Practical Deep Learning for Coders, v3¶
Lesson6_pets_more¶
In [ ]:
%reload_ext autoreload
%autoreload 2
%matplotlib inline
from fastai.vision import *
In [ ]:
bs = 64
In [ ]:
path = untar_data(URLs.PETS)/'images'
Data augmentation 数据增强¶
In [ ]:
tfms = get_transforms(max_rotate=20, max_zoom=1.3, max_lighting=0.4, max_warp=0.4,
p_affine=1., p_lighting=1.)
In [ ]:
doc(get_transforms)
In [ ]:
src = ImageList.from_folder(path).split_by_rand_pct(0.2, seed=2)
In [ ]:
def get_data(size, bs, padding_mode='reflection'):
return (src.label_from_re(r'([^/]+)_\d+.jpg$')
.transform(tfms, size=size, padding_mode=padding_mode)
.databunch(bs=bs).normalize(imagenet_stats))
In [ ]:
data = get_data(224, bs, 'zeros')
In [ ]:
def _plot(i,j,ax):
x,y = data.train_ds[3]
x.show(ax, y=y)
plot_multi(_plot, 3, 3, figsize=(8,8))
In [ ]:
data = get_data(224,bs)
In [ ]:
plot_multi(_plot, 3, 3, figsize=(8,8))
Train a model 训练网络¶
In [ ]:
gc.collect()
learn = cnn_learner(data, models.resnet34, metrics=error_rate, bn_final=True)
Out[ ]:
29237
In [ ]:
learn.fit_one_cycle(3, slice(1e-2), pct_start=0.8)
Total time: 01:08
| epoch | train_loss | valid_loss | error_rate | time |
|---|---|---|---|---|
| 0 | 2.458192 | 1.221388 | 0.276049 | 00:23 |
| 1 | 1.467777 | 0.333426 | 0.078484 | 00:22 |
| 2 | 0.906456 | 0.259250 | 0.066982 | 00:22 |
In [ ]:
learn.unfreeze()
learn.fit_one_cycle(2, max_lr=slice(1e-6,1e-3), pct_start=0.8)
Total time: 00:59
| epoch | train_loss | valid_loss | error_rate | time |
|---|---|---|---|---|
| 0 | 0.708001 | 0.269306 | 0.058187 | 00:29 |
| 1 | 0.666836 | 0.267181 | 0.060217 | 00:29 |
In [ ]:
data = get_data(352,bs)
learn.data = data
In [ ]:
learn.fit_one_cycle(2, max_lr=slice(1e-6,1e-4))
Total time: 02:15
| epoch | train_loss | valid_loss | error_rate | time |
|---|---|---|---|---|
| 0 | 0.633500 | 0.261447 | 0.054804 | 01:08 |
| 1 | 0.595398 | 0.259402 | 0.051421 | 01:06 |
In [ ]:
learn.save('352')
Convolution kernel 卷积核¶
In [ ]:
data = get_data(352,16)
In [ ]:
learn = cnn_learner(data, models.resnet34, metrics=error_rate, bn_final=True).load('352')
In [ ]:
idx=0
x,y = data.valid_ds[idx]
x.show()
data.valid_ds.y[idx]
Out[ ]:
Category newfoundland
In [ ]:
k = tensor([
[0. ,-5/3,1],
[-5/3,-5/3,1],
[1. ,1 ,1],
]).expand(1,3,3,3)/6
In [ ]:
k
Out[ ]:
tensor([[[[ 0.0000, -0.2778, 0.1667],
[-0.2778, -0.2778, 0.1667],
[ 0.1667, 0.1667, 0.1667]],
[[ 0.0000, -0.2778, 0.1667],
[-0.2778, -0.2778, 0.1667],
[ 0.1667, 0.1667, 0.1667]],
[[ 0.0000, -0.2778, 0.1667],
[-0.2778, -0.2778, 0.1667],
[ 0.1667, 0.1667, 0.1667]]]])
In [ ]:
k.shape
Out[ ]:
torch.Size([1, 3, 3, 3])
In [ ]:
t = data.valid_ds[0][0].data; t.shape
Out[ ]:
torch.Size([3, 352, 352])
In [ ]:
t[None].shape
Out[ ]:
torch.Size([1, 3, 352, 352])
In [ ]:
edge = F.conv2d(t[None], k)
In [ ]:
show_image(edge[0], figsize=(5,5));
In [ ]:
data.c
Out[ ]:
37
In [ ]:
learn.model
Out[ ]:
Sequential(
(0): Sequential(
(0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace)
(3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(4): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(1): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(5): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(3): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(6): Sequential(
(0): BasicBlock(
(conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(3): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(4): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(5): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(7): Sequential(
(0): BasicBlock(
(conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
)
(1): Sequential(
(0): AdaptiveConcatPool2d(
(ap): AdaptiveAvgPool2d(output_size=1)
(mp): AdaptiveMaxPool2d(output_size=1)
)
(1): Flatten()
(2): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): Dropout(p=0.25)
(4): Linear(in_features=1024, out_features=512, bias=True)
(5): ReLU(inplace)
(6): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): Dropout(p=0.5)
(8): Linear(in_features=512, out_features=37, bias=True)
(9): BatchNorm1d(37, eps=1e-05, momentum=0.01, affine=True, track_running_stats=True)
)
)
In [ ]:
print(learn.summary())
====================================================================== Layer (type) Output Shape Param # Trainable ====================================================================== Conv2d [64, 176, 176] 9,408 False ______________________________________________________________________ BatchNorm2d [64, 176, 176] 128 True ______________________________________________________________________ ReLU [64, 176, 176] 0 False ______________________________________________________________________ MaxPool2d [64, 88, 88] 0 False ______________________________________________________________________ Conv2d [64, 88, 88] 36,864 False ______________________________________________________________________ BatchNorm2d [64, 88, 88] 128 True ______________________________________________________________________ ReLU [64, 88, 88] 0 False ______________________________________________________________________ Conv2d [64, 88, 88] 36,864 False ______________________________________________________________________ BatchNorm2d [64, 88, 88] 128 True ______________________________________________________________________ Conv2d [64, 88, 88] 36,864 False ______________________________________________________________________ BatchNorm2d [64, 88, 88] 128 True ______________________________________________________________________ ReLU [64, 88, 88] 0 False ______________________________________________________________________ Conv2d [64, 88, 88] 36,864 False ______________________________________________________________________ BatchNorm2d [64, 88, 88] 128 True ______________________________________________________________________ Conv2d [64, 88, 88] 36,864 False ______________________________________________________________________ BatchNorm2d [64, 88, 88] 128 True ______________________________________________________________________ ReLU [64, 88, 88] 0 False ______________________________________________________________________ Conv2d [64, 88, 88] 36,864 False ______________________________________________________________________ BatchNorm2d [64, 88, 88] 128 True ______________________________________________________________________ Conv2d [128, 44, 44] 73,728 False ______________________________________________________________________ BatchNorm2d [128, 44, 44] 256 True ______________________________________________________________________ ReLU [128, 44, 44] 0 False ______________________________________________________________________ Conv2d [128, 44, 44] 147,456 False ______________________________________________________________________ BatchNorm2d [128, 44, 44] 256 True ______________________________________________________________________ Conv2d [128, 44, 44] 8,192 False ______________________________________________________________________ BatchNorm2d [128, 44, 44] 256 True ______________________________________________________________________ Conv2d [128, 44, 44] 147,456 False ______________________________________________________________________ BatchNorm2d [128, 44, 44] 256 True ______________________________________________________________________ ReLU [128, 44, 44] 0 False ______________________________________________________________________ Conv2d [128, 44, 44] 147,456 False ______________________________________________________________________ BatchNorm2d [128, 44, 44] 256 True ______________________________________________________________________ Conv2d [128, 44, 44] 147,456 False ______________________________________________________________________ BatchNorm2d [128, 44, 44] 256 True ______________________________________________________________________ ReLU [128, 44, 44] 0 False ______________________________________________________________________ Conv2d [128, 44, 44] 147,456 False ______________________________________________________________________ BatchNorm2d [128, 44, 44] 256 True ______________________________________________________________________ Conv2d [128, 44, 44] 147,456 False ______________________________________________________________________ BatchNorm2d [128, 44, 44] 256 True ______________________________________________________________________ ReLU [128, 44, 44] 0 False ______________________________________________________________________ Conv2d [128, 44, 44] 147,456 False ______________________________________________________________________ BatchNorm2d [128, 44, 44] 256 True ______________________________________________________________________ Conv2d [256, 22, 22] 294,912 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ ReLU [256, 22, 22] 0 False ______________________________________________________________________ Conv2d [256, 22, 22] 589,824 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ Conv2d [256, 22, 22] 32,768 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ Conv2d [256, 22, 22] 589,824 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ ReLU [256, 22, 22] 0 False ______________________________________________________________________ Conv2d [256, 22, 22] 589,824 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ Conv2d [256, 22, 22] 589,824 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ ReLU [256, 22, 22] 0 False ______________________________________________________________________ Conv2d [256, 22, 22] 589,824 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ Conv2d [256, 22, 22] 589,824 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ ReLU [256, 22, 22] 0 False ______________________________________________________________________ Conv2d [256, 22, 22] 589,824 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ Conv2d [256, 22, 22] 589,824 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ ReLU [256, 22, 22] 0 False ______________________________________________________________________ Conv2d [256, 22, 22] 589,824 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ Conv2d [256, 22, 22] 589,824 