4b39f92bd8
add implementation of SubNestedSequenceLayer.
8 years ago
82911cecb6
Merge branch 'develop' of https://github.com/PaddlePaddle/paddle into add-ClipLayer
8 years ago
d19355a532
Refine ClipLayer and add unit test for it
8 years ago
f35e08471c
revise the format of __all__ in layers.py
8 years ago
46988517f2
Fix a small bug.
8 years ago
4b1bc6815e
Fix comments of slice_projection, and add unit test of SliceProjection.
8 years ago
dc9f31b32b
Add SliceProjection and slice_projection.
8 years ago
c0ecd5c4c5
add config helper.
8 years ago
23a8d015e0
add ClipLayer
8 years ago
84660653f8
add RowL2NormLayer
8 years ago
8b9e678ddf
fix dropout and clipping setttings in layer helpers.
8 years ago
a59fa46c1f
Merge branch 'add_paramAttr' of https://github.com/NHZlX/Paddle into add_paramAttr
8 years ago
18f4d24d0d
moidify comment of im_conv_group
8 years ago
5f32cc10c2
Update networks.py
...
modify the format
8 years ago
21a3c9d6f4
add the comments for img_conv_groups
8 years ago
fae3632c91
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_paramAttr
8 years ago
a183a80e2e
add param_attr for img_conv_group(...)
8 years ago
6a6e1c7407
Merge pull request #2944 from lcy-seso/fix_recurrent_parse_bug
...
fix recurrent_group parsing bug.
8 years ago
1b6faffeb5
Merge branch 'develop' into fix_recurrent_parse_bug
8 years ago
0f4c733296
add ROIPooling for Fast(er) R-CNN
8 years ago
ec236f4624
fix code format
8 years ago
a6c53fc2fc
fix python wrapper bugs
8 years ago
2e58f2c4c9
Merge branch 'crop_layer' of https://github.com/wanghaoshuang/Paddle into crop_layer
8 years ago
60a788933b
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_layer
8 years ago
d83bae85da
Merge branch 'develop' into crop_layer
8 years ago
3e7819c276
1. Reading image shape from input data instead of image_config
...
2. Add crop layer unitest
3. Fix bugs
8 years ago
e8ee07f31f
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pixel_softmax_layer
8 years ago
1cdf149b6f
1. delete PixelSoftmaxLayer and add SwitchOrderLayer
...
2. Make SwitchOrderLayer support for softmax activation
3. Fix bugs
8 years ago
0ed51ce2e4
fix bug of type check of inputs to recurrent_group.
8 years ago
e2fd06c386
refine name of the input parameter.
8 years ago
ac69f7730a
add gated linear unit into config helper.
8 years ago
62da4a1cde
Merge pull request #2802 from reyoung/feature/fix_python_slow
...
Fix slow parsing a recursive depends topology
8 years ago
313e9f551f
Fix slow parsing a recursive depends topology
...
* Fix #2797
* It because trainer_config_helpers' __dfs_travel__ did not record the
node which travelled, and if the topology has a recursive dependency,
there are some nodes will be travelled multiple times.
* Add a `travelled` set to record which node is travelled.
* Also add a unittest for this situation.
8 years ago
475dd708b9
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pixel_softmax_layer
8 years ago
0152d97e63
fix pixel softmax python wrapper bug
8 years ago
de5ded6bbd
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_layer
8 years ago
8c615e8ff4
Merge pull request #2783 from lcy-seso/update_wmt14_model_md5
...
update the md5sum of WMT14 trained model.
8 years ago
68ec558c21
update the md5sum of WMT14 trained model.
8 years ago
3aa679814f
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pixel_softmax_layer
8 years ago
29f25fbe03
Add pixel softmax layer for FCN model
...
1. Add switch function for switching image dimensions order
2. Add CpuMatrix::backwardSoftmax function
3. Add pixel softmax layer, python wrapper and grad_test
8 years ago
cbc6221748
Update comments of maxout_layer
8 years ago
d378e0a0cd
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_layer
8 years ago
7f380c1be3
Merge pull request #2701 from luotao1/stride
...
stride pooling for max and average layer
8 years ago
e7b071f33a
update annotation with comments
8 years ago
5e6e1f636a
Add grad test and python wrapper for crop layer
8 years ago
312ce8b419
Merge pull request #2497 from pkuyym/ssd_outloss
...
