Spaces:
Sleeping
Sleeping
File size: 5,834 Bytes
37988e9 e5b58ae 37988e9 e5b58ae 37988e9 1e68385 9bd912f 1e68385 9bd912f 37988e9 b161d2c 37988e9 78dd9f7 37988e9 | 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 | import torch, torchvision
from torchvision import transforms
import numpy as np
import gradio as gr
from PIL import Image
from pytorch_grad_cam import GradCAM
from pytorch_grad_cam.utils.image import show_cam_on_image
from torch.utils.data import DataLoader
import itertools
import matplotlib.pyplot as plt
import utils as utils
from model import Net
model = Net()
model.load_state_dict(torch.load("model.pth", map_location=torch.device('cpu')), strict=False)
model.eval()
classes = ('plane', 'car', 'bird', 'cat', 'deer',
'dog', 'frog', 'horse', 'ship', 'truck')
cifar_valid = utils.Cifar10SearchDataset('.', train=False, download=True, transform=utils.augmentation_custom_resnet())
inv_normalize = 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]
)
def inference(wants_gradcam, n_gradcam, target_layer_number, transparency, wants_misclassified, n_misclassified, input_img = None, n_top_classes=10):
if wants_gradcam:
outputs_inference_gc = []
cifar_valid_loader = DataLoader(cifar_valid, batch_size=1, shuffle = True)
count_gradcam = 1
for data, target in cifar_valid_loader:
data, target = data.to('cpu'), target.to('cpu')
if target_layer_number == '-2':
target_layers = [model.convblock31[0]]
elif target_layer_number == '-1':
target_layers = [model.convblock21[0]]
cam = GradCAM(model=model, target_layers=target_layers, use_cuda=False)
grayscale_cam = cam(input_tensor=data, targets=None)
grayscale_cam = grayscale_cam[0, :]
org_img = inv_normalize(data).squeeze(0).numpy()
org_img = np.transpose(org_img, (1, 2, 0))
visualization = np.array(show_cam_on_image(org_img, grayscale_cam, use_rgb=True, image_weight=transparency))
outputs_inference_gc.append(visualization)
count_gradcam += 1
if count_gradcam > n_gradcam:
break
else:
outputs_inference_gc = None
if wants_misclassified:
outputs_inference_mis = []
cifar_valid_loader = DataLoader(cifar_valid, batch_size=1, shuffle = True)
count_mis = 1
for data, target in cifar_valid_loader:
data, target = data.to('cpu'), target.to('cpu')
outputs = model(data)
softmax = torch.nn.Softmax(dim=0)
o = softmax(outputs.flatten())
confidences = {classes[i]: float(o[i]) for i in range(10)}
_, prediction = torch.max(outputs, 1)
if target.numpy()[0] != prediction.numpy()[0]:
count_mis += 1
org_img = inv_normalize(data).squeeze(0).numpy()
org_img = np.transpose(org_img, (1, 2, 0))
fig = plt.figure()
fig.add_subplot(111)
plt.imshow(org_img)
plt.title(f'Target: {classes[target.numpy()[0]]}\nPred: {classes[prediction.numpy()[0]]}')
plt.axis('off')
fig.canvas.draw()
fig_img = np.frombuffer(fig.canvas.tostring_rgb(), dtype=np.uint8)
fig_img = fig_img.reshape(fig.canvas.get_width_height()[::-1] + (3,))
plt.close(fig)
outputs_inference_mis.append(fig_img)
if count_mis > n_misclassified:
break
else:
outputs_inference_mis = None
if input_img is not None:
transform=utils.augmentation_custom_resnet('Valid')
org_img = input_img
input_img = transform(image=input_img)
input_img = input_img['image'].unsqueeze(0)
outputs = model(input_img)
softmax = torch.nn.Softmax(dim=0)
o = softmax(outputs.flatten())
confidences = {classes[i]: float(o[i]) for i in range(10)}
_, prediction = torch.max(outputs, 1)
confidences = {k: v for k, v in sorted(confidences.items(), key=lambda item: item[1], reverse=True)}
confidences = dict(itertools.islice(confidences.items(), n_top_classes))
else:
confidences = None
return outputs_inference_gc, outputs_inference_mis, confidences
title = "CIFAR10 trained on Custom ResNet Model with GradCAM"
description = "A Gradio interface to infer on Custom ResNet model, and to get GradCAM results"
examples = [[None, None, None, None, None, None, 'examples/gr_'+str(i)+'.jpg', None] for i in range(10)]
demo = gr.Interface(inference,
inputs = [gr.Checkbox(False, label='Do you want to see GradCAM outputs?'),
gr.Slider(0, 10, value = 0, step=1, label="How many?"),
gr.inputs.Dropdown([-2, -1], label="Which target layer?"),
gr.Slider(0, 1, value = 0, label="Opacity of GradCAM"),
gr.Checkbox(False, label='Do you want to see misclassified images?'),
gr.Slider(0, 10, value = 0, step=1, label="How many?"),
gr.Image(shape=(32, 32), label="Input image"),
gr.Slider(0, 10, value = 0, step=1, label="How many top classes you want to see?")
],
outputs = [
gr.Gallery(label="GradCAM Outputs", show_label=True, elem_id="gallery").style(columns=[2], rows=[2], object_fit="contain", height="auto"),
gr.Gallery(label="Misclassified Images", show_label=True, elem_id="gallery").style(columns=[2], rows=[2], object_fit="contain", height="auto"),
gr.Label(num_top_classes=10, label = "Top classes")
],
title = title,
description = description,
examples = examples
)
demo.launch() |