Created
January 30, 2020 10:58
-
-
Save manish-kumar-garg/f3efee2071c80400767c7a4b10a43a90 to your computer and use it in GitHub Desktop.
compile_tf_graph
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. | |
_np_qint8 = np.dtype([("qint8", np.int8, 1)]) | |
/home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. | |
_np_quint8 = np.dtype([("quint8", np.uint8, 1)]) | |
/home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. | |
_np_qint16 = np.dtype([("qint16", np.int16, 1)]) | |
/home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:529: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. | |
_np_quint16 = np.dtype([("quint16", np.uint16, 1)]) | |
/home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:530: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. | |
_np_qint32 = np.dtype([("qint32", np.int32, 1)]) | |
/home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:535: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. | |
np_resource = np.dtype([("resource", np.ubyte, 1)]) | |
Using config file 'returnn.config'. | |
Returnn compile-tf-graph starting up. | |
RETURNN starting up, version 20200129.184103--git-a399fac3-dirty, date/time 2020-01-30-10-57-15 (UTC+0000), pid 19583, cwd /home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention, Python /home/ubuntu/tf1.13/bin/python | |
Hostname: ip-10-1-16-53 | |
TensorFlow: 1.13.1 (b'v1.13.1-0-g6612da8951') (<site-package> in /home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow) | |
Setup TF inter and intra global thread pools, num_threads None, session opts {'log_device_placement': False, 'device_count': {'GPU': 0}}. | |
2020-01-30 10:57:15.058438: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA | |
2020-01-30 10:57:15.660183: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero | |
2020-01-30 10:57:15.687918: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero | |
2020-01-30 10:57:15.694795: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero | |
2020-01-30 10:57:15.704406: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:998] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero | |
2020-01-30 10:57:15.706023: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x556e6b9f1cb0 executing computations on platform CUDA. Devices: | |
2020-01-30 10:57:15.706056: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): Tesla V100-SXM2-16GB, Compute Capability 7.0 | |
2020-01-30 10:57:15.706067: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (1): Tesla V100-SXM2-16GB, Compute Capability 7.0 | |
2020-01-30 10:57:15.706074: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (2): Tesla V100-SXM2-16GB, Compute Capability 7.0 | |
2020-01-30 10:57:15.706085: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (3): Tesla V100-SXM2-16GB, Compute Capability 7.0 | |
2020-01-30 10:57:15.728153: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2300080000 Hz | |
2020-01-30 10:57:15.730335: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x556e6c0b5780 executing computations on platform Host. Devices: | |
2020-01-30 10:57:15.730364: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): <undefined>, <undefined> | |
2020-01-30 10:57:15.730446: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix: | |
2020-01-30 10:57:15.730465: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] | |
CUDA_VISIBLE_DEVICES is not set. | |
Collecting TensorFlow device list... | |
2020-01-30 10:57:15.733876: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 0 with properties: | |
name: Tesla V100-SXM2-16GB major: 7 minor: 0 memoryClockRate(GHz): 1.53 | |
pciBusID: 0000:00:1b.0 | |
totalMemory: 15.78GiB freeMemory: 15.47GiB | |
2020-01-30 10:57:15.733937: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 1 with properties: | |
name: Tesla V100-SXM2-16GB major: 7 minor: 0 memoryClockRate(GHz): 1.53 | |
pciBusID: 0000:00:1c.0 | |
totalMemory: 15.78GiB freeMemory: 15.47GiB | |
2020-01-30 10:57:15.733985: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 2 with properties: | |
name: Tesla V100-SXM2-16GB major: 7 minor: 0 memoryClockRate(GHz): 1.53 | |
pciBusID: 0000:00:1d.0 | |
totalMemory: 15.78GiB freeMemory: 15.47GiB | |
2020-01-30 10:57:15.734029: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 3 with properties: | |
name: Tesla V100-SXM2-16GB major: 7 minor: 0 memoryClockRate(GHz): 1.53 | |
pciBusID: 0000:00:1e.0 | |
totalMemory: 15.78GiB freeMemory: 15.47GiB | |
