import torch
import torch.nn as nn
from common_tools import set_seed
set_seed(1) # 设置随机种子
# %% Module.register_forward_hook and pre hook
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 2, 3)
self.pool1 = nn.MaxPool2d(2, 2)
def forward(self, x):
x = self.conv1(x)
x = self.pool1(x)
return x
def forward_hook(module, data_input, data_output):
fmap_block.append(data_output)
input_block.append(data_input)
def forward_pre_hook(module, data_input):
print("forward_pre_hook input:{}".format(data_input))
assert os.path.exists(path_lenet), "{}不存在，请将lenet.py文件放到 {}".format(
path_lenet, os.path.dirname(path_lenet))
assert os.path.exists(path_tools), "{}不存在，请将common_tools.py文件放到 {}".format(
path_tools, os.path.dirname(path_tools))
import sys
hello_pytorch_DIR = os.path.abspath(
os.path.dirname(__file__) + os.path.sep + ".." + os.path.sep + "..")
sys.path.append(hello_pytorch_DIR)
from lenet import LeNet
from my_dataset import RMBDataset
# from my_dataset import DogOrCatDataset
from common_tools import set_seed
set_seed() # 设置随机种子
rmb_label = {"1": 0, "100": 1}
# 参数设置
MAX_EPOCH = 10
BATCH_SIZE = 16
LR = 0.01
log_interval = 10
val_interval = 1
# ============================ step 1/5 数据 ============================
split_dir = os.path.abspath(os.path.join(BASE_DIR, "data", "rmb_split"))
if not os.path.exists(split_dir):
raise Exception(
r"数据 {} 不存在, 回到lesson-06\1_split_dataset.py生成数据".format(split_dir))
train_dir = os.path.join(split_dir, "train")
import torch
from common_tools import set_seed
set_seed(1)
# %% tensor hook 1
def grad_hook(grad):
a_grad.append(grad)
w = torch.tensor([1.], requires_grad=True)
x = torch.tensor([2.], requires_grad=True)
a = torch.add(w, x)
b = torch.add(w, 1)
y = torch.mul(a, b)
a_grad = list()
handle = a.register_hook(grad_hook)
y.backward()
# 查看梯度
print("gradient:", w.grad, x.grad, a.grad, b.grad, y.grad)
print("a_grad[0]: ", a_grad[0])
handle.remove()
# %% tensor hook 2
# -*- coding: utf-8 -*-
import os
import torch.nn as nn
from PIL import Image
from torchvision import transforms
from matplotlib import pyplot as plt
from common_tools import transform_invert, set_seed
set_seed(3) # 设置随机种子
# ================================= load img ==================================
path_img = os.path.join(os.path.dirname(os.path.abspath(__file__)), "imgs",
"lena.png")
print(path_img)
img = Image.open(path_img).convert('RGB') # 0~255
# convert to tensor
img_transform = transforms.Compose([transforms.ToTensor()])
img_tensor = img_transform(img)
# 添加 batch 维度
img_tensor.unsqueeze_(dim=0) # C*H*W to B*C*H*W
# ================================= create convolution layer ==================================
# ================ 2d
# flag = 1
flag = 0
if flag:
conv_layer = nn.Conv2d(3, 1, 3) # input:(i, o, size) weights:(o, i , h, w)
# 初始化卷积层权值