Comments (5)
An external user here that has run into the same.
MSR-VTT 1K-A (from JSFusion work) doesn't have a "val" split, so people kind of use the names "test" and "val" interchangeably for it.
from frozen-in-time.
@bryant1410 Did you evaluate the pretrained model on MSR-VTT 1K-A test set? Both the zero-shot and the finetuned results are higher than that reported in Table 5 of the paper.
from frozen-in-time.
I think I haven't run the fine-tuned one with the provided model. For zero-shot one, I get pretty similar results with a different code (I get slightly smaller). Differences in MSR-VTT can be related to the fact that there are repeated labels (so there are ties).
from frozen-in-time.
(but not sure how much the repeated-labels thing affects)
from frozen-in-time.
Hi, yes unfortunately MSR-VTT 1k-A does not have a test split (many of the downstream retrieval datasets), so val and test are one and the same as @bryant1410 says. The line in the paper ought to be: "we train on 9k train videos, and val/test on 1k"
Regarding the resulting numbers being slightly higher: I retrained the pre-trained models after submission when rewriting the code, and performance increased a bit -- hence the higher ZS results.
For finetuning, the current code picks the best performing checkpoint from val == test, which preforms better than if you train and evaluate and a pre-decided fixed number of epochs (as described in the paper). Doing the latter will give results closer to those written in the paper.
from frozen-in-time.
Related Issues (20)
- CC3M data error HOT 3
- Which results in paper correspond to the finetune command? HOT 5
- About Curriculum Learning HOT 3
- What does zero-pad means? HOT 1
- License ? HOT 2
- Curriculum Learning and Video-Image Joint Training HOT 4
- How about initializing parameters with CLIP model HOT 1
- Creating 256 emb vector from text during inferenece HOT 2
- evaluation for MSVD . HOT 1
- How to select checkpoint when fine-tuning on MSRVTT HOT 1
- config about Paper Result HOT 2
- Code/template for the demo? HOT 4
- CC3M dataset broken HOT 1
- Result about MSVD HOT 2
- About the effects of sliding_window_stride
- pre-process mp4 HOT 1
- Question about pretrained models? HOT 1
- Could you please also share the demo UI codes? HOT 2
- RuntimeError: There were no tensor arguments to this function (e.g., you passed an empty list of Tensors), but no fallback function is registered for schema aten::_cat. HOT 1
- Cannot reproduce results
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from frozen-in-time.