测试中间层输出
import torch
import numpy as np
from PIL import Image
from torchvision import transforms, models
import matplotlib.cm
from torchinfo import summary
import copy
import cv2
import matplotlib.pyplot as plt
device = 'cuda' if torch.cuda.is_available() else 'cpu'
module_name = []
p_in = []
p_out = []
# 定义hook_fn，顾名思义就是把数值从forward计算过程中“勾出”来
def hook_fn(module, inputs, outputs):
module_name.append(module.__class__)
print(module)
p_in.append(inputs)
p_out.append(outputs)
# 加载模型，注册钩子函数
model = models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
model.rpn.head.cls_logits.register_forward_hook(hook_fn) # faster_rcnn
## Retinanet
# model = models.detection.retinanet_resnet50_fpn(pretrained=True)
# model.head.classification_head.cls_logits.register_forward_hook(hook_fn)
## SSD300 VGG16
# model = models.detection.ssd300_vgg16(pretrained=True)
# model.head.classification_head.register_forward_hook(hook_fn)
# print(summary(model, (1,3,300,300), verbose=1))
# 导入一张图像
img_file = "elephant_1280p.jpg"
img = Image.open(img_file)
ori_img = img.copy()
# 前处理
transform = transforms.Compose([
# transforms.Resize((416,416)),
transforms.ToTensor(),
transforms.Normalize(
[0.485, 0.456, 0.406],
[0.229, 0.224, 0.225]
)
])
img = transform(img).unsqueeze(0) # 增加batch维度
model.to(device)
img = img.to(device) # torch.Size([1, 3, 720, 1280])
# EVAL模式
model.eval()
with torch.no_grad():
model(img)
# 特征可视化
def show_feature_map(img_src, conv_features):
'''可视化卷积层特征图输出
img_src:源图像文件路径
conv_feature:得到的卷积输出,[b, c, h, w]
'''
img = Image.open(img_file).convert('RGB')
height, width = img.size
conv_features = conv_features.cpu()
heat = conv_features.squeeze(0)#降维操作,尺寸变为(C,H,W)
heatmap = torch.mean(heat,dim=0)#对各卷积层(C)求平均值,尺寸变为(H,W)
# heatmap = torch.max(heat,dim=1).values.squeeze()
heatmap = heatmap.numpy()#转换为numpy数组
heatmap = np.maximum(heatmap, 0)
heatmap /= np.max(heatmap)#minmax归一化处理
heatmap = cv2.resize(heatmap,(img.size[0],img.size[1]))#变换heatmap图像尺寸,使之与原图匹配,方便后续可视化
heatmap = np.uint8(255*heatmap)#像素值缩放至(0,255)之间,uint8类型,这也是前面需要做归一化的原因,否则像素值会溢出255(也就是8位颜色通道)
heatmap = cv2.applyColorMap(heatmap,cv2.COLORMAP_HSV)#颜色变换
plt.imshow(heatmap)
plt.show()
# heatmap = np.array(Image.fromarray(heatmap).convert('L'))
superimg = heatmap*0.4+np.array(img)[:,:,::-1] #图像叠加，注意翻转通道，cv用的是bgr
cv2.imwrite('./superimg.jpg',superimg)#保存结果
# 可视化叠加至源图像的结果
img_ = np.array(Image.open('./superimg.jpg').convert('RGB'))
plt.imshow(img_)
plt.show()
model_str = model.__str__()
if model_str.startswith('SSD'):
for k in range(len(module_name)):
for j in range(len(p_in[0][0])):
print(p_in[k][0][j].shape)
print(p_out[k].shape)
show_feature_map(img_file, p_in[k][0][j])
# show_feature_map(img_file, torch.sigmoid(p_out[k]))
print()
if model_str.startswith('RetinaNet'): # retinanet
for k in range(len(module_name)):# 不同尺寸的特征图
print(p_in[k][0].shape)
print(p_out[k].shape)
# show_feature_map(img_file, p_in[k][j])
show_feature_map(img_file, torch.sigmoid(p_out[k]))
print()
if model_str.startswith('FasterRCNN'): # FasterRCNN
for k in range(len(module_name)):
print(p_in[k][0].shape)
print(p_out[k].shape)
# show_feature_map(img_file, p_in[k][0])
show_feature_map(img_file, torch.sigmoid(p_out[k]))
print()
print(summary(model, (1,3,300,300), verbose=1))
测试hook
import torch
import torch.nn as nn
import torch.nn.functional as F
class LeNet(nn.Module):
def __init__(self):
super(LeNet, self).__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16*5*5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
out = F.relu(self.conv1(x)) #1
out = F.max_pool2d(out, 2) #2
out = F.relu(self.conv2(out)) #3
out = F.max_pool2d(out, 2)
out = out.view(out.size(0), -1)
out = F.relu(self.fc1(out))
out = F.relu(self.fc2(out))
out = self.fc3(out)
return out
features = []
def hook(module, input, output):
# module: model.conv2
# input :in forward function [#2]
# output:is [#3 self.conv2(out)]
features.append(output.clone().detach())
