Comments (5)
https://github.com/n1ckfg/deep3d
from deep3d.
I've tried.This url is still wrong...
from deep3d.
No, I mean the file you're looking for is preserved in my fork
from deep3d.
Thank you,I have just downloaded it.
from deep3d.
hello,I open your deep3d.ipython when i load the params:
"""
model = mx.model.FeedForward.load('./deep3d',50,ctx=ctx)
MXNetError Traceback (most recent call last)
in ()
5 print(ctx)
6 #model = mx.model.FeedForward.load('deep3d',50,ctx=ctx)
----> 7 model = mx.model.FeedForward.load('./deep3d',50,ctx=ctx)
/home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/model.pyc in load(prefix, epoch, ctx, **kwargs)
921 - prefix-epoch.params
will be saved for parameters.
922 """
--> 923 symbol, arg_params, aux_params = load_checkpoint(prefix, epoch)
924 return FeedForward(symbol, ctx=ctx,
925 arg_params=arg_params, aux_params=aux_params,
/home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/model.pyc in load_checkpoint(prefix, epoch)
418 - Parameters will be loaded from prefix-epoch.params
.
419 """
--> 420 symbol = sym.load('%s-symbol.json' % prefix)
421 save_dict = nd.load('%s-%04d.params' % (prefix, epoch))
422 arg_params = {}
/home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/symbol/symbol.pyc in load(fname)
2516 raise TypeError('fname need to be string')
2517 handle = SymbolHandle()
-> 2518 check_call(_LIB.MXSymbolCreateFromFile(c_str(fname), ctypes.byref(handle)))
2519 return Symbol(handle)
2520
/home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/base.pyc in check_call(ret)
144 """
145 if ret != 0:
--> 146 raise MXNetError(py_str(_LIB.MXGetLastError()))
147
148
MXNetError: Failed loading Op depth of type DepthDot: [09:30:47] src/core/op.cc:55: Check failed: op != nullptr Operator DepthDot is not registered
Stack trace returned 10 entries:
[bt] (0) /home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x2ab998) [0x7f194f624998]
[bt] (1) /home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x6234ee5) [0x7f19555adee5]
[bt] (2) /home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x6266c3b) [0x7f19555dfc3b]
[bt] (3) /home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x626bf60) [0x7f19555e4f60]
[bt] (4) /home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x626580f) [0x7f19555de80f]
[bt] (5) /home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x262d28f) [0x7f19519a628f]
[bt] (6) /home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x62381dd) [0x7f19555b11dd]
[bt] (7) /home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x262e421) [0x7f19519a7421]
[bt] (8) /home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x262d28f) [0x7f19519a628f]
[bt] (9) /home/quantumliu/anaconda3/envs/mx27/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x62381dd) [0x7f19555b11dd]
"""
It occuers an error,I don't know whether is the param too old to follow the new mxnet api .
Can you help me ? Thank you.
from deep3d.
Related Issues (20)
- check failed: (in_data[softmax_activation::kData].ndim()) == (2) HOT 3
- What is the right working configuration under Ubuntu?
- MXNetError: src/operator/cudnn_batch_norm.cc:20: CuDNNBatchNorm is merged into BatchNorm for cudnn version above v5.Use the later instead.
- Is still available deep3d-0050.params? HOT 8
- runing code meet some problem
- Memory Usage
- How to output the 4-by-3 maps from the depth layers? HOT 4
- is the training model available?
- How to training using KITTI stereo datasets?
- Cann't download deep3d file from https://www.cs.washington.edu/~jxie/ HOT 1
- License
- how the parameter prefix to be given?
- rror in operator depth: [22:17:11] /home/hui/third/deep3d-master/operators/./depth_dot-inl.h:103: Check failed: lshape[1] == param_.scale[1]-param_.scale[0]+1 (33 vs. -4294967263) HOT 3
- Tensorflow Re-Implementation HOT 3
- how to download dataset? HOT 2
- Can This Be Used in Real Time? HOT 8
- mxnet version
- Pretrained model missing
- AttributeError: module 'mxnet.model' has no attribute 'FeedForward'
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 deep3d.