Comments (5)
In DSOD_train.ipynb
, batch size is actually 6 and the gradients get accumulated with AdamAccumulate
for 128//6 batches before a gradient update is performed. This results in a virtual batch size of 126, but the log is updateted after each batch.
Setting the batch size to 4 or even 2 should solve the issue. How large is your GPU memory?
from ssd_detectors.
Thank you so much for your kind help!
I changed the 512's batch size to 4 and the train code is running!
I'm using two Titan Xp GPU and the memory spec is as follows:
11.4 GbpsMemory Speed
12 GB GDDR5XStandard Memory Config
384-bitMemory Interface Width
547.7 GB/sMemory Bandwidth (GB/sec)
currently the execution is using only 1 GPU..don't know why
I have one more question!
In your data_coco.py, there is convert_to_voc function.
I'm only using COCO dataset, so in DSOD_trian, I commented out codes related to VOC dataset and did
gt_util_train = gt_util_coco.convert_to_voc()
gt_util_val = gt_util_coco_val.convert_to_voc()
Does this code make DSOD_Train to train on only 21 categories? I figured you only have 21 initial weights.
from ssd_detectors.
I've always used 1 GPU for training a model, but it should work with multiple GPUs as well. The documentation of Model.fit_generator()
explains how to do this.
convert_to_voc
in the COCO case returns a new GTUtility
with COCO data, but with the 20 (21 including background) VOC classes leading to a model with 21 categories.
The weights you mentioned are not trainable parameters... See #14 for more details.
from ssd_detectors.
Thank you for the reply!
I played some parameters in fit_generator() (use_multiprocessing=True
, workers=2
) but still only one gpu was on.
I also tried using multi_gpu_model
from keras.utils, but failed with _TfDeviceCaptureOp does not have method _set_device_from_string.
I found that the class _TfDeviceCaptureOp in tensorflow/python/keras/backend.py does have _set_device_from_string, but in keras/backend/tensorflow_backend.py does not have that method..
If anyone solved this issue, please share your knowledge
Thank you!
from ssd_detectors.
Search for keras.utils.multi_gpu_model
, use_multiprocessing=True, workers=2
refers to data loading.
from ssd_detectors.
Related Issues (20)
- TBPP model arbitrary input shape HOT 1
- encode/decode error for tbpp
- DSOD Low mAP HOT 1
- Target length zero error
- about environment set (tf version?) HOT 2
- SL_end2end_predict.ipynb: Model dimensions don't match that in weights file. HOT 4
- Request to add .pkl files to repo HOT 4
- DSODSL Output tensor format HOT 1
- CRNN output format HOT 1
- How to convert to tflite?
- SL_end2end_predict.ipynb fails on converting to .py with necessary modifications. HOT 9
- Light architectures for object detection HOT 5
- fit_generator for ssd training & Check loss during training HOT 1
- training with own dataset resize issue HOT 1
- While training, got <UnknownError: AttributeError: 'NoneType' object has no attribute 'shape'> HOT 1
- links to download models not working HOT 2
- TypeError: map() got an unexpected keyword argument 'deterministic' error HOT 3
- How to modify the size of anchor? HOT 4
- Metrics issue ? HOT 4
- Problem during with Crowd Human dataset 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 ssd_detectors.