# output is saved in a list
net = LeNet() ## 模型实例化
print(net)
x = torch.randn(2, 3, 32, 32) ## input
handle = net.conv2.register_forward_hook(hook) ## 获取整个Lenet模型 conv2的中间结果
y = net(x) ## 获取的是 关于 input x 的 conv2 结果
print(features[0].size()) # 即 [#3 self.conv2(out)]
handle.remove() ## hook删除
"""
import torch
from torch.autograd import Variable
def print_grad(grad):
print('grad is \n',grad)
x = Variable(torch.randn(2, 1), requires_grad=True)
## x = torch.rand(2,1,requires_grad=True) # 等效
print('x value is \n',x)
y = x+3
print('y value is \n',y)
z = torch.mean(torch.pow(y, 1/2))
lr = 1e-3
y.register_hook(print_grad)
z.backward() # 梯度求解
print(x.grad.data)
x.data -= lr*x.grad.data
print('new x is\n',x)
"""
测试net
import torch.nn as nn
class AlexNet(nn.Module):
def __init__(self, num_classes=1000, init_weights=False):
super(AlexNet, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(3, 48, kernel_size=11, stride=4, padding=2), # input[3, 224, 224] output[48, 55, 55]
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2), # output[48, 27, 27]
nn.Conv2d(48, 128, kernel_size=5, padding=2), # output[128, 27, 27]
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2), # output[128, 13, 13]
nn.Conv2d(128, 192, kernel_size=3, padding=1), # output[192, 13, 13]
nn.ReLU(inplace=True),
nn.Conv2d(192, 192, kernel_size=3, padding=1), # output[192, 13, 13]
nn.ReLU(inplace=True),
nn.Conv2d(192, 128, kernel_size=3, padding=1), # output[128, 13, 13]
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2), # output[128, 6, 6]
)
self.classifier = nn.Sequential(
nn.Dropout(p=0.5),
nn.Linear(128 * 6 * 6, 2048),
nn.ReLU(inplace=True),
nn.Dropout(p=0.5),
nn.Linear(2048, 2048),
nn.ReLU(inplace=True),
nn.Linear(2048, num_classes),
)
if init_weights:
self._initialize_weights()
def forward(self, x):
x = self.features(x)
x = self.classifier(x)
return x
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)
if __name__ == '__main__':
model = AlexNet()
print('model children: ')
for module in model.children():
print(module)
print("\n")
print('model modules: ')
for module in model.modules():
print(module)
print("\n")
print('model named children: ')
for name, module in model.named_children():
print('name: {}, module: {}'.format(name, module))
print("\n")
print('model named modules: ')
for name, module in model.named_modules():
print('name: {}, module: {}'.format(name, module))
print("\n")
print('parameters: ')
for parameter in model.parameters():
print('parameter: {}'.format(parameter.shape))
print("\n")
print('model named parameters: ')
for name, parameter in model.named_parameters():
print('name: {}, parameter: {}'.format(name, parameter.shape))
"""
model children:
Sequential(
(0): Conv2d(3, 48, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
(1): ReLU(inplace=True)
(2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(3): Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): ReLU(inplace=True)
(5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(6): Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(7): ReLU(inplace=True)
(8): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(9): ReLU(inplace=True)
(10): Conv2d(192, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
)
Sequential(
(0): Dropout(p=0.5, inplace=False)
(1): Linear(in_features=4608, out_features=2048, bias=True)
(2): ReLU(inplace=True)
(3): Dropout(p=0.5, inplace=False)
(4): Linear(in_features=2048, out_features=2048, bias=True)
(5): ReLU(inplace=True)
(6): Linear(in_features=2048, out_features=1000, bias=True)
)
model modules:
AlexNet(
(features): Sequential(
(0): Conv2d(3, 48, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
(1): ReLU(inplace=True)
(2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(3): Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): ReLU(inplace=True)
