Skip to main content
Nicolas Gervais's user avatar
Nicolas Gervais's user avatar
Nicolas Gervais's user avatar
Nicolas Gervais
Data Scientist at TD Bank
  • Member for 5 years, 6 months
  • Last seen this week
Profile Activity
Stats
36,012
reputation
10.9m
reached
945
answers
119
questions
Communities
About

Senior Data Scientist located in Montréal, Québec.

Here are my Stack Overflow achievements:

About me: I like doing running competitions. I also have two computer vision patents!

Badges
View all badges
20
gold badges
118
silver badges
157
bronze badges
Top tags
View all tags
2,481
Score
1,033
Posts
97
Posts %
995
Score
160
Posts
15
Posts %
951
Score
538
Posts
51
Posts %
891
Score
454
Posts
43
Posts %
876
Score
125
Posts
12
Posts %
725
Score
71
Posts
7
Posts %
Top posts
View all questions, answers, and articles
310
RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same
Nov 23, 2019
97
RuntimeError: expected scalar type Long but found Float
Feb 27, 2020
85
Fixed digits after decimal with f-strings
Jan 4, 2020
69
Random Choice with Pytorch?
Dec 23, 2019
60
How to fix "ResourceExhaustedError: OOM when allocating tensor"
Dec 18, 2019
50
Upgrade to python 3.8 using conda
Dec 15, 2019
48
TypeError: cannot unpack non-iterable NoneType object
May 24, 2020
40
Random Choice with Pytorch?
Dec 23, 2019
35
"RuntimeError: Expected 4-dimensional input for 4-dimensional weight 32 3 3, but got 3-dimensional input of size [3, 224, 224] instead"?
Jan 2, 2020
34
How do you invert a tensor of boolean values in Pytorch?
Dec 3, 2019
Top Meta posts
2
1
64
What is the appropriate course of action towards a user that is consistently answering off-topic, low quality, and duplicate questions?
29
How should we handle machine learning questions asking for performance improvements?
20
How should we handle answers that don't answer the question, but evaluate the performance of other answers?
Top network posts
View all network posts
5
Can I completely cancel the effects of using a smaller batch size by reducing the learning rate?