2020-01-30 10:57:15.734082: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0, 1, 2, 3 | |
2020-01-30 10:57:15.739501: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix: | |
2020-01-30 10:57:15.739527: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0 1 2 3 | |
2020-01-30 10:57:15.739543: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0: N Y Y Y | |
2020-01-30 10:57:15.739554: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 1: Y N Y Y | |
2020-01-30 10:57:15.739565: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 2: Y Y N Y | |
2020-01-30 10:57:15.739576: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 3: Y Y Y N | |
2020-01-30 10:57:15.739723: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/device:GPU:0 with 15049 MB memory) -> physical GPU (device: 0, name: Tesla V100-SXM2-16GB, pci bus id: 0000:00:1b.0, compute capability: 7.0) | |
2020-01-30 10:57:15.740041: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/device:GPU:1 with 15049 MB memory) -> physical GPU (device: 1, name: Tesla V100-SXM2-16GB, pci bus id: 0000:00:1c.0, compute capability: 7.0) | |
2020-01-30 10:57:15.740296: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/device:GPU:2 with 15049 MB memory) -> physical GPU (device: 2, name: Tesla V100-SXM2-16GB, pci bus id: 0000:00:1d.0, compute capability: 7.0) | |
2020-01-30 10:57:15.740592: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/device:GPU:3 with 15049 MB memory) -> physical GPU (device: 3, name: Tesla V100-SXM2-16GB, pci bus id: 0000:00:1e.0, compute capability: 7.0) | |
Local devices available to TensorFlow: | |
1/10: name: "/device:CPU:0" | |
device_type: "CPU" | |
memory_limit: 268435456 | |
locality { | |
} | |
incarnation: 12254757501798345357 | |
2/10: name: "/device:XLA_GPU:0" | |
device_type: "XLA_GPU" | |
memory_limit: 17179869184 | |
locality { | |
} | |
incarnation: 17434536340433975299 | |
physical_device_desc: "device: XLA_GPU device" | |
3/10: name: "/device:XLA_GPU:1" | |
device_type: "XLA_GPU" | |
memory_limit: 17179869184 | |
locality { | |
} | |
incarnation: 6951473131317435871 | |
physical_device_desc: "device: XLA_GPU device" | |
4/10: name: "/device:XLA_GPU:2" | |
device_type: "XLA_GPU" | |
memory_limit: 17179869184 | |
locality { | |
} | |
incarnation: 11901565618654746057 | |
physical_device_desc: "device: XLA_GPU device" | |
5/10: name: "/device:XLA_GPU:3" | |
device_type: "XLA_GPU" | |
memory_limit: 17179869184 | |
locality { | |
} | |
incarnation: 2041843563430914595 | |
physical_device_desc: "device: XLA_GPU device" | |
6/10: name: "/device:XLA_CPU:0" | |
device_type: "XLA_CPU" | |
memory_limit: 17179869184 | |
locality { | |
} | |
incarnation: 17127850179857194621 | |
physical_device_desc: "device: XLA_CPU device" | |
7/10: name: "/device:GPU:0" | |
device_type: "GPU" | |
memory_limit: 15780652647 | |
locality { | |
bus_id: 1 | |
links { | |
link { | |
device_id: 1 | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
link { | |
device_id: 2 | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
link { | |
device_id: 3 | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
} | |
} | |
incarnation: 12586835745688706958 | |
physical_device_desc: "device: 0, name: Tesla V100-SXM2-16GB, pci bus id: 0000:00:1b.0, compute capability: 7.0" | |
8/10: name: "/device:GPU:1" | |
device_type: "GPU" | |
memory_limit: 15780652647 | |
locality { | |
bus_id: 1 | |
links { | |
link { | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
link { | |
device_id: 2 | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
link { | |
device_id: 3 | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
} | |
} | |
incarnation: 16219785379659910568 | |
physical_device_desc: "device: 1, name: Tesla V100-SXM2-16GB, pci bus id: 0000:00:1c.0, compute capability: 7.0" | |
9/10: name: "/device:GPU:2" | |
device_type: "GPU" | |
memory_limit: 15780652647 | |
locality { | |
bus_id: 1 | |
links { | |
link { | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
link { | |
device_id: 1 | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
link { | |
device_id: 3 | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
} | |
} | |
incarnation: 15498480627625260496 | |
physical_device_desc: "device: 2, name: Tesla V100-SXM2-16GB, pci bus id: 0000:00:1d.0, compute capability: 7.0" | |
10/10: name: "/device:GPU:3" | |
device_type: "GPU" | |
memory_limit: 15780652647 | |
locality { | |
bus_id: 1 | |
links { | |
link { | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
link { | |
device_id: 1 | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
link { | |
device_id: 2 | |
type: "StreamExecutor" | |
strength: 1 | |
} | |
} | |
} | |
incarnation: 4701660963018527730 | |
physical_device_desc: "device: 3, name: Tesla V100-SXM2-16GB, pci bus id: 0000:00:1e.0, compute capability: 7.0" | |
Using gpu device 0: Tesla V100-SXM2-16GB | |
Using gpu device 1: Tesla V100-SXM2-16GB | |
Using gpu device 2: Tesla V100-SXM2-16GB | |
Using gpu device 3: Tesla V100-SXM2-16GB | |
Create graph... | |
Loading network, train flag False, eval flag True, search flag False | |
WARNING:tensorflow:From /home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version. | |
Instructions for updating: | |
Colocations handled automatically by placer. | |
layer root/'data' output: Data(name='data', shape=(None, 40), batch_shape_meta=[B,T|'time:var:extern_data:data',F|40]) | |
layer root/'source' output: Data(name='source_output', shape=(None, 40), batch_shape_meta=[B,T|'time:var:extern_data:data',F|40]) | |
layer root/'lstm0_fw' output: Data(name='lstm0_fw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'time:var:extern_data:data',B,F|1024]) | |
layer root/'lstm0_bw' output: Data(name='lstm0_bw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'time:var:extern_data:data',B,F|1024]) | |
layer root/'lstm0_pool' output: Data(name='lstm0_pool_output', shape=(None, 2048), batch_shape_meta=[B,T|?,F|2048]) | |
layer root/'lstm1_fw' output: Data(name='lstm1_fw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm0_pool',B,F|1024]) | |
layer root/'lstm1_bw' output: Data(name='lstm1_bw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm0_pool',B,F|1024]) | |
layer root/'lstm1_pool' output: Data(name='lstm1_pool_output', shape=(None, 2048), batch_shape_meta=[B,T|?,F|2048]) | |
layer root/'lstm2_fw' output: Data(name='lstm2_fw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm1_pool',B,F|1024]) | |
layer root/'lstm2_bw' output: Data(name='lstm2_bw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm1_pool',B,F|1024]) | |
layer root/'lstm2_pool' output: Data(name='lstm2_pool_output', shape=(None, 2048), batch_shape_meta=[B,T|?,F|2048]) | |
layer root/'lstm3_fw' output: Data(name='lstm3_fw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1024]) | |
layer root/'lstm3_bw' output: Data(name='lstm3_bw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1024]) | |
layer root/'lstm3_pool' output: Data(name='lstm3_pool_output', shape=(None, 2048), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|2048]) | |
layer root/'lstm4_fw' output: Data(name='lstm4_fw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1024]) | |
layer root/'lstm4_bw' output: Data(name='lstm4_bw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1024]) | |
layer root/'lstm4_pool' output: Data(name='lstm4_pool_output', shape=(None, 2048), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|2048]) | |
layer root/'lstm5_fw' output: Data(name='lstm5_fw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1024]) | |
layer root/'lstm5_bw' output: Data(name='lstm5_bw_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1024]) | |
layer root/'encoder' output: Data(name='encoder_output', shape=(None, 2048), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|2048]) | |
layer root/'ctc' output: Data(name='ctc_output', shape=(None, 10026), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|10026]) | |
layer root/'enc_ctx' output: Data(name='enc_ctx_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1024]) | |
layer root/'inv_fertility' output: Data(name='inv_fertility_output', shape=(None, 1), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1]) | |
layer root/'enc_value' output: Data(name='enc_value_output', shape=(None, 1, 2048), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,1,F|2048]) | |
layer root/'output' output: Data(name='output_output', shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B]) | |
Rec layer 'output' (search False, train False) sub net: | |
Input layers moved out of loop: (#: 1) | |
output | |
Output layers moved out of loop: (#: 0) | |
None | |
Layers in loop: (#: 1) | |
end | |
Unused layers: (#: 14) | |
accum_att_weights | |
att | |
att0 | |
att_weights | |
energy | |
energy_in | |
energy_tanh | |
output_prob | |
readout | |
readout_in | |
s | |
s_transformed | |
target_embed | |
weight_feedback | |