(5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(6): Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(7): ReLU(inplace=True)
(8): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(9): ReLU(inplace=True)
(10): Conv2d(192, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(classifier): Sequential(
(0): Dropout(p=0.5, inplace=False)
(1): Linear(in_features=4608, out_features=2048, bias=True)
(2): ReLU(inplace=True)
(3): Dropout(p=0.5, inplace=False)
(4): Linear(in_features=2048, out_features=2048, bias=True)
(5): ReLU(inplace=True)
(6): Linear(in_features=2048, out_features=1000, bias=True)
)
)
Sequential(
(0): Conv2d(3, 48, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
(1): ReLU(inplace=True)
(2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(3): Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): ReLU(inplace=True)
(5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(6): Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(7): ReLU(inplace=True)
(8): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(9): ReLU(inplace=True)
(10): Conv2d(192, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
)
Conv2d(3, 48, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
ReLU(inplace=True)
MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
ReLU(inplace=True)
MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace=True)
Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace=True)
Conv2d(192, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace=True)
MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
Sequential(
(0): Dropout(p=0.5, inplace=False)
(1): Linear(in_features=4608, out_features=2048, bias=True)
(2): ReLU(inplace=True)
(3): Dropout(p=0.5, inplace=False)
(4): Linear(in_features=2048, out_features=2048, bias=True)
(5): ReLU(inplace=True)
(6): Linear(in_features=2048, out_features=1000, bias=True)
)
Dropout(p=0.5, inplace=False)
Linear(in_features=4608, out_features=2048, bias=True)
ReLU(inplace=True)
Dropout(p=0.5, inplace=False)
Linear(in_features=2048, out_features=2048, bias=True)
ReLU(inplace=True)
Linear(in_features=2048, out_features=1000, bias=True)
model named children:
name: features, module: Sequential(
(0): Conv2d(3, 48, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
(1): ReLU(inplace=True)
(2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(3): Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): ReLU(inplace=True)
(5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(6): Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(7): ReLU(inplace=True)
(8): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(9): ReLU(inplace=True)
(10): Conv2d(192, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
)
name: classifier, module: Sequential(
(0): Dropout(p=0.5, inplace=False)
(1): Linear(in_features=4608, out_features=2048, bias=True)
(2): ReLU(inplace=True)
(3): Dropout(p=0.5, inplace=False)
(4): Linear(in_features=2048, out_features=2048, bias=True)
(5): ReLU(inplace=True)
(6): Linear(in_features=2048, out_features=1000, bias=True)
)
model named modules:
name: , module: AlexNet(
(features): Sequential(
(0): Conv2d(3, 48, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
(1): ReLU(inplace=True)
(2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(3): Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): ReLU(inplace=True)
(5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(6): Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(7): ReLU(inplace=True)
(8): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(9): ReLU(inplace=True)
(10): Conv2d(192, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(classifier): Sequential(
(0): Dropout(p=0.5, inplace=False)
(1): Linear(in_features=4608, out_features=2048, bias=True)
(2): ReLU(inplace=True)
(3): Dropout(p=0.5, inplace=False)
(4): Linear(in_features=2048, out_features=2048, bias=True)
