Spaces:
Sleeping
Sleeping
File size: 10,463 Bytes
4db4d66 f94c291 4db4d66 f94c291 4db4d66 f94c291 4db4d66 aa9b93a 4db4d66 5596c9b 4db4d66 c8586d3 c881a28 4db4d66 4822531 4db4d66 c8586d3 4db4d66 4822531 c881a28 4db4d66 4822531 4db4d66 c881a28 4db4d66 ad8aabf c881a28 4822531 4db4d66 a76f9a5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 |
import gradio as gr
import random
import pathlib
import numpy as np
from PIL import Image
import torch
import torchvision
from pytorch_grad_cam import GradCAM
from pytorch_grad_cam.utils.image import show_cam_on_image
from models.resnet_lightning import ResNet
from utils.data import CIFARDataModule
from utils.transforms import test_transform
from utils.common import get_misclassified_data
inv_normalize = torchvision.transforms.Normalize(
mean=[-0.50 / 0.23, -0.50 / 0.23, -0.50 / 0.23], std=[1 / 0.23, 1 / 0.23, 1 / 0.23]
)
datamodule = CIFARDataModule()
datamodule.setup()
classes = datamodule.train_dataset.classes
model = ResNet.load_from_checkpoint("model.ckpt")
model = model.to("cpu")
prediction_image = None
def upload_file(files):
file_paths = [file.name for file in files]
return file_paths
def read_image(path):
img = Image.open(path)
img.load()
data = np.asarray(img, dtype="uint8")
return data
# def sample_images():
# images = []
# length = len(datamodule.test_dataset)
# classes = datamodule.train_dataset.classes
# for i in range(10):
# idx = random.randint(0, length - 1)
# image, label = datamodule.test_dataset[idx]
# image = inv_normalize(image).permute(1, 2, 0).numpy()
# images.append((image, classes[label]))
# return images
def sample_images():
sample_imges_dir = pathlib.Path("./sample_images")
sample_images = list(sample_imges_dir.iterdir())
sample_image_labels = [image.stem for image in sample_images]
return list(zip(sample_images, sample_image_labels))
def get_misclassified_images(misclassified_count):
misclassified_images = []
misclassified_data = get_misclassified_data(
model=model,
device="cpu",
test_loader=datamodule.test_dataloader(),
count=misclassified_count,
)
for i in range(misclassified_count):
img = misclassified_data[i][0].squeeze().to("cpu")
img = inv_normalize(img)
img = np.transpose(img.numpy(), (1, 2, 0))
label = f"Label: {classes[misclassified_data[i][1].item()]} | Prediction: {classes[misclassified_data[i][2].item()]}"
misclassified_images.append((img, label))
return misclassified_images
def get_gradcam_images(gradcam_layer, gradcam_count, gradcam_opacity):
gradcam_images = []
if gradcam_layer == "Layer1":
target_layers = [model.layer1[-1]]
elif gradcam_layer == "Layer2":
target_layers = [model.layer2[-1]]
else:
target_layers = [model.layer3[-1]]
cam = GradCAM(model=model, target_layers=target_layers, use_cuda=False)
data = get_misclassified_data(
model=model,
device="cpu",
test_loader=datamodule.test_dataloader(),
count=gradcam_count,
)
for i in range(gradcam_count):
input_tensor = data[i][0]
# Get the activations of the layer for the images
grayscale_cam = cam(input_tensor=input_tensor, targets=None)
grayscale_cam = grayscale_cam[0, :]
# Get back the original image
img = input_tensor.squeeze(0).to("cpu")
if inv_normalize is not None:
img = inv_normalize(img)
rgb_img = np.transpose(img, (1, 2, 0))
rgb_img = rgb_img.numpy()
# Mix the activations on the original image
visualization = show_cam_on_image(
rgb_img, grayscale_cam, use_rgb=True, image_weight=gradcam_opacity
)
label = f"Label: {classes[data[i][1].item()]} | Prediction: {classes[data[i][2].item()]}"
gradcam_images.append((visualization, label))
return gradcam_images
def show_hide_misclassified(status):
if not status:
return {misclassified_count: gr.update(visible=False)}
return {misclassified_count: gr.update(visible=True)}
def show_hide_gradcam(status):
if not status:
return [gr.update(visible=False) for i in range(3)]
return [gr.update(visible=True) for i in range(3)]
def set_prediction_image(evt: gr.SelectData, gallery):
global prediction_image
if isinstance(gallery[evt.index], dict):
prediction_image = gallery[evt.index]["name"]
else:
prediction_image = gallery[evt.index][0]["name"]
def predict(
is_misclassified,
misclassified_count,
is_gradcam,
gradcam_count,
gradcam_layer,
gradcam_opacity,
num_classes,
):
if prediction_image is None:
raise gr.Error(
"Please select one of the sample image or upload an image for prediction!"