Add DetectionOutputLayer and MultiBoxLossLayer.
8 years ago
86543f7f6a
Follow comments.
8 years ago
0e61730039
stride pooling for max and average layer
8 years ago
0c70f34c60
Fix bug for flowers dataset and row_conv.
8 years ago
3a0919bab3
Add test for configuration and add doc.
8 years ago
5c68aacad1
follow comments.
8 years ago
b0ad9c9074
enable intializing memory state for lstmemory_group.
8 years ago
b5ab4b69bc
Follow comments, mainly use std::copy to simplify logic.
8 years ago
b34a05d114
Fix travis-ci in new image
...
Fix issue #2562
8 years ago
1d6b859549
modity topo
8 years ago
561c4562cf
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
fdde4eff0d
modify some topo
8 years ago
08d0b1d9ac
Merge pull request #2576 from pengli09/cls_cost_coeff
...
add coeff parameter to classification_cost
8 years ago
f551c271af
Merge pull request #2467 from pkuyym/ssd_map
...
Add DetectionMAPEvaluator
8 years ago
7cf640b58d
add coeff parameter to classification_cost
8 years ago
1eab8cce32
modify the annotations of HookAttribute, Variable declaration
8 years ago
15bf6e05b5
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
61222578b4
Allow printer layer to print user provided message
...
For example:
layer.printer(input=[x, y], format="x=%s y=%s")
8 years ago
8266546eb2
Merge pull request #2480 from emailweixu/repeat_layer
...
Repeat layer for column vector
8 years ago
f48535102b
Add the test_repeat_layer.py
8 years ago
5f924d5d53
Follow comments.
8 years ago
65969dad64
Add DetectionOutputLayer and MultiBoxLossLayer.
8 years ago
226f810352
Add activiation for repeat_layer
...
Also remove active_type argument for many layers in config_parser.py because it is automatically
handled by LayerBase.
8 years ago
ef61288f9e
Clean-up recurrent group related python code
...
No longer need to specify target_inlinks or is_seq.
8 years ago
fc9e3e4bda
explain the sparsity ratio
8 years ago
fc0ad9048a
Repeat layer for column vector
8 years ago
17994e38aa
RecurrentGroup with mixed input sequence types
...
No longer need to use SubsequenceInput. The framework will detect.
8 years ago
2207659250
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into ssd_map
8 years ago
6248e566f9
merge from remote
8 years ago
dd2cbb63bf
Parameter initializer in V2 API
...
User can provide an initializer in ParamAttr. The initializer will be called when at parameters.create().
8 years ago
23b1a27483
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
997cef2e63
tiny modify
8 years ago
597a58c3ef
Add DetectionMAPEvaluator.
8 years ago
97a2fde995
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
6bc9277503
Merge branch 'develop' into row_conv
8 years ago
892b1f9ff6
Merge branch 'develop' into fix_config_parsing_bug
8 years ago
f18d83f3c4
follow comments
8 years ago
37015fadbd
update code
8 years ago
a3123e210c
Merge pull request #2412 from lcy-seso/add_config_helper_for_prelu
...
add configuration helper for prelu layer.
8 years ago
996614814d
follow comments and refine doc.
8 years ago
50764480c1
follow comments.
8 years ago
c7483bf956
add configuration helper for prelu layer.
8 years ago
5bab98a3c5
remove top_k argument in classification_cost
8 years ago
692d251869
add missing configuration functions in v2 API.
8 years ago
15668482e3
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
a5dfc556d4
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into row_conv
8 years ago
2c7d8e7b9f
Merge pull request #2369 from emailweixu/print_layer
...
Correctly handle print_layer in V2 API
8 years ago
1a1c589f31
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
092828fbe3
modify the doc of the interface
8 years ago
4537b7bc8c
Merge pull request #2376 from Xreki/warpctc_note
...
Add doc to the usage of warp-ctc.
8 years ago
31e333a212
Add doc to the usage of warp-ctc.