layer root/output:rec-subnet-input/'output' output: Data(name='output_output', shape=(None,), dtype='int32', sparse=True, dim=10025, batch_shape_meta=[B,T|'time:var:extern_data:classes']) | |
layer root/output:rec-subnet/'end' output: Data(name='end_output', shape=(None,), dtype='bool', sparse=True, dim=2, batch_shape_meta=[B,T|'time:var:extern_data:classes']) | |
layer root/output:rec-subnet/'weight_feedback' output: Data(name='weight_feedback_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|?,B,F|1024]) | |
layer root/output:rec-subnet/'s' output: Data(name='s_output', shape=(1000,), time_dim_axis=None, batch_shape_meta=[B,F|1000]) | |
layer root/output:rec-subnet/'s_transformed' output: Data(name='s_transformed_output', shape=(1024,), time_dim_axis=None, batch_shape_meta=[B,F|1024]) | |
layer root/output:rec-subnet/'energy_in' output: Data(name='energy_in_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1024]) | |
layer root/output:rec-subnet/'energy_tanh' output: Data(name='energy_tanh_output', shape=(None, 1024), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1024]) | |
layer root/output:rec-subnet/'energy' output: Data(name='energy_output', shape=(None, 1), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1]) | |
layer root/output:rec-subnet/'att_weights' output: Data(name='att_weights_output', shape=(1, None), time_dim_axis=2, feature_dim_axis=1, batch_shape_meta=[B,F|1,T|'spatial:0:lstm2_pool']) | |
layer root/output:rec-subnet/'accum_att_weights' output: Data(name='accum_att_weights_output', shape=(None, 1), batch_dim_axis=1, batch_shape_meta=[T|'spatial:0:lstm2_pool',B,F|1]) | |
layer root/output:rec-subnet/'att0' output: Data(name='att0_output', shape=(1, 2048), time_dim_axis=None, batch_shape_meta=[B,1,F|2048]) | |
layer root/output:rec-subnet/'att' output: Data(name='att_output', shape=(2048,), time_dim_axis=None, batch_shape_meta=[B,F|2048]) | |
layer root/output:rec-subnet/'target_embed' output: Data(name='target_embed_output', shape=(None, 621), batch_shape_meta=[B,T|'time:var:extern_data:classes',F|621]) | |
Exception creating layer root/'output' of class RecLayer with opts: | |
{'_target_layers': {}, | |
'cheating': False, | |
'max_seq_len': <tf.Tensor 'max_seq_len_encoder:0' shape=() dtype=int32>, | |
'n_out': <class 'Util.NotSpecified'>, | |
'name': 'output', | |
'network': <TFNetwork 'root' train=False>, | |
'output': Data(name='output_output', shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B]), | |
'sources': [], | |
'target': 'classes', | |
'unit': {'accum_att_weights': {'class': 'eval', | |
'eval': 'source(0) + source(1) * source(2) * ' | |
'0.5', | |
'from': ['prev:accum_att_weights', | |
'att_weights', | |
'base:inv_fertility'], | |
'out_type': {'dim': 1, 'shape': (None, 1)}}, | |
'att': {'axes': 'except_batch', | |
'class': 'merge_dims', | |
'from': ['att0']}, | |
'att0': {'base': 'base:enc_value', | |
'class': 'generic_attention', | |
'weights': 'att_weights'}, | |
'att_weights': {'class': 'softmax_over_spatial', 'from': ['energy']}, | |
'end': {'class': 'compare', 'from': ['output'], 'value': 0}, | |
'energy': {'activation': None, | |
'class': 'linear', | |
'from': ['energy_tanh'], | |
'n_out': 1, | |
'with_bias': False}, | |
'energy_in': {'class': 'combine', | |
'from': ['base:enc_ctx', | |
'weight_feedback', | |
's_transformed'], | |
'kind': 'add', | |
'n_out': 1024}, | |
'energy_tanh': {'activation': 'tanh', | |
'class': 'activation', | |
'from': ['energy_in']}, | |
'output': {'beam_size': 12, | |
'cheating': False, | |
'class': 'choice', | |
'from': ['output_prob'], | |
'initial_output': 0, | |
'target': 'classes'}, | |
'output_prob': {'class': 'softmax', | |
'dropout': 0.3, | |
'from': ['readout'], | |
'loss': 'ce', | |
'loss_opts': {'label_smoothing': 0.1}, | |
'target': 'classes'}, | |
'readout': {'class': 'reduce_out', | |
'from': ['readout_in'], | |
'mode': 'max', | |
'num_pieces': 2}, | |
'readout_in': {'activation': None, | |
'class': 'linear', | |
'from': ['s', 'prev:target_embed', 'att'], | |
'n_out': 1000}, | |
's': {'class': 'rnn_cell', | |
'from': ['prev:target_embed', 'prev:att'], | |
'n_out': 1000, | |
'unit': 'LSTMBlock'}, | |
's_transformed': {'activation': None, | |
'class': 'linear', | |
'from': ['s'], | |
'n_out': 1024, | |
'with_bias': False}, | |
'target_embed': {'activation': None, | |
'class': 'linear', | |
'from': ['output'], | |
'initial_output': 0, | |
'n_out': 621, | |
'with_bias': False}, | |
'weight_feedback': {'activation': None, | |