)
misclassified_images = None
if is_misclassified:
misclassified_images = get_misclassified_images(int(misclassified_count))
gradcam_images = None
if is_gradcam:
gradcam_images = get_gradcam_images(
gradcam_layer, int(gradcam_count), gradcam_opacity
)
img = read_image(prediction_image)
image_transformed = test_transform(image=img)["image"]
output = model(image_transformed.unsqueeze(0))
preds = torch.softmax(output, dim=1).squeeze().detach().numpy()
indices = (
output.argsort(descending=True).squeeze().detach().numpy()[: int(num_classes)]
)
predictions = {classes[i]: round(float(preds[i]), 2) for i in indices}
return {
miscalssfied_output: gr.update(value=misclassified_images),
gradcam_output: gr.update(value=gradcam_images),
prediction_label: gr.update(value=predictions),
}
with gr.Blocks() as app:
gr.Markdown("## CIFAR10 Classification with ResNet")
with gr.Row():
with gr.Column():
with gr.Box():
is_misclassified = gr.Checkbox(
label="Misclassified Images", info="Display misclassified images?"
)
misclassified_count = gr.Dropdown(
choices=[str(i + 1) for i in range(20)],
value=5,
label="Select Number of Images",
info="Number of Misclassified images (Default:5)",
visible=False,
interactive=True,
)
is_misclassified.input(
show_hide_misclassified,
inputs=[is_misclassified],
outputs=[misclassified_count],
)
with gr.Box():
is_gradcam = gr.Checkbox(
label="GradCAM Images",
info="Display GradCAM images?",
)
gradcam_count = gr.Dropdown(
choices=[str(i + 1) for i in range(20)],
label="Select Number of Images",
info="Number of GradCAM images (Default:5)",
value=5,
interactive=True,
visible=False,
)
gradcam_layer = gr.Dropdown(
choices=["Layer1", "Layer2", "Layer3"],
label="Select the layer",
info="Please select the layer for which the GradCAM is required (Default:Layer3)",
interactive=True,
value="Layer3",
visible=False,
)
gradcam_opacity = gr.Slider(
minimum=0,
maximum=1,
value=0.6,
label="Opacity",
info="Opacity of GradCAM output",
interactive=True,
visible=False,
)
is_gradcam.input(
show_hide_gradcam,
inputs=[is_gradcam],
outputs=[gradcam_count, gradcam_layer, gradcam_opacity],
)
with gr.Box():
# file_output = gr.File(file_types=["image"])
with gr.Group():
upload_gallery = gr.Gallery(
value=None,
label="Uploaded images",
show_label=False,
elem_id="gallery_upload",
columns=5,
rows=2,
height="auto",
object_fit="contain",
)
upload_button = gr.UploadButton(
"Click to Upload images",
file_types=["image"],
file_count="multiple",
)
upload_button.upload(upload_file, upload_button, upload_gallery)
with gr.Group():
sample_gallery = gr.Gallery(
value=sample_images,
label="Sample images",
show_label=True,
elem_id="gallery_sample",
columns=5,
rows=2,
height="auto",
object_fit="contain",
)
upload_gallery.select(set_prediction_image, inputs=[upload_gallery])
sample_gallery.select(set_prediction_image, inputs=[sample_gallery])
with gr.Box():
num_classes = gr.Dropdown(
choices=[str(i + 1) for i in range(10)],
label="Select Number of Top Classes",
value=5,
interactive=True,
info="Number of Top target classes to be shown (Default:5)",
)
run_btn = gr.Button()
with gr.Column():
with gr.Box():
miscalssfied_output = gr.Gallery(
value=None, label="Misclassified Images", show_label=True
)
with gr.Box():
gradcam_output = gr.Gallery(
value=None, label="GradCAM Images", show_label=True
)
with gr.Box():
prediction_label = gr.Label(value=None, label="Predictions")
run_btn.click(
predict,
inputs=[
is_misclassified,
misclassified_count,
is_gradcam,
gradcam_count,
gradcam_layer,
gradcam_opacity,
num_classes,
],
outputs=[miscalssfied_output, gradcam_output, prediction_label],
)
app.launch()
|