8 years ago
18cd1f2558
Fix bug and Python API.
8 years ago
252c84dbe1
Correctly handle print_layer in V2 API
...
print_layer is used to print the values of a layer when evaluating the model for debugging purpose. No layer depends on print_layer. It should be added to the topology if it is used to print some layer already in the topology.
8 years ago
bfe8ecfc31
Fix blanks.
8 years ago
18435f2a73
modify the pruning from reading mask to specify sparsity_ratio
8 years ago
ca55a24eb3
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
5413af8d11
imporve pruning module
8 years ago
68c68ec958
Merge pull request #2218 from luotao1/rename
...
rename AggregateLevel and ExpandLevel
8 years ago
a8d44cc56a
Fix size for lstm, identity_projection and concat
8 years ago
0ef86cbd2e
Merge pull request #2288 from emailweixu/fix_v2_api
...
Fix V2 API
8 years ago
efd2d3351c
add multiplex layer for python API
8 years ago
9e774a1cdf
remove duplicate code of python/paddle/trainer_config_helpers/config_parser.py
8 years ago
97c4d23fab
Add docs and clean up unused code
8 years ago
7d0355cdd0
Fix V2 API
8 years ago
630b27ec10
Compatible with previous configurations
8 years ago
b7e2adbd47
Merge branch 'develop' into rename
8 years ago
35bfb1d5c3
Allow setting both is_static and initial_mean, initial_std at the same time.
...
Some time we simply want to have a fixed initialization for a model.
8 years ago
28e9807247
Merge branch 'develop' into rename
8 years ago
2e4c0bd2ea
enable global gradient_clipping_threshold
...
correct a typo
optimize code
fix a bug
8 years ago
3ae7541ad3
rename AggregateLevel and ExpandLevel
8 years ago
ba333e8a02
Merge pull request #2219 from emailweixu/sqrt-reciprocal
...
Add Sqrt and Reciprocal activation
8 years ago
a0a3a68551
Add Sqrt and Reciprocal activation
8 years ago
d3e003be04
Merge pull request #2165 from pkuyym/fix-2078
...
Fix 2078
8 years ago
dfc27aaadc
fix document formation bugs.
8 years ago
c7fb78b0a5
follow comments
8 years ago
f8a42d5de9
add doc for AggregateLevel and ExpandLevel
8 years ago
f3eb9cb36a
Override getValueImpl and revise document
8 years ago
a74060d48e
modify usage document of chunk evaluator
8 years ago
87cb840ce9
add coeff parameter to the helpers of mse_cost, crf_layer and smooth_l1_cost
8 years ago
7556ceffa6
add unitest for nce layer.
8 years ago
1171014d3f
add param_attr to nce_layer and enable multiple inputs.
8 years ago
805088c615
pass unit test
8 years ago
c810e6a7c0
Merge branch 'develop' into release/0.10.0
8 years ago
b23a23c9db
fixed error in beam_search example and documents
8 years ago
4dafa6987c
fix gru_step_naive_layer name
8 years ago
c6a8e23a9e
Fix unittests
8 years ago
3f1151a54c
Add error clipping to MT demo.
...
* Compose GRU step naive layer in trainer config helpers.
* It is uses mixed_layer for gate.
* It supports ERROR_CLIPPING, DROPOUT
* Add error clipping in MT demo.
* Fix #1143
* Fix #1891
8 years ago
63e4e16ced
add smooth_l1 interface to v2 doc.
8 years ago
2838491235
add smooth_l1 interface to v2 doc.
8 years ago
6c654c012a
resolve conflicts
8 years ago
cd7c55aa8c
generate protostr automatically when adding a new test for trainer_config_helpers.
8 years ago
22f2519eba
refine documents
8 years ago
1fd00758ac
SmoothL1 loss
8 years ago
68b958c368
Merge pull request #1852 from pengli09/doc-error
...
