
        y = self.conv1x1(x)
        y = self.norm(self.conv_3x3(y) + self.conv_1x3(y) + self.conv_3x1(y))
        y = tf.math.reduce_sum(y,axis=1, keepdims=True)
        return x*y


class CrossAttnHead(Layer):
    def __init__(self, c=512):
        super(CrossAttnHead,self).__init__()
        self.sa = SpatialAttn(c)
        self.ca = ChannelAttn(c)

    def call(self, x):
        return self.ca(self.sa(x))


@keras.saving.register_keras_serializable(package='custom')
class DAN(Model):
    def __init__(self, num_classes=8,trainable=True,dtype='float32'):
        super(DAN,self).__init__()
        self.mod = keras.applications.ResNet50(
            include_top=False,
            weights="imagenet",
            input_shape=(224,224,3)
        )
        self.mod.trainable= False
        self.num_head = 4
        self.hd = CrossAttnHead()
        self.hd=[]
        for i in range(self.num_head):
          self.hd.append(CrossAttnHead())
        self.features = nn.Conv2D(512, 1,padding='same')
        self.fc = nn.Dense(num_classes)
        self.bn = nn.BatchNormalization()

    def call(self, x) :
        x = self.mod(x)
        x=self.features(x)
        heads = []
        for h in self.hd:
            heads.append(h(x))

        heads = tf.transpose(tf.stack(heads),perm=(1,0,2))
        heads = keras.ops.log_softmax(heads, axis=1)
        return tf.math.reduce_sum(heads,axis=1)

backbone = DAN()
backbone.load_weights('weights.keras')
xgb_params = {
    'objective':                    'binary:logistic',
    'predictor':                    'cpu_predictor',
    'disable_default_eval_metric':  1,
}

model_xgb= xgb.XGBClassifier(**xgb_params)

model_xgb.load_model('xgb.json')
emotions = ['anger', 'contempt', 'disgust', 'fear', 'happy', 'neutral', 'sad', 'surprise']
def fn(image):
  if len(image.shape)==2:
    img = np.stack([image,image,image],axis=2)
    img = np.resize(img,(224,224,3))
  elif len(image.shape)==3 and image.shape[2]==1:
    img = np.stack([image[:,:,0],image[:,:,0],image[:,:,0]],axis=2)
    img = np.resize(img,(224,224,3))
  else:
    img = np.resize(image,(224,224,3))
  img = np.expand_dims(img,axis=0)
  feats = backbone.predict(img)
  pred = model_xgb.predict(feats)
  print(pred)
  return emotions[pred[0]]
    

demo = gr.Interface(
    fn,['image'],"text",
    
)

if __name__ == "__main__":
    demo.launch()