(5): ReLU(inplace=True)
(6): Linear(in_features=2048, out_features=1000, bias=True)
)
)
name: features, module: Sequential(
(0): Conv2d(3, 48, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
(1): ReLU(inplace=True)
(2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(3): Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): ReLU(inplace=True)
(5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(6): Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(7): ReLU(inplace=True)
(8): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(9): ReLU(inplace=True)
(10): Conv2d(192, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
)
name: features.0, module: Conv2d(3, 48, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
name: features.1, module: ReLU(inplace=True)
name: features.2, module: MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
name: features.3, module: Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
name: features.4, module: ReLU(inplace=True)
name: features.5, module: MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
name: features.6, module: Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
name: features.7, module: ReLU(inplace=True)
name: features.8, module: Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
name: features.9, module: ReLU(inplace=True)
name: features.10, module: Conv2d(192, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
name: features.11, module: ReLU(inplace=True)
name: features.12, module: MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
name: classifier, module: Sequential(
(0): Dropout(p=0.5, inplace=False)
(1): Linear(in_features=4608, out_features=2048, bias=True)
(2): ReLU(inplace=True)
(3): Dropout(p=0.5, inplace=False)
(4): Linear(in_features=2048, out_features=2048, bias=True)
(5): ReLU(inplace=True)
(6): Linear(in_features=2048, out_features=1000, bias=True)
)
name: classifier.0, module: Dropout(p=0.5, inplace=False)
name: classifier.1, module: Linear(in_features=4608, out_features=2048, bias=True)
name: classifier.2, module: ReLU(inplace=True)
name: classifier.3, module: Dropout(p=0.5, inplace=False)
name: classifier.4, module: Linear(in_features=2048, out_features=2048, bias=True)
name: classifier.5, module: ReLU(inplace=True)
name: classifier.6, module: Linear(in_features=2048, out_features=1000, bias=True)
parameters:
parameter: torch.Size([48, 3, 11, 11])
parameter: torch.Size([48])
parameter: torch.Size([128, 48, 5, 5])
parameter: torch.Size([128])
parameter: torch.Size([192, 128, 3, 3])
parameter: torch.Size([192])
parameter: torch.Size([192, 192, 3, 3])
parameter: torch.Size([192])
parameter: torch.Size([128, 192, 3, 3])
parameter: torch.Size([128])
parameter: torch.Size([2048, 4608])
parameter: torch.Size([2048])
parameter: torch.Size([2048, 2048])
parameter: torch.Size([2048])
parameter: torch.Size([1000, 2048])
parameter: torch.Size([1000])
model named parameters:
name: features.0.weight, parameter: torch.Size([48, 3, 11, 11])
name: features.0.bias, parameter: torch.Size([48])
name: features.3.weight, parameter: torch.Size([128, 48, 5, 5])
name: features.3.bias, parameter: torch.Size([128])
name: features.6.weight, parameter: torch.Size([192, 128, 3, 3])
name: features.6.bias, parameter: torch.Size([192])
name: features.8.weight, parameter: torch.Size([192, 192, 3, 3])
name: features.8.bias, parameter: torch.Size([192])
name: features.10.weight, parameter: torch.Size([128, 192, 3, 3])
name: features.10.bias, parameter: torch.Size([128])
name: classifier.1.weight, parameter: torch.Size([2048, 4608])
name: classifier.1.bias, parameter: torch.Size([2048])
name: classifier.4.weight, parameter: torch.Size([2048, 2048])
name: classifier.4.bias, parameter: torch.Size([2048])
name: classifier.6.weight, parameter: torch.Size([1000, 2048])
name: classifier.6.bias, parameter: torch.Size([1000])
"""