Fix doc error
8 years ago
42b09b9cac
Fix doc error
8 years ago
8b5e0275b2
fix sphinx doc bug
8 years ago
78b322fdba
Merge pull request #1848 from luotao1/doc
...
fix sphinx doc bug
8 years ago
4f769a8a1d
fix sphinx doc bug
8 years ago
18a3588b24
Merge branch 'develop' of github.com:baidu/Paddle into feature/c_api
8 years ago
df5a95dce8
Merge pull request #1701 from luotao1/stride
...
stride pooling for seqlastin and seqfirstin.
8 years ago
e8f65b86f5
nce_layer cannot accept neg_distribution
8 years ago
ba68ce1a1a
Merge branch 'develop' into stride
8 years ago
e423c5d030
It is no need to config num_classes in hsigmoid
...
It should be always equals to label's size.
8 years ago
c1738e29c8
Merge branch 'develop' into stride
8 years ago
7adad0c92d
Refine NCE Layer
8 years ago
dd613047b1
refine annotation
8 years ago
cbbec59547
adjust poolSequenceWithStride interface for average and max
8 years ago
9c1c19b6d0
Merge branch 'develop' of github.com:baidu/Paddle into feature/c_api
8 years ago
0291c01884
Merge branch 'develop' into stride
8 years ago
5961b52b13
Merge pull request #1653 from Noplz/normalize-layer
...
CrossChannelNorm Layer for SSD
8 years ago
9298a9ec0d
stride pooling for seqlastin and seqfirstin
8 years ago
dc45cb4b9d
changed projections.protostr
8 years ago
784e242bd5
Remove redundancy codes
8 years ago
fc7f72c03f
modified after reyoung's comments
8 years ago
090c974e4b
completed implementation of cudnn_convt convTransProjection and convTransOperator
8 years ago
07c1ea258f
python interface for convTransProjection and convTransOperator
8 years ago
c06d8d2129
Assert cross_channel_norm's input filters
8 years ago
8c2d1bad7a
Merge branch 'develop' into normalize-layer
8 years ago
eb43d93a58
Change Normalize layer to CrossChannelNorm layer
8 years ago
08113b2019
Merge branch 'develop' of github.com:baidu/Paddle into feature/c_api
8 years ago
bd4ec1b493
Merge branch 'develop' into memory.set_input
8 years ago
36ed2ff1ea
keep forward compatibility
8 years ago
7dbc77ba4d
rename regression_cost to mse_cost
8 years ago
bf838034d6
Merge branch 'develop' into fix-crf-weight-and-coeff-bug
8 years ago
eea0097dcb
NormalizeLayer for SSD
8 years ago
8feb58368c
Merge branch 'feature/fix_ccache_not_in_path' into feature/c_api
8 years ago
8243797059
add relu in layer_math.py
8 years ago
4380e73fcd
Merge branch 'develop' of github.com:baidu/Paddle into feature/c_api
8 years ago
8d5a18a209
Complete Layers documentation
8 years ago
3758993393
Simplify layer.v2
8 years ago
06056fe26e
Merge branch 'develop' into layer
8 years ago
623d24ad5c
convert mixed layer, projection and operator
8 years ago
5258bcf3ee
implement more layers in v2
8 years ago
e768721cd9
fix calculating totalScore2_ bug
8 years ago
043859b5db
clean up code
8 years ago
e00f06afa4
Add top-k error
8 years ago
0b673756f1
add SequenceReshapeLayer in trainer_config_helpers
8 years ago
f9eddadb3e
follow comments, add seq_concat_layer in docs
8 years ago
27a42c2e3b
add SequenceConcatLayer in trainer_config_helpers
8 years ago
7d551dd484
Make it possible to postpone setting the layer name for a memory.
...
The reason for adding the function is exemplified in the following hypothetical code:
mem = memory(name=None, size=256)
hidden = fc_layer(input=mem)
state = hidden + x
mem.set_input(state)
In the above code segment, it would be very annoying if we require the user to provide
the name at memory() call because the layer name of state is automatically generated
and is not easy to set it.
Change-Id: I918bf1d3d5c26addd88a6f7021e98b3e0e9df494
8 years ago
71c3c93c72
Fix unittest
8 years ago
970440622f
Temporary disable async load data in PyDP2.
...
* It seems some other change breaks the async load. It will cause data
error in GPU mode.
