Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+src/models/colorization_release_v2.caffemodel filter=lfs diff=lfs merge=lfs -text

src/models/colorization_deploy_v2.prototxt

@@ -0,0 +1,589 @@
+name: "LtoAB"
+
+layer {
+  name: "data_l"
+  type: "Input"
+  top: "data_l"
+  input_param {
+    shape { dim: 1 dim: 1 dim: 224 dim: 224 }
+  }
+}
+
+# *****************
+# ***** conv1 *****
+# *****************
+layer {
+  name: "bw_conv1_1"
+  type: "Convolution"
+  bottom: "data_l"
+  top: "conv1_1"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+  }
+}
+layer {
+  name: "relu1_1"
+  type: "ReLU"
+  bottom: "conv1_1"
+  top: "conv1_1"
+}
+layer {
+  name: "conv1_2"
+  type: "Convolution"
+  bottom: "conv1_1"
+  top: "conv1_2"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+    stride: 2
+  }
+}
+layer {
+  name: "relu1_2"
+  type: "ReLU"
+  bottom: "conv1_2"
+  top: "conv1_2"
+}
+layer {
+  name: "conv1_2norm"
+  type: "BatchNorm"
+  bottom: "conv1_2"
+  top: "conv1_2norm"
+  batch_norm_param{ }
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+}
+# *****************
+# ***** conv2 *****
+# *****************
+layer {
+  name: "conv2_1"
+  type: "Convolution"
+  # bottom: "conv1_2"
+  bottom: "conv1_2norm"
+  # bottom: "pool1"
+  top: "conv2_1"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+  }
+}
+layer {
+  name: "relu2_1"
+  type: "ReLU"
+  bottom: "conv2_1"
+  top: "conv2_1"
+}
+layer {
+  name: "conv2_2"
+  type: "Convolution"
+  bottom: "conv2_1"
+  top: "conv2_2"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 2
+  }
+}
+layer {
+  name: "relu2_2"
+  type: "ReLU"
+  bottom: "conv2_2"
+  top: "conv2_2"
+}
+layer {
+  name: "conv2_2norm"
+  type: "BatchNorm"
+  bottom: "conv2_2"
+  top: "conv2_2norm"
+  batch_norm_param{ }
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+}
+# *****************
+# ***** conv3 *****
+# *****************
+layer {
+  name: "conv3_1"
+  type: "Convolution"
+  # bottom: "conv2_2"
+  bottom: "conv2_2norm"
+  # bottom: "pool2"
+  top: "conv3_1"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layer {
+  name: "relu3_1"
+  type: "ReLU"
+  bottom: "conv3_1"
+  top: "conv3_1"
+}
+layer {
+  name: "conv3_2"
+  type: "Convolution"
+  bottom: "conv3_1"
+  top: "conv3_2"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+  }
+}
+layer {
+  name: "relu3_2"
+  type: "ReLU"
+  bottom: "conv3_2"
+  top: "conv3_2"
+}
+layer {
+  name: "conv3_3"
+  type: "Convolution"
+  bottom: "conv3_2"
+  top: "conv3_3"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    stride: 2
+  }
+}
+layer {
+  name: "relu3_3"
+  type: "ReLU"
+  bottom: "conv3_3"
+  top: "conv3_3"
+}
+layer {
+  name: "conv3_3norm"
+  type: "BatchNorm"
+  bottom: "conv3_3"
+  top: "conv3_3norm"
+  batch_norm_param{ }
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+}
+# *****************
+# ***** conv4 *****
+# *****************
+layer {
+  name: "conv4_1"
+  type: "Convolution"
+  # bottom: "conv3_3"
+  bottom: "conv3_3norm"
+  # bottom: "pool3"
+  top: "conv4_1"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    stride: 1
+    pad: 1
+    dilation: 1
+  }
+}
+layer {
+  name: "relu4_1"
+  type: "ReLU"
+  bottom: "conv4_1"
+  top: "conv4_1"
+}
+layer {
+  name: "conv4_2"