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ ReLU [256, 22, 22] 0 False ______________________________________________________________________ Conv2d [256, 22, 22] 589,824 False ______________________________________________________________________ BatchNorm2d [256, 22, 22] 512 True ______________________________________________________________________ Conv2d [512, 11, 11] 1,179,648 False ______________________________________________________________________ BatchNorm2d [512, 11, 11] 1,024 True ______________________________________________________________________ ReLU [512, 11, 11] 0 False ______________________________________________________________________ Conv2d [512, 11, 11] 2,359,296 False ______________________________________________________________________ BatchNorm2d [512, 11, 11] 1,024 True ______________________________________________________________________ Conv2d [512, 11, 11] 131,072 False ______________________________________________________________________ BatchNorm2d [512, 11, 11] 1,024 True ______________________________________________________________________ Conv2d [512, 11, 11] 2,359,296 False ______________________________________________________________________ BatchNorm2d [512, 11, 11] 1,024 True ______________________________________________________________________ ReLU [512, 11, 11] 0 False ______________________________________________________________________ Conv2d [512, 11, 11] 2,359,296 False ______________________________________________________________________ BatchNorm2d [512, 11, 11] 1,024 True ______________________________________________________________________ Conv2d [512, 11, 11] 2,359,296 False ______________________________________________________________________ BatchNorm2d [512, 11, 11] 1,024 True ______________________________________________________________________ ReLU [512, 11, 11] 0 False ______________________________________________________________________ Conv2d [512, 11, 11] 2,359,296 False ______________________________________________________________________ BatchNorm2d [512, 11, 11] 1,024 True ______________________________________________________________________ AdaptiveAvgPool2d [512, 1, 1] 0 False ______________________________________________________________________ AdaptiveMaxPool2d [512, 1, 1] 0 False ______________________________________________________________________ Flatten [1024] 0 False ______________________________________________________________________ BatchNorm1d [1024] 2,048 True ______________________________________________________________________ Dropout [1024] 0 False ______________________________________________________________________ Linear [512] 524,800 True ______________________________________________________________________ ReLU [512] 0 False ______________________________________________________________________ BatchNorm1d [512] 1,024 True ______________________________________________________________________ Dropout [512] 0 False ______________________________________________________________________ Linear [37] 18,981 True ______________________________________________________________________ BatchNorm1d [37] 74 True ______________________________________________________________________ Total params: 21,831,599 Total trainable params: 563,951 Total non-trainable params: 21,267,648
Heatmap 热力图¶
In [ ]:
m = learn.model.eval();
In [ ]:
xb,_ = data.one_item(x)
xb_im = Image(data.denorm(xb)[0])
xb = xb.cuda()
In [ ]:
from fastai.callbacks.hooks import *
In [ ]:
def hooked_backward(cat=y):
with hook_output(m[0]) as hook_a:
with hook_output(m[0], grad=True) as hook_g:
preds = m(xb)
preds[0,int(cat)].backward()
return hook_a,hook_g
In [ ]:
hook_a,hook_g = hooked_backward()
In [ ]:
acts = hook_a.stored[0].cpu()
acts.shape
Out[ ]:
torch.Size([512, 11, 11])
In [ ]:
avg_acts = acts.mean(0)
avg_acts.shape
Out[ ]:
torch.Size([11, 11])
In [ ]:
def show_heatmap(hm):
_,ax = plt.subplots()
xb_im.show(ax)
ax.imshow(hm, alpha=0.6, extent=(0,352,352,0),
interpolation='bilinear', cmap='magma');
In [ ]:
show_heatmap(avg_acts)
Grad-CAM¶
In [ ]:
grad = hook_g.stored[0][0].cpu()
grad_chan = grad.mean(1).mean(1)
grad.shape,grad_chan.shape
Out[ ]:
(torch.Size([512, 11, 11]), torch.Size([512]))
In [ ]:
mult = (acts*grad_chan[...,None,None]).mean(0)
In [ ]:
show_heatmap(mult)
In [ ]:
fn = path/'../other/bulldog_maine.jpg' #Replace with your own image
In [ ]:
x = open_image(fn); x
Out[ ]:
In [ ]:
xb,_ = data.one_item(x)
xb_im = Image(data.denorm(xb)[0])
xb = xb.cuda()
In [ ]:
hook_a,hook_g = hooked_backward()
In [ ]:
acts = hook_a.stored[0].cpu()
grad = hook_g.stored[0][0].cpu()
grad_chan = grad.mean(1).mean(1)
mult = (acts*grad_chan[...,None,None]).mean(0)
In [ ]:
show_heatmap(mult)
In [ ]:
data.classes[0]
Out[ ]:
'Abyssinian'
In [ ]:
hook_a,hook_g = hooked_backward(0)
In [ ]:
acts = hook_a.stored[0].cpu()
grad = hook_g.stored[0][0].cpu()
grad_chan = grad.mean(1).mean(1)
mult = (acts*grad_chan[...,None,None]).mean(0)
In [ ]:
show_heatmap(mult)