8 years ago
c785975b4b
Merge pull request #1256 from luotao1/maxout
...
remove usused arguments for maxout_layer, refine notes for pad_layer
8 years ago
ca25b9a508
remove unused notes in maxout layer
8 years ago
ccb553fec4
Merge pull request #1253 from wangkuiyi/python_learning_and_refactor
...
Rename Python function DataBase into create_data_config_proto
8 years ago
058eeac0fc
Revert "Remove completely create_data_config_proto"
...
This reverts commit ab279beed1
8 years ago
ab279beed1
Remove completely create_data_config_proto
8 years ago
03148804bb
remove usused arguments for maxout_layer, refine notes for pad_layer
8 years ago
b9dfe8e7c8
Merge pull request #1231 from yu239/rotate_and_flip
...
One bug fix and two new features
8 years ago
996b1de1d8
Rename DataBase into create_data_config_proto
8 years ago
73dcf2cd58
improving code comments
8 years ago
6245fed240
rotate_layer python interface fixes
8 years ago
9c42d90468
add comments in gru_step_layer of layers.py to explain the parameter location
8 years ago
b4c1d17580
remove flip_layer
8 years ago
55eb2fcffa
format correction
8 years ago
781b85b5fc
rotate_layer and flip_layer * added getMin and getMax for GpuMatrix * gru_step_layer parameter name
8 years ago
04b5daf92d
change the parameter position of gru_step_layer from 1 back to 0
8 years ago
c1f9cd9dbe
Merge pull request #1241 from wangyang59/rnnParaShare
...
make gru_group parameters sharable
8 years ago
e1d074abdb
updated comments for gru_group and lstm_group in networks.py
8 years ago
6da7283475
make gru_group parameters sharable
8 years ago
44e3c724f9
Refine and comments
8 years ago
88c3862378
Merge branch 'develop' of github.com:baidu/Paddle into feature/c_api
8 years ago
312326899e
add api to doc
8 years ago
8d47499e1d
update code
8 years ago
a5c1658d45
Always create protobuf_equal
...
* Because currently Paddle only use protobuf 3.
8 years ago
ceb2d39799
Fix bugs in config_helpers unittest.
...
* It gets wrong command line arguments before.
8 years ago
19cb2a7fb3
fix default value of cos_sim scale
8 years ago
64022143d8
Fix unittest
8 years ago
6b61a096e1
Optional padding mode, namely ceil or floor, ceil by default.
8 years ago
c8817a192b
merge upstream
8 years ago
8b5431d5e1
padding operation
8 years ago
8acd1ac31a
Add extern python interp
8 years ago
eefe5a7ca6
Merge branch 'develop' of github.com:baidu/Paddle into feature/mnist_train_api
8 years ago
6951c8ad2e
Merge pull request #1014 from reyoung/feature/fix_bugs_in_math
...
Rename math.py to layer_math.py
8 years ago
685299c3c5
Rename math.py to layer_math.py
...
* Fix #903
8 years ago
224e5fcc77
fix bug:
...
* gradient_clipping_threshold should be allowed to set with parameter-grain
8 years ago
763a30fdde
add config_parser_utils
8 years ago
843b63bb84
add config_parser in trainer_config_helpers to seperate trainer config
8 years ago
b53bdcdc67
Merge pull request #867 from Noplz/ssd
...
priorbox layer for Single Shot Multibox Detection Network
8 years ago
af820fb2eb
Merge branch 'develop' into fix-crf-weight-and-coeff-bug
8 years ago
6e405a10c5
fix style issues
8 years ago
f1e31ecada
Merge branch 'develop' into fix-crf-weight-and-coeff-bug
8 years ago
8fe3a3aa73
Add excluded_chunk_types to ChunkEvaluator
...
The chunks of types in excluded_chunk_types will not be counted in
ChunkEvaluator. This is useful for tasks such as SRL, in which chunks of
type V (verb) will not be taken into account in evaluation.