+  type: "Convolution"
+  bottom: "conv4_1"
+  top: "conv4_2"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    stride: 1
+    pad: 1
+    dilation: 1
+  }
+}
+layer {
+  name: "relu4_2"
+  type: "ReLU"
+  bottom: "conv4_2"
+  top: "conv4_2"
+}
+layer {
+  name: "conv4_3"
+  type: "Convolution"
+  bottom: "conv4_2"
+  top: "conv4_3"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    stride: 1
+    pad: 1
+    dilation: 1
+  }
+}
+layer {
+  name: "relu4_3"
+  type: "ReLU"
+  bottom: "conv4_3"
+  top: "conv4_3"
+}
+layer {
+  name: "conv4_3norm"
+  type: "BatchNorm"
+  bottom: "conv4_3"
+  top: "conv4_3norm"
+  batch_norm_param{ }
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+}
+# *****************
+# ***** conv5 *****
+# *****************
+layer {
+  name: "conv5_1"
+  type: "Convolution"
+  # bottom: "conv4_3"
+  bottom: "conv4_3norm"
+  # bottom: "pool4"
+  top: "conv5_1"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0}   
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    stride: 1
+    pad: 2
+    dilation: 2
+  }
+}
+layer {
+  name: "relu5_1"
+  type: "ReLU"
+  bottom: "conv5_1"
+  top: "conv5_1"
+}
+layer {
+  name: "conv5_2"
+  type: "Convolution"
+  bottom: "conv5_1"
+  top: "conv5_2"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    stride: 1
+    pad: 2
+    dilation: 2
+  }
+}
+layer {
+  name: "relu5_2"
+  type: "ReLU"
+  bottom: "conv5_2"
+  top: "conv5_2"
+}
+layer {
+  name: "conv5_3"
+  type: "Convolution"
+  bottom: "conv5_2"
+  top: "conv5_3"
+  # param {lr_mult: 0 decay_mult: 0} 
+  # param {lr_mult: 0 decay_mult: 0} 
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    stride: 1
+    pad: 2
+    dilation: 2
+  }
+}
+layer {
+  name: "relu5_3"
+  type: "ReLU"
+  bottom: "conv5_3"
+  top: "conv5_3"
+}
+layer {
+  name: "conv5_3norm"
+  type: "BatchNorm"
+  bottom: "conv5_3"
+  top: "conv5_3norm"
+  batch_norm_param{ }
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+}
+# *****************
+# ***** conv6 *****
+# *****************
+layer {
+  name: "conv6_1"
+  type: "Convolution"
+  bottom: "conv5_3norm"
+  top: "conv6_1"
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    pad: 2
+    dilation: 2
+  }
+}
+layer {
+  name: "relu6_1"
+  type: "ReLU"
+  bottom: "conv6_1"
+  top: "conv6_1"
+}
+layer {
+  name: "conv6_2"
+  type: "Convolution"
+  bottom: "conv6_1"
+  top: "conv6_2"
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    pad: 2
+    dilation: 2
+  }
+}
+layer {
+  name: "relu6_2"
+  type: "ReLU"
+  bottom: "conv6_2"
+  top: "conv6_2"
+}
+layer {
+  name: "conv6_3"
+  type: "Convolution"
+  bottom: "conv6_2"
+  top: "conv6_3"
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    pad: 2
+    dilation: 2
+  }
+}
+layer {
+  name: "relu6_3"
+  type: "ReLU"
+  bottom: "conv6_3"
+  top: "conv6_3"
+}
+layer {
+  name: "conv6_3norm"
+  type: "BatchNorm"
+  bottom: "conv6_3"
+  top: "conv6_3norm"
+  batch_norm_param{ }
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+}
+# *****************
+# ***** conv7 *****
+# *****************
+layer {
+  name: "conv7_1"
+  type: "Convolution"
+  bottom: "conv6_3norm"
+  top: "conv7_1"
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    pad: 1
+    dilation: 1
+  }
+}
+layer {
