Comments (2)
Thanks for letting me know. Indeed, Colab notebook stopped working. It sometimes happens since Google Colab changes its environment frequently.
I did the following changes:
- updated the conda version that colab installs
!wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -q --show-progress
!bash ./Miniconda3-latest-Linux-x86_64.sh -b -f -p /usr/local
- fixed the locale information by adding
import locale
locale.getpreferredencoding = lambda: "UTF-8"
- Removed the build information from env files:
=p3.7_cuda10.0.130...
frompytorch=1.2.0
rows in./submodules/video_features/conda_env_i3d.yml
,./submodules/video_features/conda_env_vggish.yml
, and./conda_env.yml
However, when I try to extract VGGish features, it fails with AttributeError: module 'torch._C' has no attribute '_broadcast_coalesced'
.
Here is the updated notebook:
colab_demo_BMT.ipynb.zip
I don't have time atm to explore it further. Please let me know if you could fix it.
from bmt.
This and the follow-up colab errors are fixed in #58
from bmt.
Related Issues (20)
- RuntimeError: Vector for token b'27ll' has 38 dimensions, but previously read vectors have 300 dimensions HOT 8
- Caption my custom video with no audio information HOT 2
- Error while extracting vggish features HOT 2
- Can BMT generate the caption for the customized video? HOT 1
- Question: Why is duration_in_secs 35.155 ? HOT 1
- ERROR: .zip file with i3d features is corrupted HOT 1
- Final performance HOT 1
- Error(s) in loading state_dict for DataParallel HOT 4
- RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)` HOT 3
- Error while extracting i3d features HOT 1
- How to train the captioning module on ground truth proposals HOT 3
- video files HOT 1
- About evaluation HOT 2
- OSError: [Errno 30] Read-only file system: './captioning_results_learned_props_e26.json' HOT 3
- Final results HOT 1
- How to evaluate proposal generation module for specific epoch
- Fine tuning and end-to-end inference on a video.
- RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)` HOT 1
- Unexpected "UNK" captions with single video prediction HOT 10
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 bmt.