'class': 'linear', | |
'from': ['prev:accum_att_weights'], | |
'n_out': 1024, | |
'with_bias': False}}} | |
Unhandled exception <class 'ValueError'> in thread <_MainThread(MainThread, started 140318093119616)>, proc 19583. | |
Thread current, main, <_MainThread(MainThread, started 140318093119616)>: | |
(Excluded thread.) | |
That were all threads. | |
EXCEPTION | |
Traceback (most recent call last): | |
File "returnn/tools/compile_tf_graph.py", line 758, in <module> | |
line: main(sys.argv) | |
locals: | |
main = <local> <function main at 0x7f9e3c0a3bf8> | |
sys = <local> <module 'sys' (built-in)> | |
sys.argv = <local> ['returnn/tools/compile_tf_graph.py', 'returnn.config', '--eval', '1', '--output_file', 'out.meta'], len = 6, _[0]: {len = 33} | |
File "returnn/tools/compile_tf_graph.py", line 686, in main | |
line: network = create_graph(train_flag=train_flag, eval_flag=eval_flag, search_flag=search_flag, net_dict=net_dict) | |
locals: | |
network = <not found> | |
create_graph = <global> <function create_graph at 0x7f9e3c0a36a8> | |
train_flag = <local> False | |
eval_flag = <local> True | |
search_flag = <local> False | |
net_dict = <local> {'source': {'class': 'eval', 'eval': 'tf.clip_by_value(source(0), -3.0, 3.0)'}, 'lstm0_fw': {'class': 'rec', 'unit': 'nativelstm2', 'n_out': 1024, 'direction': 1, 'from': ['source']}, 'lstm0_bw': {'class': 'rec', 'unit': 'nativelstm2', 'n_out': 1024, 'direction': -1, 'from': ['source']}, 'lstm0_p..., len = 25 | |
File "returnn/tools/compile_tf_graph.py", line 77, in create_graph | |
line: network, updater = Engine.create_network( | |
config=config, rnd_seed=1, | |
train_flag=train_flag, eval_flag=eval_flag, search_flag=search_flag, | |
net_dict=net_dict) | |
locals: | |
network = <not found> | |
updater = <not found> | |
Engine = <local> <class 'TFEngine.Engine'> | |
Engine.create_network = <local> <bound method Engine.create_network of <class 'TFEngine.Engine'>> | |
config = <global> <Config.Config object at 0x7f9e3c0880b8> | |
rnd_seed = <not found> | |
train_flag = <local> False | |
eval_flag = <local> True | |
search_flag = <local> False | |
net_dict = <local> {'source': {'class': 'eval', 'eval': 'tf.clip_by_value(source(0), -3.0, 3.0)'}, 'lstm0_fw': {'class': 'rec', 'unit': 'nativelstm2', 'n_out': 1024, 'direction': 1, 'from': ['source']}, 'lstm0_bw': {'class': 'rec', 'unit': 'nativelstm2', 'n_out': 1024, 'direction': -1, 'from': ['source']}, 'lstm0_p..., len = 25 | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFEngine.py", line 1113, in create_network | |
line: network.construct_from_dict(net_dict) | |
locals: | |
network = <local> <TFNetwork 'root' train=False> | |
network.construct_from_dict = <local> <bound method TFNetwork.construct_from_dict of <TFNetwork 'root' train=False>> | |
net_dict = <local> {'source': {'class': 'eval', 'eval': 'tf.clip_by_value(source(0), -3.0, 3.0)'}, 'lstm0_fw': {'class': 'rec', 'unit': 'nativelstm2', 'n_out': 1024, 'direction': 1, 'from': ['source']}, 'lstm0_bw': {'class': 'rec', 'unit': 'nativelstm2', 'n_out': 1024, 'direction': -1, 'from': ['source']}, 'lstm0_p..., len = 25 | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetwork.py", line 460, in construct_from_dict | |
line: self.construct_layer(net_dict, name) | |
locals: | |
self = <local> <TFNetwork 'root' train=False> | |
self.construct_layer = <local> <bound method TFNetwork.construct_layer of <TFNetwork 'root' train=False>> | |
net_dict = <local> {'source': {'class': 'eval', 'eval': 'tf.clip_by_value(source(0), -3.0, 3.0)'}, 'lstm0_fw': {'class': 'rec', 'unit': 'nativelstm2', 'n_out': 1024, 'direction': 1, 'from': ['source']}, 'lstm0_bw': {'class': 'rec', 'unit': 'nativelstm2', 'n_out': 1024, 'direction': -1, 'from': ['source']}, 'lstm0_p..., len = 25 | |
name = <local> 'decision', len = 8 | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetwork.py", line 652, in construct_layer | |
line: layer_class.transform_config_dict(layer_desc, network=self, get_layer=get_layer) | |
locals: | |
layer_class = <local> <class 'TFNetworkRecLayer.DecideLayer'> | |
layer_class.transform_config_dict = <local> <bound method BaseChoiceLayer.transform_config_dict of <class 'TFNetworkRecLayer.DecideLayer'>> | |
layer_desc = <local> {'loss': 'edit_distance', 'target': 'classes', 'loss_opts': {}} | |
network = <not found> | |
self = <local> <TFNetwork 'root' train=False> | |