+  name: "relu7_1"
+  type: "ReLU"
+  bottom: "conv7_1"
+  top: "conv7_1"
+}
+layer {
+  name: "conv7_2"
+  type: "Convolution"
+  bottom: "conv7_1"
+  top: "conv7_2"
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    pad: 1
+    dilation: 1
+  }
+}
+layer {
+  name: "relu7_2"
+  type: "ReLU"
+  bottom: "conv7_2"
+  top: "conv7_2"
+}
+layer {
+  name: "conv7_3"
+  type: "Convolution"
+  bottom: "conv7_2"
+  top: "conv7_3"
+  convolution_param {
+    num_output: 512
+    kernel_size: 3
+    pad: 1
+    dilation: 1
+  }
+}
+layer {
+  name: "relu7_3"
+  type: "ReLU"
+  bottom: "conv7_3"
+  top: "conv7_3"
+}
+layer {
+  name: "conv7_3norm"
+  type: "BatchNorm"
+  bottom: "conv7_3"
+  top: "conv7_3norm"
+  batch_norm_param{ }
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+  param {lr_mult: 0 decay_mult: 0}
+}
+# *****************
+# ***** conv8 *****
+# *****************
+layer {
+  name: "conv8_1"
+  type: "Deconvolution"
+  bottom: "conv7_3norm"
+  top: "conv8_1"
+  convolution_param {
+    num_output: 256
+    kernel_size: 4
+    pad: 1
+    dilation: 1
+    stride: 2
+  }
+}
+layer {
+  name: "relu8_1"
+  type: "ReLU"
+  bottom: "conv8_1"
+  top: "conv8_1"
+}
+layer {
+  name: "conv8_2"
+  type: "Convolution"
+  bottom: "conv8_1"
+  top: "conv8_2"
+  convolution_param {
+    num_output: 256
+    kernel_size: 3
+    pad: 1
+    dilation: 1
+  }
+}
+layer {
+  name: "relu8_2"
+  type: "ReLU"
+  bottom: "conv8_2"
+  top: "conv8_2"
+}
+layer {
+  name: "conv8_3"
+  type: "Convolution"
+  bottom: "conv8_2"
+  top: "conv8_3"
+  convolution_param {
+    num_output: 256
+    kernel_size: 3
+    pad: 1
+    dilation: 1
+  }
+}
+layer {
+  name: "relu8_3"
+  type: "ReLU"
+  bottom: "conv8_3"
+  top: "conv8_3"
+}
+# *******************
+# ***** Softmax *****
+# *******************
+layer {
+  name: "conv8_313"
+  type: "Convolution"
+  bottom: "conv8_3"
+  top: "conv8_313"
+  convolution_param {
+    num_output: 313
+    kernel_size: 1
+    stride: 1
+    dilation: 1
+  }
+}
+layer {
+  name: "conv8_313_rh"
+  type: "Scale"
+  bottom: "conv8_313"
+  top: "conv8_313_rh"
+  scale_param {
+    bias_term: false
+    filler {      type: 'constant'      value: 2.606    }
+  }
+}
+layer {
+  name: "class8_313_rh"
+  type: "Softmax"
+  bottom: "conv8_313_rh"
+  top: "class8_313_rh"
+}
+# ********************
+# ***** Decoding *****
+# ********************
+layer {
+  name: "class8_ab"
+  type: "Convolution"
+  bottom: "class8_313_rh"
+  top: "class8_ab"
+  convolution_param {
+    num_output: 2
+    kernel_size: 1
+    stride: 1
+    dilation: 1
+  }
+}
+layer {
+  name: "Silence"
+  type: "Silence"
+  bottom: "class8_ab"
+}

src/models/colorization_release_v2.caffemodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5af1e602646328c792e1094f9876fe9cd4c09ac46fa886e5708a1abc89137b1
+size 128946764

src/models/pts_in_hull.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5dec01315c34f43f1c8c089e84c45ae35d1838d8e77ed0e7ca930f79ffa450e
+size 5088

src/utils.py

@@ -0,0 +1,90 @@
+import numpy as np
+import cv2
+from PIL import Image
+
+def convert_to_bw(image):
+    """
+    Converts a PIL image to black & white (grayscale),
+    and then back to RGB to maintain compatibility with other processes.
