15個重要Python面試題 測測你適不適合做Python？
torch.squeeze()
Returns a tensor with all the dimensions of input of size 1 removed.
-
torch.unsqueeze(input, dim, out=None) → Tensor - Returns a new tensor with a dimension of size one inserted at the specified position.
Python 3:filter()
filter() 函數用於過濾序列，過濾掉不符合條件的元素，返回一個迭代器對象，如果要轉換為列表，可以使用 list() 來轉換。
該接收兩個參數，第一個為函數，第二個為序列，序列的每個元素作為參數傳遞給函數進行判，然后返回 True 或 False，最后將返回 True 的元素放到新列表中。
Gensim
Gensim是一款開源的第三方Python工具包，用於從原始的非結構化的文本中，無監督地學習到文本隱層的主題向量表達。它支持包括TF-IDF，LSA，LDA，和word2vec在內的多種主題模型算法，支持流式訓練，並提供了諸如相似度計算，信息檢索等一些常用任務的API接口。簡單地說，Gensim主要處理文本數據，對文本數據進行建模挖掘。
https://blog.csdn.net/HuangZhang_123/article/details/80326363
traceback
捕獲並打印異常,可以輸出哪個文件哪個函數哪一行報的錯。
@classmethod,@staticmethod,@property
torch.max()
__call__
在類中實現該方法,一個類實例可以變成一個可調用對象。
代碼出處：https://www.cnblogs.com/superxuezhazha/p/5793536.html
更多特殊函數: https://www.cnblogs.com/xiao987334176/p/8884002.html#autoid-0-1-0
IoU(Intersection over Union)的計算
def IOU(xywh1, xywh2):
x1, y1, w1, h1 = xywh1
x2, y2, w2, h2 = xywh2
dx = min(x1+w1, x2+w2) - max(x1, x2)
dy = min(y1+h1, y2+h2) - max(y1, y2)
intersection = dx * dy if (dx >=0 and dy >= 0) else 0.
union = w1 * h1 + w2 * h2 - intersection
return (intersection / union)
其中(x1,y1),(x2,y2)分別為兩個矩陣左下角的頂點，w,h為寬和高。
xml解析
https://www.cnblogs.com/zqchen/articles/3936805.html
layer of model
model.children() returns an iterable of high-level layers present in model.
model.named_children() returns an iterable of two-element tuples, where the first element is the name of the high-level layer and the second element is the high-level layer.
inception loss
if is_inception and phase == 'train':
# From https://discuss.pytorch.org/t/how-to-optimize-inception-model-with-auxiliary-classifiers/7958
outputs, aux_outputs = model(inputs)
loss1 = criterion(outputs, labels)
loss2 = criterion(aux_outputs, labels)
loss = loss1 + 0.4*loss2
inception_v3 requires the input size to be (299,299), whereas all of the other models expect (224,224).
詳解Pytorch中的網絡構造(nn.Module)
https://zhuanlan.zhihu.com/p/53927068
affine_grad和grid_sample
https://www.jianshu.com/p/723af68beb2e
torch.gather
torch.cat
.view() : reshape a tensor.
By default, user created Tensors have 'requires_grad = False'
.requires_grad_() 和 .detach()
torch.nn.ReplicationPad2d(padding)
Pads the input tensor using replication of the input boundary.
torch.tensor(np_array):
.numpy()：Converting a Torch Tensor to a NumPy Array
.from_numpy: Converting NumPy Array to Torch Tensor
tensor_b is a different view (interpretation) of the same data present in the underlying storage
torch.stack: 增加新的維度做堆疊
torch.masked_select ：在訓練階段，損失函數通常需要進行mask操作，因為一個batch中句子的長度通常是不一樣的，一個batch中不足長度的位置需要進行填充（pad）補0，最后生成句子計算loss時需要忽略那些原本是pad的位置的值，即只保留mask中值為1位置的值，忽略值為0位置的值
Python標准庫(3.x): itertools庫
https://www.cnblogs.com/tp1226/p/8453564.html
Python標准庫(3.x): 內建函數
https://www.cnblogs.com/tp1226/p/8446503.html
torch.einsum:
https://www.jqr.com/article/000481
Scikit-Learn中TF-IDF權重計算方法主要用到兩個類：CountVectorizer和TfidfTransformer
select first/last N
select by specific index
index_select
…
select by mask 會把數據打平
select by flatten index
Tensor維度變換
view/reshape: 丟失維度信息
squeeze
unsqueeze：插入的index的取值范圍[-a.dim()-1, a.dim()+1)
transpose / .t() (only for 2D)
permute
expand: broadcasting (推薦)
repeat: memory copied
Broadcast
Expand
without copying data
match from last dim
Merge or Split
cat: concate的維度可以不一樣，其它維度必須一樣.
stack: create new dim at the dim value
所有的維度必須一樣(e.g. a和b).
split: by length
chunk: by num
*: element-wise
matmul：matrix 乘法， torch.mm(only for 2D)、torch.matmul、@
>2d tensor matmul
.floor() .ceil()
.round(): 四舍五入
.trunc() .frac()
clamp: gradient clipping, (min), (min, max)
statistics
norm: 范數用來衡量一個向量的大小
mean sum
prod
max, min,
argmin, argmax: 返回的是索引
dim, keepdim
kthvalue(返回第k小), topk
compare
torch.eq
torch.gt
Tensor advanced operation
where (condition, a, b)
gather
Image Preprocessing:
Image Resize
Data Augumentation
Normalize
ToTensor
Numpy中數組索引為None
https://www.kaggle.com/gyani95/380000-lyrics-from-
metrolyrics