get_layer = <local> <function TFNetwork.construct_layer.<locals>.get_layer at 0x7f9e06474158> | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetworkRecLayer.py", line 4092, in transform_config_dict | |
line: super(BaseChoiceLayer, cls).transform_config_dict(d, network=network, get_layer=get_layer) | |
locals: | |
super = <builtin> <class 'super'> | |
BaseChoiceLayer = <global> <class 'TFNetworkRecLayer.BaseChoiceLayer'> | |
cls = <local> <class 'TFNetworkRecLayer.DecideLayer'> | |
transform_config_dict = <not found> | |
d = <local> {'loss': 'edit_distance', 'target': 'classes', 'loss_opts': {}} | |
network = <local> <TFNetwork 'root' train=False> | |
get_layer = <local> <function TFNetwork.construct_layer.<locals>.get_layer at 0x7f9e06474158> | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetworkLayer.py", line 448, in transform_config_dict | |
line: for src_name in src_names | |
locals: | |
src_name = <not found> | |
src_names = <local> ['output'], _[0]: {len = 6} | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetworkLayer.py", line 449, in <listcomp> | |
line: d["sources"] = [ | |
get_layer(src_name) | |
for src_name in src_names | |
if not src_name == "none"] | |
locals: | |
d = <not found> | |
get_layer = <local> <function TFNetwork.construct_layer.<locals>.get_layer at 0x7f9e06474158> | |
src_name = <local> 'output', len = 6 | |
src_names = <not found> | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetwork.py", line 607, in get_layer | |
line: return self.construct_layer(net_dict=net_dict, name=src_name) # set get_layer to wrap construct_layer | |
locals: | |
self = <local> <TFNetwork 'root' train=False> | |
self.construct_layer = <local> <bound method TFNetwork.construct_layer of <TFNetwork 'root' train=False>> | |
net_dict = <local> {'source': {'class': 'eval', 'eval': 'tf.clip_by_value(source(0), -3.0, 3.0)'}, 'lstm0_fw': {'class': 'rec', 'unit': 'nativelstm2', 'n_out': 1024, 'direction': 1, 'from': ['source']}, 'lstm0_bw': {'class': 'rec', 'unit': 'nativelstm2', 'n_out': 1024, 'direction': -1, 'from': ['source']}, 'lstm0_p..., len = 25 | |
name = <not found> | |
src_name = <local> 'output', len = 6 | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetwork.py", line 655, in construct_layer | |
line: return add_layer(name=name, layer_class=layer_class, **layer_desc) | |
locals: | |
add_layer = <local> <bound method TFNetwork.add_layer of <TFNetwork 'root' train=False>> | |
name = <local> 'output', len = 6 | |
layer_class = <local> <class 'TFNetworkRecLayer.RecLayer'> | |
layer_desc = <local> {'cheating': False, 'unit': {'output': {'class': 'choice', 'target': 'classes', 'beam_size': 12, 'cheating': False, 'from': ['output_prob'], 'initial_output': 0}, 'end': {'class': 'compare', 'from': ['output'], 'value': 0}, 'target_embed': {'class': 'linear', 'activation': None, 'with_bias': Fals..., len = 7 | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetwork.py", line 760, in add_layer | |
line: layer = self._create_layer(name=name, layer_class=layer_class, **layer_desc) | |
locals: | |
layer = <not found> | |
self = <local> <TFNetwork 'root' train=False> | |
self._create_layer = <local> <bound method TFNetwork._create_layer of <TFNetwork 'root' train=False>> | |
name = <local> 'output', len = 6 | |
layer_class = <local> <class 'TFNetworkRecLayer.RecLayer'> | |
layer_desc = <local> {'cheating': False, 'unit': {'output': {'class': 'choice', 'target': 'classes', 'beam_size': 12, 'cheating': False, 'from': ['output_prob'], 'initial_output': 0}, 'end': {'class': 'compare', 'from': ['output'], 'value': 0}, 'target_embed': {'class': 'linear', 'activation': None, 'with_bias': Fals..., len = 7 | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetwork.py", line 709, in _create_layer | |
line: layer = layer_class(**layer_desc) | |
locals: | |
layer = <not found> | |
layer_class = <local> <class 'TFNetworkRecLayer.RecLayer'> | |
layer_desc = <local> {'cheating': False, 'unit': {'output': {'class': 'choice', 'target': 'classes', 'beam_size': 12, 'cheating': False, 'from': ['output_prob'], 'initial_output': 0}, 'end': {'class': 'compare', 'from': ['output'], 'value': 0}, 'target_embed': {'class': 'linear', 'activation': None, 'with_bias': Fals..., len = 10 | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetworkRecLayer.py", line 210, in __init__ | |
line: y = self._get_output_subnet_unit(self.cell) | |
locals: | |
y = <not found> | |
self = <local> <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])> | |