+    
+    Parameters:
+        image (PIL.Image): Input RGB image.
+
+    Returns:
+        PIL.Image: Black & white image in RGB format.
+    """
+    return image.convert("L").convert("RGB")
+
+def load_colorization_model():
+    """
+    Loads the pre-trained Caffe model for colorizing black & white images.
+    
+    Model files required:
+        - colorization_deploy_v2.prototxt
+        - colorization_release_v2.caffemodel
+        - pts_in_hull.npy
+
+    Returns:
+        cv2.dnn_Net: Loaded and initialized OpenCV DNN colorization model.
+    """
+    # Paths to model architecture, weights, and cluster centers
+    proto_file = "models/colorization_deploy_v2.prototxt"
+    model_file = "models/colorization_release_v2.caffemodel"
+    cluster_file = "models/pts_in_hull.npy"
+
+
+    # Load the model using OpenCV DNN module
+    net = cv2.dnn.readNetFromCaffe(proto_file, model_file)
+    pts = np.load(cluster_file)
+
+    # Populate cluster centers as 1x1 convolution kernel
+    class8_ab = net.getLayerId("class8_ab")
+    conv8_313_rh = net.getLayerId("conv8_313_rh")
+
+    pts = pts.transpose().reshape(2, 313, 1, 1)
+    net.getLayer(class8_ab).blobs = [pts.astype(np.float32)]
+    net.getLayer(conv8_313_rh).blobs = [np.full([1, 313], 2.606, dtype=np.float32)]
+
+    return net
+
+def colorize_bw_image(pil_img, net):
+    """
+    Colorizes a grayscale (black & white) image using a pre-trained DNN model.
+
+    Parameters:
+        pil_img (PIL.Image): Input grayscale image in RGB format.
+        net (cv2.dnn_Net): Loaded OpenCV DNN colorization model.
+
+    Returns:
+        PIL.Image: Colorized image in RGB format.
+    """
+    # Convert PIL image to NumPy array
+    img = np.array(pil_img)
+    img_rgb = img[:, :, [2, 1, 0]]  # Convert RGB to BGR
+    img_rgb = img_rgb.astype("float32") / 255.0
+    # Convert to LAB color space and extract L channel
+    img_lab = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2LAB)
+    l_channel = img_lab[:, :, 0]
+    
+    # Resize L channel to match model input size and normalize
+    input_l = cv2.resize(l_channel, (224, 224))
+    input_l -= 50
+    
+    # Run inference
+    net.setInput(cv2.dnn.blobFromImage(input_l))
+    ab_channels = net.forward()[0, :, :, :].transpose((1, 2, 0))  # shape: (56, 56, 2)
+
+    # Resize predicted ab channels to match original image size
+    ab_channels = cv2.resize(ab_channels, (img.shape[1], img.shape[0]))
+    
+    # Merge original L channel with predicted ab channels
+    lab_output = np.concatenate((l_channel[:, :, np.newaxis], ab_channels), axis=2)
+    
+    # Convert LAB to BGR, clip values, and convert to uint8
+    bgr_out = cv2.cvtColor(lab_output, cv2.COLOR_LAB2BGR)
+    bgr_out = np.clip(bgr_out, 0, 1)
+
+    
+    # Convert back to RGB and return as PIL Image
+    final_rgb = (bgr_out[:, :, [2, 1, 0]] * 255).astype("uint8")
+    return Image.fromarray(final_rgb)