import torch.nn as nn
import torch.utils.data.distributed
from torchvision.models.densenet import densenet201
from torchvision import transforms
from torchvision import datasets
import json
from imagemove2 import getlookup
a, b, c = getlookup()
d = [a[x] for x in a]
labels_1_ptype = {
0: 8,
1: 2,
2: 0,
3: 7,
4: 9,
5: 1,
6: 4,
7: 3,
8: 10,
9: 5,
10: 6,
}
startidx = {
'Apple': 0,
'Cedar': 4,
'Cherry': 6,
'Corn': 9,
'Grape': 17,
'Citrus': 24,
'Peach': 27,
else:
buf = param_state['momentum_buffer']
buf.mul_(momentum).add_(1 - dampening, d_p)
if nesterov:
d_p = d_p.add(momentum, buf)
else:
d_p = buf
p.data.add_(-group['lr'], d_p)
return loss
if __name__ == '__main__':
lookup = getlookup()
args = DotDict({
'batch_size': 32,
'batch_mul': 4,
'val_batch_size': 10,
'cuda': True,
'model': '',
'train_plot': False,
'epochs': [60],
'try_no': '1_densecedar',
'imsize': [224],
'imsize_l': [256],
# 'traindir': '/root/palm/DATA/plant/typesep_train/Cedar',
'valdir': '/media/palm/Unimportant/pdr2018/typesep_train/Cedar',
'workers': 4,
'resume': False,
def main():
root_path = '/media/palm/Unimportant/pdr2018/typesep_validate/Tomato/'
image_name = 'c9ebc74c2177ce60a8230855333fb9e7.jpg'
folder_name = '14_Tomato_Spider_Mite_Damage_Serious'
# image_path = root_path+'/14_Tomato_Spider_Mite_Damage_Serious/1c0f1ae1374d01c2933069232735a331.jpg'
image_path = os.path.join(root_path, folder_name, image_name)
topk = 1
cuda = 'cuda'
arch = 'densenet201'
CONFIG = {
'resnet152': {
'target_layer': 'layer4.2',
'input_size': 224
},
'vgg19': {
'target_layer': 'features.36',
'input_size': 224
},
'vgg19_bn': {
'target_layer': 'features.52',
'input_size': 224
},
'inception_v3': {
'target_layer': 'Mixed_7c',
'input_size': 299
},
'densenet201': {
'target_layer': 'features.denseblock4',
'input_size': 224
},
# Add your model
}.get(arch)
a, b, c = getlookup()
device = torch.device(
'cuda' if cuda and torch.cuda.is_available() else 'cpu')
if cuda:
current_device = torch.cuda.current_device()
print('Running on the GPU:',
torch.cuda.get_device_name(current_device))
else:
print('Running on the CPU')
# Synset words
classes = c['Tomato']
# Model
model = getmodel(20)
checkpoint = torch.load('checkpoint/try_4_densesep-Tomatotemp.t7')
model.load_state_dict(checkpoint['net'])
model.to('cuda')
model.eval()
# Image
raw_image = cv2.imread(image_path)[..., ::-1]
raw_image = cv2.resize(raw_image, (CONFIG['input_size'], ) * 2)
image = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
)
])(raw_image).unsqueeze(0)
# =========================================================================
print('Grad-CAM')
# =========================================================================
gcam = GradCAM(model=model)
probs, idx = gcam.forward(image.to(device))
for i in range(0, topk):
gcam.backward(idx=idx[i])
output = gcam.generate(target_layer=CONFIG['target_layer'])
save_gradcam(
'results/{}_{}_gcam_{}.png'.format(image_name, classes[idx[i]],
arch), output, raw_image)
print('[{:.5f}] {}'.format(probs[i], classes[idx[i]]))
# =========================================================================
print('Vanilla Backpropagation')
# =========================================================================
bp = BackPropagation(model=model)
probs, idx = bp.forward(image.to(device))
for i in range(0, topk):
bp.backward(idx=idx[i])
output = bp.generate()
save_gradient(
'results/{}_{}_bp_{}.png'.format(image_name, classes[idx[i]],
arch), output)
print('[{:.5f}] {}'.format(probs[i], classes[idx[i]]))
# =========================================================================
print('Deconvolution')
# =========================================================================
deconv = Deconvolution(
model=copy.deepcopy(model)) # TODO: remove hook func in advance
probs, idx = deconv.forward(image.to(device))
for i in range(0, topk):
deconv.backward(idx=idx[i])
output = deconv.generate()
save_gradient(
'results/{}_{}_deconv_{}.png'.format(image_name, classes[idx[i]],
arch), output)
print('[{:.5f}] {}'.format(probs[i], classes[idx[i]]))
# =========================================================================
print('Guided Backpropagation/Guided Grad-CAM')
# =========================================================================
gbp = GuidedBackPropagation(model=model)
probs, idx = gbp.forward(image.to(device))
for i in range(0, topk):
gcam.backward(idx=idx[i])
region = gcam.generate(target_layer=CONFIG['target_layer'])
gbp.backward(idx=idx[i])
feature = gbp.generate()
h, w, _ = feature.shape
region = cv2.resize(region, (w, h))[..., np.newaxis]
output = feature * region
save_gradient(
'results/{}_{}_gbp_{}.png'.format(image_name, classes[idx[i]],
arch), feature)
save_gradient(
'results/{}_{}_ggcam_{}.png'.format(image_name, classes[idx[i]],
arch), output)
print('[{:.5f}] {}'.format(probs[i], classes[idx[i]]))
