Upload MyPipe.py

MyPipe.py

@@ -1,4 +1,3 @@
-
 import torch, os
 import torch.nn.functional as F
 from torchvision.transforms.functional import normalize
@@ -7,70 +6,75 @@ from transformers import Pipeline
 from skimage import io
 from PIL import Image
 
+
 class RMBGPipe(Pipeline):
-  def __init__(self,**kwargs):
-    Pipeline.__init__(self,**kwargs)
-    self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-    self.model.to(self.device)
-    self.model.eval()
+    def __init__(self, **kwargs):
+        Pipeline.__init__(self, **kwargs)
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.model.to(self.device)
+        self.model.eval()
+
+    def _sanitize_parameters(self, **kwargs):
+        # parse parameters
+        preprocess_kwargs = {}
+        postprocess_kwargs = {}
+        if "model_input_size" in kwargs:
+            preprocess_kwargs["model_input_size"] = kwargs["model_input_size"]
+        if "out_name" in kwargs:
+            postprocess_kwargs["out_name"] = kwargs["out_name"]
+        return preprocess_kwargs, {}, postprocess_kwargs
+
+    def preprocess(self, orig_im: Image, model_input_size: list = [1024, 1024]):
+        # preprocess the input
+        orig_im_size = orig_im.shape[0:2]
+        image = self.preprocess_image(orig_im, model_input_size).to(self.device)
+        inputs = {
+            "orig_im": orig_im,
+            "image": image,
+            "orig_im_size": orig_im_size,
+        }
+        return inputs
 
-  def _sanitize_parameters(self, **kwargs):
-    # parse parameters
-    preprocess_kwargs = {}
-    postprocess_kwargs = {}
-    if "model_input_size" in kwargs : 
-      preprocess_kwargs["model_input_size"] = kwargs["model_input_size"]
-    if "out_name" in kwargs: 
-      postprocess_kwargs["out_name"] = kwargs["out_name"]
-    return preprocess_kwargs, {}, postprocess_kwargs
+    def _forward(self, inputs):
+        result = self.model(inputs.pop("image"))
+        inputs["result"] = result
+        return inputs
 
-  def preprocess(self,im_path:str,model_input_size: list=[1024,1024]):
-      # preprocess the input 
-      orig_im = io.imread(im_path)
-      orig_im_size = orig_im.shape[0:2]
-      image = self.preprocess_image(orig_im, model_input_size).to(self.device)
-      inputs = {
-          "image":image,
-          "orig_im_size":orig_im_size,
-          "im_path" : im_path
-      }
-      return inputs
+    def postprocess(self, inputs, out_name=""):
+        result = inputs.pop("result")
+        orig_im_size = inputs.pop("orig_im_size")
+        orig_image = inputs.pop("orig_image")
+        result_image = self.postprocess_image(result[0][0], orig_im_size)
+        if out_name != "":
+            # if out_name is specified we save the image using that name
+            pil_im = Image.fromarray(result_image)
+            no_bg_image = Image.new("RGBA", pil_im.size, (0, 0, 0, 0))
+            no_bg_image.paste(orig_image, mask=pil_im)
+            no_bg_image.save(out_name)
+        else:
+            return result_image
 
-  def _forward(self,inputs):
-    result = self.model(inputs.pop("image"))
-    inputs["result"] = result
-    return inputs
-  def postprocess(self,inputs,out_name = ""):
-    result = inputs.pop("result")
-    orig_im_size = inputs.pop("orig_im_size")
-    im_path = inputs.pop("im_path")
-    result_image = self.postprocess_image(result[0][0], orig_im_size)
-    if out_name != "" : 
-      # if out_name is specified we save the image using that name
-      pil_im = Image.fromarray(result_image)
-      no_bg_image = Image.new("RGBA", pil_im.size, (0,0,0,0))
-      orig_image = Image.open(im_path)
-      no_bg_image.paste(orig_image, mask=pil_im)
-      no_bg_image.save(out_name)
-    else : 
-      return result_image
+    # utilities functions
+    def preprocess_image(
+        self, im: np.ndarray, model_input_size: list = [1024, 1024]
+    ) -> torch.Tensor:
+        # same as utilities.py with minor modification
+        if len(im.shape) < 3:
+            im = im[:, :, np.newaxis]
+        # orig_im_size=im.shape[0:2]
+        im_tensor = torch.tensor(im, dtype=torch.float32).permute(2, 0, 1)
+        im_tensor = F.interpolate(
+            torch.unsqueeze(im_tensor, 0), size=model_input_size, mode="bilinear"
+        ).type(torch.uint8)
+        image = torch.divide(im_tensor, 255.0)
+        image = normalize(image, [0.5, 0.5, 0.5], [1.0, 1.0, 1.0])
+        return image
 
-  # utilities functions
-  def preprocess_image(self,im: np.ndarray, model_input_size: list=[1024,1024]) -> torch.Tensor:
-    # same as utilities.py with minor modification
-    if len(im.shape) < 3:
-        im = im[:, :, np.newaxis]
-    # orig_im_size=im.shape[0:2]
-    im_tensor = torch.tensor(im, dtype=torch.float32).permute(2,0,1)
-    im_tensor = F.interpolate(torch.unsqueeze(im_tensor,0), size=model_input_size, mode='bilinear').type(torch.uint8)
-    image = torch.divide(im_tensor,255.0)
-    image = normalize(image,[0.5,0.5,0.5],[1.0,1.0,1.0])
-    return image
-  def postprocess_image(self,result: torch.Tensor, im_size: list)-> np.ndarray:
-      result = torch.squeeze(F.interpolate(result, size=im_size, mode='bilinear') ,0)
-      ma = torch.max(result)
-      mi = torch.min(result)
-      result = (result-mi)/(ma-mi)
-      im_array = (result*255).permute(1,2,0).cpu().data.numpy().astype(np.uint8)
-      im_array = np.squeeze(im_array)
-      return im_array
+    def postprocess_image(self, result: torch.Tensor, im_size: list) -> np.ndarray:
+        result = torch.squeeze(F.interpolate(result, size=im_size, mode="bilinear"), 0)
+        ma = torch.max(result)
+        mi = torch.min(result)
+        result = (result - mi) / (ma - mi)
+        im_array = (result * 255).permute(1, 2, 0).cpu().data.numpy().astype(np.uint8)
+        im_array = np.squeeze(im_array)
+        return im_array