self._get_output_subnet_unit = <local> <bound method RecLayer._get_output_subnet_unit of <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])>> | |
self.cell = <local> <_SubnetworkRecCell of <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])>> | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetworkRecLayer.py", line 834, in _get_output_subnet_unit | |
line: output = cell.get_output(rec_layer=self) | |
locals: | |
output = <not found> | |
cell = <local> <_SubnetworkRecCell of <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])>> | |
cell.get_output = <local> <bound method _SubnetworkRecCell.get_output of <_SubnetworkRecCell of <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])>>> | |
rec_layer = <not found> | |
self = <local> <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])> | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetworkRecLayer.py", line 2252, in get_output | |
line: final_loop_vars = self._while_loop( | |
cond=cond, | |
body=body, | |
loop_vars=init_loop_vars, | |
shape_invariants=shape_invariants) | |
locals: | |
final_loop_vars = <not found> | |
self = <local> <_SubnetworkRecCell of <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])>> | |
self._while_loop = <local> <bound method _SubnetworkRecCell._while_loop of <_SubnetworkRecCell of <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])>>> | |
cond = <local> <function _SubnetworkRecCell.get_output.<locals>.cond at 0x7f9b1eed7950> | |
body = <local> <function _SubnetworkRecCell.get_output.<locals>.body at 0x7f9b1eed7ae8> | |
loop_vars = <not found> | |
init_loop_vars = <local> (<tf.Tensor 'output/rec/initial_i:0' shape=() dtype=int32>, ([<tf.Tensor 'output/rec/accum_att_weights/init_accum_att_weights_zeros:0' shape=(1, ?, 1) dtype=float32>, <tf.Tensor 'output/rec/att/init_att_zeros:0' shape=(?, 2048) dtype=float32>, <tf.Tensor 'output/rec/target_embed/init_target_embed... | |
shape_invariants = <local> (TensorShape([]), ([TensorShape([Dimension(None), Dimension(None), Dimension(1)]), TensorShape([Dimension(None), Dimension(2048)]), TensorShape([Dimension(None), Dimension(621)])], [[LSTMStateTuple(c=TensorShape([Dimension(None), Dimension(1000)]), h=TensorShape([Dimension(None), Dimension(1000)]..., _[0]: {len = 0} | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetworkRecLayer.py", line 1627, in _while_loop | |
line: return tf.while_loop( | |
cond=cond, | |
body=body, | |
loop_vars=loop_vars, | |
shape_invariants=shape_invariants, | |
back_prop=self.parent_rec_layer.back_prop) | |
locals: | |
tf = <global> <module 'tensorflow' from '/home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow/__init__.py'> | |
tf.while_loop = <global> <function while_loop at 0x7f9da476cae8> | |
cond = <local> <function _SubnetworkRecCell.get_output.<locals>.cond at 0x7f9b1eed7950> | |
body = <local> <function _SubnetworkRecCell.get_output.<locals>.body at 0x7f9b1eed7ae8> | |
loop_vars = <local> (<tf.Tensor 'output/rec/initial_i:0' shape=() dtype=int32>, ([<tf.Tensor 'output/rec/accum_att_weights/init_accum_att_weights_zeros:0' shape=(1, ?, 1) dtype=float32>, <tf.Tensor 'output/rec/att/init_att_zeros:0' shape=(?, 2048) dtype=float32>, <tf.Tensor 'output/rec/target_embed/init_target_embed... | |
shape_invariants = <local> (TensorShape([]), ([TensorShape([Dimension(None), Dimension(None), Dimension(1)]), TensorShape([Dimension(None), Dimension(2048)]), TensorShape([Dimension(None), Dimension(621)])], [[LSTMStateTuple(c=TensorShape([Dimension(None), Dimension(1000)]), h=TensorShape([Dimension(None), Dimension(1000)]..., _[0]: {len = 0} | |
back_prop = <not found> | |
self = <local> <_SubnetworkRecCell of <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])>> | |
self.parent_rec_layer = <local> <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])> | |
self.parent_rec_layer.back_prop = <local> False | |
File "/home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 3556, in while_loop | |
line: result = loop_context.BuildLoop(cond, body, loop_vars, shape_invariants, | |
return_same_structure) | |
locals: | |
result = <not found> | |
loop_context = <local> <tensorflow.python.ops.control_flow_ops.WhileContext object at 0x7f9b1eed8940> | |
loop_context.BuildLoop = <local> <bound method WhileContext.BuildLoop of <tensorflow.python.ops.control_flow_ops.WhileContext object at 0x7f9b1eed8940>> | |
cond = <local> <function _SubnetworkRecCell.get_output.<locals>.cond at 0x7f9b1eed7950> | |
