Comments (2)
did you assign floatX flag to be equal to float32
from text2image.
sure
envy@ub1404:/os_pri/github/text2image$ THEANO_FLAGS='floatX=float32' python coco/alignDraw.py coco/models/coco-captions-32x32.json/os_pri/github/text2image$
Using gpu device 0: GeForce GTX 950M (CNMeM is disabled, CuDNN 4007)
coco/alignDraw.py:343: FutureWarning: comparison to None
will result in an elementwise object comparison in the future.
if valData != None:
Traceback (most recent call last):
File "coco/alignDraw.py", line 617, in
rvae = ReccurentAttentionVAE(dimY, dimLangRNN, dimAlign, dimX, dimReadAttent, dimWriteAttent, dimRNNEnc, dimRNNDec, dimZ, runSteps, batch_size, reduceLRAfter, data, data_captions, valData=val_data, valDataCaptions=val_data_captions, pathToWeights=pathToWeights)
File "coco/alignDraw.py", line 355, in init
self._kl_final, self._logpxz, self._log_likelihood, self._c_ts, self._c_ts_gener, self._x, self._y, self._run_steps, self._updates_train, self._updates_gener, self._read_attent_params, self._write_attent_params, self._write_attent_params_gener, self._alphas_gener, self._params, self._mu_prior_t_gener, self._log_sigma_prior_t_gener = build_lang_encoder_and_attention_vae_decoder(self.dimY, self.dimLangRNN, self.dimAlign, self.dimX, self.dimReadAttent, self.dimWriteAttent, self.dimRNNEnc, self.dimRNNDec, self.dimZ, self.runSteps, self.pathToWeights)
File "coco/alignDraw.py", line 294, in build_lang_encoder_and_attention_vae_decoder
sequences=eps, outputs_info=[c0, h0_dec, cell0_dec, h0_enc, cell0_enc, kl_0, mu_prior_0, log_sigma_prior_0, None, None], non_sequences=all_params, n_steps=run_steps)
File "/home/envy/.local/lib/python2.7/site-packages/theano/scan_module/scan.py", line 1041, in scan
scan_outs = local_op(*scan_inputs)
File "/home/envy/.local/lib/python2.7/site-packages/theano/gof/op.py", line 611, in call
node = self.make_node(_inputs, *_kwargs)
File "/home/envy/.local/lib/python2.7/site-packages/theano/scan_module/scan_op.py", line 538, in make_node
inner_sitsot_out.type.dtype))
ValueError: When compiling the inner function of scan the following error has been encountered: The initial state (outputs_info
in scan nomenclature) of variable IncSubtensor{Set;:int64:}.0 (argument number 1) has dtype float32, while the result of the inner function (fn
) has dtype float64. This can happen if the inner function of scan results in an upcast or downcast.
envy@ub1404:
but it works on mnist dataset like:
envy@ub1404:~/os_pri/github/text2image$ python mnist-captions/alignDraw.py mnist-captions/models/mnist-captions.json
Using gpu device 0: GeForce GTX 950M (CNMeM is disabled, CuDNN 4007)
(50000, 784) (50000,) (10000, 784) (10000,)
Banned configurations are :
[5, 1, 2, 8, 0, 3, 3, 10, 9, 0, 0, 4]
Train Dataset
(10000, 3600) (10000, 12) [1176, 1140, 1193, 1317, 1288, 1274, 1331, 1281]
mnist-captions/alignDraw.py:337: FutureWarning: comparison to None
will result in an elementwise object comparison in the future.
if valData != None:
Val Dataset
(10000, 3600) (10000, 12) [1101, 1153, 1229, 1316, 1228, 1332, 1314, 1327]
building gradient function
0:00:12.684201
building train function
0:10:49.556639
Epoch 0 took 0:15:29.012441
Train Results
22.5236268711 1385.53319336 1408.0568158
Validation Results
building validate function
0:00:29.504751
20.0507067261 1111.01946533 1131.07016968
Recreated Train Dataset
[1161, 1189, 1130, 1333, 1282, 1294, 1300, 1311]
Epoch 1 took 0:14:09.783145
Train Results
13.5244888062 748.785505981 762.309996948
Recreated Train Dataset
[1154, 1133, 1218, 1289, 1294, 1264, 1341, 1307]
Epoch 2 took 0:13:24.739994
Train Results
25.99415979 627.837939148 653.832095032
Recreated Train Dataset
[1168, 1218, 1116, 1261, 1332, 1273, 1276, 1356]
from text2image.
Related Issues (20)
- NameError: name 'ArgumentParser' is not defined HOT 1
- KeyError: 'costFunction' HOT 1
- Training Models is taking too long HOT 5
- Unable to generate coco images HOT 1
- How much time does an epoch take for training mnist data?
- float32/float64 issue unresolved HOT 3
- Can‘t find the result of the experiment. HOT 2
- Why HOT 1
- Is the KL divergence computed correctly? HOT 1
- text2image is giving error
- How to generate images with bigger size?
- wanted the pre-trained model
- IOError: Unable to open file (unable to open file: name = '/ais/gobi3/u/nitish/mnist/mnist.h5'
- Chinese image caption, In the result, multiple words of the same type appear
- Unable to load some downloaded files HOT 2
- your .theanorc HOT 1
- Error ! HOT 2
- TypeError HOT 7
- binary_crossentropy 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 text2image.