Update files

app.py

@@ -0,0 +1,94 @@
+### 1. Imports and class names setup ### 
+import gradio as gr
+import os
+import torch
+from torch import nn
+from typing import Dict
+import torchvision
+from torchvision import transforms
+import PIL
+import numpy
+
+# import os
+# os.system("pip uninstall -y gradio")
+# os.system("pip install gradio==3.50.2")
+
+with open("class_names.txt", "r") as f: # reading them in from class_names.txt
+    class_names = [food_name.strip() for food_name in  f.readlines()]
+
+
+mobileNetV3_transform = torchvision.models.MobileNet_V3_Large_Weights.DEFAULT.transforms()
+
+mobileNetV3 = torchvision.models.mobilenet_v3_large()
+    
+mobileNetV3.classifier = nn.Sequential(
+  nn.Linear(in_features=960, out_features=1280, bias=True),
+  nn.Hardswish(),
+  nn.Dropout(p=0.2, inplace=True),
+  nn.Linear(in_features=1280, out_features=len(class_names), bias=True)
+)
+
+mobileNetV3.load_state_dict(torch.load("models/mobileNetV3_quickdraw_animals_epoch_80_Adam.pth",map_location=torch.device('cpu')))
+
+
+
+def convert_img_to_tensor(img):
+    convert_img = torch.from_numpy(img)
+    convert_img = convert_img.repeat(3, 1, 1)
+    return convert_img
+
+
+
+def predict(img) -> Dict:
+    """Transforms and performs a prediction on img and returns prediction and time taken.
+    """
+    # Start the timer
+    # print(type(img))
+    # img = img['composite']
+    # if type(img) == numpy.ndarray:
+    #   img = PIL.Image.fromarray(img)
+    img = convert_img_to_tensor(img)
+    # padding =  transforms.CenterCrop([224, 224])
+    # img = padding(img)
+    # img = torch.from_numpy(img)
+    # print(img.shape)
+    # Transform the target image and add a batch dimension
+    # # img = torch.tensor(img, dtype=torch.float32).unsqueeze(0).unsqueeze(0) / 255
+    img = mobileNetV3_transform(img).unsqueeze(0)
+    # img = image_transform(img).unsqueeze(0)
+
+
+    # Put model into evaluation mode and turn on inference mode
+    mobileNetV3.eval()
+    with torch.inference_mode():
+        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
+        y_pred = mobileNetV3(img)
+        pred_probs = torch.softmax(y_pred, dim=1)
+        # y_pred_class = torch.argmax(torch.softmax(y_pred, dim=1), dim=1)
+
+    # Create a prediction label and prediction probability dictionary for each prediction class (this is the required format for Gradio's output parameter)
+    pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
+
+    # Calculate the prediction time
+
+    # Return the prediction dictionary and prediction time
+    return pred_labels_and_probs
+
+title = "MobileNetV3 - Quick Draw - Animals 🔢"
+description = "An MobileNetV3 feature extractor computer vision model to classify doodling of animals."
+article = "Created using transfer learning from MobileNetV3"
+
+
+sp = gr.Sketchpad(shape = (28,28), brush_radius = 1)
+# sp = gr.Sketchpad(type = "pil")
+demo = gr.Interface(
+    fn=predict,
+    inputs=sp,
+    outputs= gr.Label(num_top_classes=5, label="Predictions"),
+    # outputs= gr.Image(),
+    # examples=example_list,
+    # title=title,
+    # description=description,
+    # article=article,
+)
+demo.launch(debug=True)

class_names.txt

@@ -0,0 +1,42 @@
+Ant
+Bat
+Bear
+Bee
+Bird
+Crab
+Crocodile
+Dog
+Dolphin
+Donut
+Dragon
+Elephant
+Flamingo
+Frog
+Giraffe
+Hedgehog
+Horse
+Kangaroo
+Lion
+Lobster
+Monkey
+Octopus
+Owl
+Panda
+Parrot
+Penguin
+Pig
+Rabbit
+Raccoon
+Rhinoceros
+Scorpion
+Sea Turtle
+Shark
+Sheep
+Snail
+Snake
+Spider
+Squirrel
+Swan
+Tiger
+Whale
+Zebra

models/mobileNetV3_quickdraw_animals_epoch_80_Adam.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57405814360d60d10c8bb7562be945e338844ffbca061796ace78d4bf2a74493
+size 17245682

requirements.txt

@@ -0,0 +1,3 @@
+torch
+torchvision
+gradio==3.50.2