8 years ago
deed483c22
Merge branch 'develop' into link
8 years ago
50edf5243e
Merge pull request #862 from backyes/fix_data_sources
...
refine data_sources.py and PyDataProvider2.py to make more readable
8 years ago
2b4ddb3808
fix dead links and refine tutorials/index
8 years ago
7b74a6de63
Merge pull request #900 from wangyang59/batchNorm
...
fixed a bug for demo/gan caused by batchNormLayer
8 years ago
f94a0cce90
Merge pull request #922 from reyoung/feature/fix_bugs_in_math
...
Fix bad import name in trainer_config_helpers.
8 years ago
54cb6bdb37
Fix bad import name in trainer_config_helpers.
...
* math => layer_math
* Fix #903
8 years ago
ee2c14229e
Partially fix demo data provider.
...
* Partially fix #622
8 years ago
a50caba881
modified img_trans_layers.protostr to refect the change in batchNorm layer behavior
8 years ago
638cf8d469
Merge pull request #905 from pengli09/fix-model-avg-py-error
...
Remove do_average_in_cpu, max_average_window, average_window from optimizers.py
8 years ago
59ae6612e1
Fix formatting error.
8 years ago
6516fd9294
Fix formatting error.
8 years ago
c287b6b216
Add an extra parameter label to chunk_evaluator
...
In order to keep consistent with other evaluators, an extra parameter
label is add to chunk_evaluator. Document and demos are modified
accordingly.
8 years ago
7598846cf5
Merge remote branch 'origin/develop' into fix_data_sources
8 years ago
89a638b8b3
do pre-commit
8 years ago
8455071a51
Remove do_average_in_cpu, max_average_window, average_window from optimizers.py
...
These three parameters have already been moved to model_average. Leaving
them here will cause duplicate keys in kwargs
8 years ago
707a9c9bbd
Fix variable name and add the annotation
8 years ago
c0076084e2
Format the python file.
8 years ago
0764bb4a9e
add exclude_patterns for conf.py.in
8 years ago
0eac399280
priorbox layer for ssd
8 years ago
62b20ca033
refine data_sources.py and PyDataProvider2.py to make more readable
8 years ago
52f6c9a6a9
Merge branch 'develop' into link
8 years ago
4afaaa4b92
Autoformat all files
8 years ago
3f9f222328
fix some dead links in doc/
8 years ago
56c20f8261
Merge pull request #734 from hohdiy/dev-test
...
test code for issue #729
8 years ago
b6aca330a2
Merge pull request #764 from emailweixu/multiple_parse
...
Correctly handling multiple calls to parse_config()
8 years ago
e9549cbb78
Change "Baidu, Inc" into "PaddlePaddle Authors"
8 years ago
957794cd29
fix bad ident
8 years ago
23d57335f1
update cr for pull #734 .
8 years ago
d87b2c11ac
Fix bug in CMakeList.txt
...
test_rest_hook.py => test_reset_hook.py
Change-Id: I84909ade4a1ea2bec4311264626dd000cd6bc86c
8 years ago
3cf7337f30
Correctly handling multiple calls to parse_config()
...
To solve this, we maintain the list of DefaultNameFactory used in by trainer_config_helper,
and reset the state at the beginning of each parse_config call.
Change-Id: I13c7574dc8f0b6bc6f6b7c92eb425e2c52c926e8
8 years ago
78bdd32471
Merge branch 'develop' into warpctc
8 years ago
7f78912c9f
test code for issue #729
8 years ago
7bb627d3f9
Merge pull request #409 from luotao1/conv
...
Support rectangle input for CNN
8 years ago
7bb7fed833
Simplify the CMakelist.txt and fix typos.
8 years ago
23e61c2132
fix bug when run test_layerHelpers multiple times
8 years ago
7830893a83
fix conflict
8 years ago
749456bd60
Fix test_layerHelpers bug
...
The values for ____crf_layer_0__.w0 in python/paddle/trainer_config_helpers/tests/configs/protostr/test_cost_layers.protostr is not correct due to swapped height and width in config_parser
8 years ago
25f1fbc491
Merge branch 'develop' into warpctc
8 years ago
4641285c75
Added a test in test_NetworkCompare to verify cudnn and exconv, fixed a bug in cudnn_conv in dealing with groups
8 years ago
1eb9c36fd2
Make ApproximatelyEquals fit for protobuf2
8 years ago
1733a777fe
Using ApproximatelyEquals for trainer config unittest.
