Comments (4)
A simple solution to this to re-run the experiment ( only appears during training )
from stale.
Solution : Putting .float() after CLIP model initialization. This error is due to mixed precision training
from stale.
The Nan bug is due to the with autograd.detect_anomaly(): function
from stale.
I downloaded the code and dataset, and modified only anet.yaml
, but I still have this problem, can you help me?
My environment and configuration:
torch 1.10.1
torchfile 0.1.0
torchnet 0.0.4
torchvision 0.11.2
dataset:
num_classes: 200
split: 75
training:
video_info_path: "./data/activitynet_annotations/video_info_new.csv"
video_anno_path: "./data/activitynet_annotations/anet_anno_action.json"
num_frame: 5
output_path: './path/to/train/'
testing:
video_info_path: "./data/activitynet_annotations/video_info_new.csv"
video_anno_path: "./data/activitynet_annotations/anet_anno_action.json"
num_frame: 5
output_path: './path/to/test/'
model:
embedding_head: 4
# feat_dim: 2048
feat_dim: 512
temporal_scale: 100
clip_pretrain: "O" ## K : KInetics , O : openAI
training:
batch_size: 100
learning_rate: 0.00004
weight_decay: 0.02
max_epoch: 5
checkpoint_path: './path/to/output/'
random_seed: 1
step: 10
gamma: 0.3
feature_path: "/disk/sdd/liuyang/ANet_CLIP"
num_gpu: 1
loss:
lambda_1: 0.6
lambda_2: 0.4
fewshot:
shot: 0 ## > 0 is few-shot ; = 0 is zero-shot
mode: 1 # 1 : base-training 2 : meta-training 3 : meta-testing 4 : no meta-training/ vanilla few-shot
trimmed: 0 # 0 : untrimmed 1 : trimmed
episode: 1000
num_base: 180
num_test: 20
ismulti : 1 # 0 : single-instance 1 : multi-instance
num_way : 4
meta_class : 1 # # 1: meta-learn classifier 0: vanilla few-shot w/o meta-learning
meta_mask : 0 # # 1: meta-learn mask 0: vanilla few-shot w/o meta-learning
trim_support : 1
num_context : 20
testing:
cls_thresh: 0.01
mask_thresh: [0,0.2,0.4,0.6,0.8]
class_thresh: [0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]
top_k_snip: 10
top_k: 500
nms_thresh: 0.6
pretraining:
video_transformer: "./path/to/ckpt"
isPretrain : 0 # 0 : Finetune , 1 : Pretrain
video_path: "/disk/sdd/liuyang/ANet_CLIP222"
raw_video: "/path/to/raw/video"
clip_length: 768
clip_stride: 8
emb_dim: 512
demo:
generated_feat_dir: "./path/to/feature"
from stale.
Related Issues (20)
- stale_best_score HOT 14
- How to extract the video features with CLIP visual encoder? HOT 3
- Better not use pytorch 1.8 + cuda 10.2
- The support for THUMOS14 dataset. HOT 2
- RuntimeError: Function 'DivBackward0' returned nan values in its 0th output. HOT 4
- Focal loss with internal softmax HOT 1
- Data splits (zero shot) HOT 1
- The annotation of Thumos14 HOT 1
- Clarifying Details to Reproduce on THUMOS14 HOT 10
- Why use only the last segment of the video HOT 4
- Checkpoint link is corrupted HOT 2
- Why can Zero Shot be achieved?
- About the B-II model
- Questions about the implementation of the IOU
- feature_frame in THUMOS14
- Unet score for Thumos HOT 1
- Could you publish your supplementary material?Thanks!!
- Performance under GT proposals HOT 2
- The Thumos14 clip features
- if action_end - action_start > 1 and gt_label in lbl_dict HOT 1
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 stale.