...
* Make float equal works well.
* compare 0.01 and 0.009999999999 will return true.
8 years ago
4d487c6f35
Integrate warp-ctc as WarpCTCLayer, including unitest and layer interface.
8 years ago
7573205c68
follow comments on config_parser
8 years ago
96615fe329
merge develop, fix conflict
8 years ago
b3f4e53539
fix LogActivation is not defined
8 years ago
ed7334d694
fix the has_LayerOutput boolean for StaticInput as the input of recurrent_group
8 years ago
496d64ebdb
Support rectangle input for CNN
9 years ago
29727289fc
modify first level directory of english doc
9 years ago
8c59437612
change is_train to is_generating
9 years ago
ffbf00a022
Merge branch 'develop' into group
9 years ago
a6ad9a1608
Fix unittest
...
Change-Id: Ic80845c892c96c37a0df0ddc433fe1aeaa5a9d1c
9 years ago
bf6f690f31
Add ScalingProjection
...
out = w * input
where w is a parameter of size 1
Change-Id: Ife682d62323ceb1a20cbbf6269421b20a862d888
9 years ago
0752b3b710
add layer check for recurrent_group
9 years ago
a1ba3f442f
format python code in python directory
9 years ago
4607d517bf
Add unittest for split datasource
...
* Fix #436
9 years ago
afba3a2d46
Merge branch 'develop' of github.com:baidu/Paddle into feature/fix_pydataprovider_multiple_obj_bugs
9 years ago
ae7452f47b
Merge branch 'develop' of github.com:baidu/Paddle into feature/fix_pydataprovider_multiple_obj_bugs
9 years ago
33b81648a3
Fix bug in multple objects in define_py_sources
9 years ago
62c5389bad
fix test_layerHelpers unittest error
9 years ago
ca0bb40c6e
Merge pull request #300 from QiJune/feature/sppnet
...
add SpatialPyramidPoolLayer c++ support
9 years ago
aa560dbb97
fix bug in sum_cost
9 years ago
ebb153b067
Merge pull request #416 from yu239/hl_activetype
...
change the act.name for LinearActivation() to "linear" so that it won't fail in hl_activetype; also fix the hasinputsset in submodel
9 years ago
eb3bf9ea64
Merge pull request #360 from emailweixu/sum_cost
...
Add SumCost
9 years ago
45f6e1abee
change hlactivetype instead of act.name
9 years ago
36fa251756
'*' operator overload for LayerOutput
...
Making '*' support the multiplication between a scalar and LayerOutput
Also changing '+' to support adding between a vector and a scalar.
Change-Id: I7daf35590dc2b2f855a29d9ef43ac57979442e0f
9 years ago
9dd588b414
fix merge conflicts
9 years ago
8295eb91bf
Merge pull request #287 from gangliao/bilinear
...
Add bilinear interpolation layer
9 years ago
cfc965d52c
Merge pull request #269 from wangyang59/deconv
9 years ago
61444d903d
Merge remote-tracking branch 'baidu/develop' into feature/sppnet
9 years ago
880774d141
change the act.name for LinearActivation() to "linear" so that it won't
...
fail in hl_activetype; also fix the hasinputsset in submodel
9 years ago
8d4c453bbb
set mixedlayer output size according to input operator ( #414 )
...
* set mixedlayer output size according to input operator
* change from num_channel to num_channels for conv_operator (the old one is
really misleading because all the others are num_channels)
* also changed the arg name in projections.py
9 years ago
9ff0db37fe
Generate bilinear protostr via Linux
9 years ago
caoying03
guosheng
hedaoyuan
zlx
Cao Ying
wanghaoshuang
Yu Yang
xuwei06
Tao Luo
Yang yaming
dangqingqing
Peng LI
Peng Li
yangyaming
emailweixu
Liu Yiqun
wwhu
qiaolongfei
Yibing Liu
zhanghaichao
qijun
Yi Wang
wangyang59
gaoyuan
Yuan Gao
Liang Zhao
Yi Wang
Haonan
Haonan
zhangruiqing01
liaogang
wangyanfei01
Yi Wang
hanchao