body = <local> <function _SubnetworkRecCell.get_output.<locals>.body at 0x7f9b1eed7ae8> | |
loop_vars = <local> (<tf.Tensor 'output/rec/initial_i:0' shape=() dtype=int32>, ([<tf.Tensor 'output/rec/accum_att_weights/init_accum_att_weights_zeros:0' shape=(1, ?, 1) dtype=float32>, <tf.Tensor 'output/rec/att/init_att_zeros:0' shape=(?, 2048) dtype=float32>, <tf.Tensor 'output/rec/target_embed/init_target_embed... | |
shape_invariants = <local> (TensorShape([]), ([TensorShape([Dimension(None), Dimension(None), Dimension(1)]), TensorShape([Dimension(None), Dimension(2048)]), TensorShape([Dimension(None), Dimension(621)])], [[LSTMStateTuple(c=TensorShape([Dimension(None), Dimension(1000)]), h=TensorShape([Dimension(None), Dimension(1000)]..., _[0]: {len = 0} | |
return_same_structure = <local> False | |
File "/home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 3087, in BuildLoop | |
line: original_body_result, exit_vars = self._BuildLoop( | |
pred, body, original_loop_vars, loop_vars, shape_invariants) | |
locals: | |
original_body_result = <not found> | |
exit_vars = <not found> | |
self = <local> <tensorflow.python.ops.control_flow_ops.WhileContext object at 0x7f9b1eed8940> | |
self._BuildLoop = <local> <bound method WhileContext._BuildLoop of <tensorflow.python.ops.control_flow_ops.WhileContext object at 0x7f9b1eed8940>> | |
pred = <local> <function _SubnetworkRecCell.get_output.<locals>.cond at 0x7f9b1eed7950> | |
body = <local> <function _SubnetworkRecCell.get_output.<locals>.body at 0x7f9b1eed7ae8> | |
original_loop_vars = <local> (<tf.Tensor 'output/rec/initial_i:0' shape=() dtype=int32>, ([<tf.Tensor 'output/rec/accum_att_weights/init_accum_att_weights_zeros:0' shape=(1, ?, 1) dtype=float32>, <tf.Tensor 'output/rec/att/init_att_zeros:0' shape=(?, 2048) dtype=float32>, <tf.Tensor 'output/rec/target_embed/init_target_embed... | |
loop_vars = <local> [<tf.Tensor 'output/rec/initial_i:0' shape=() dtype=int32>, <tf.Tensor 'output/rec/accum_att_weights/init_accum_att_weights_zeros:0' shape=(1, ?, 1) dtype=float32>, <tf.Tensor 'output/rec/att/init_att_zeros:0' shape=(?, 2048) dtype=float32>, <tf.Tensor 'output/rec/target_embed/init_target_embed_c..., len = 8 | |
shape_invariants = <local> (TensorShape([]), ([TensorShape([Dimension(None), Dimension(None), Dimension(1)]), TensorShape([Dimension(None), Dimension(2048)]), TensorShape([Dimension(None), Dimension(621)])], [[LSTMStateTuple(c=TensorShape([Dimension(None), Dimension(1000)]), h=TensorShape([Dimension(None), Dimension(1000)]..., _[0]: {len = 0} | |
File "/home/ubuntu/tf1.13/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 3022, in _BuildLoop | |
line: body_result = body(*packed_vars_for_body) | |
locals: | |
body_result = <not found> | |
body = <local> <function _SubnetworkRecCell.get_output.<locals>.body at 0x7f9b1eed7ae8> | |
packed_vars_for_body = <local> (<tf.Tensor 'output/rec/while/Identity:0' shape=() dtype=int32>, ([<tf.Tensor 'output/rec/while/Identity_1:0' shape=(?, ?, 1) dtype=float32>, <tf.Tensor 'output/rec/while/Identity_2:0' shape=(?, 2048) dtype=float32>, <tf.Tensor 'output/rec/while/Identity_3:0' shape=(?, 621) dtype=float32>], [[LST... | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetworkRecLayer.py", line 2141, in body | |
line: outputs_flat = [ | |
maybe_transform(self.net.layers[k]).output.copy_compatible_to( | |
self.layer_data_templates[k].output).placeholder | |
for k in sorted(self._initial_outputs)] | |
locals: | |
outputs_flat = <not found> | |
maybe_transform = <local> <function _SubnetworkRecCell.get_output.<locals>.body.<locals>.maybe_transform at 0x7f9c3812f1e0> | |
self = <local> <_SubnetworkRecCell of <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])>> | |
self.net = <local> <TFNetwork 'root/output:rec-subnet' parent_layer=<RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])> train=False> | |
self.net.layers = <local> {'prev:end': <_TemplateLayer(CompareLayer)(:prev:compare) 'output/prev:end' out_type=Data(shape=(), dtype='bool', sparse=True, dim=2, time_dim_axis=None, batch_shape_meta=[B]) (construction stack None)>, ':i': <RecStepInfoLayer 'output/:i' out_type=Data(shape=(), dtype='int32', batch_dim_axis=Non..., len = 18 | |
k = <not found> | |
output = <not found> | |
output.copy_compatible_to = <not found> | |
self.layer_data_templates = <local> {'output': <_TemplateLayer(ChoiceLayer)(:template:choice) 'output/output' out_type=Data(shape=(), dtype='int32', sparse=True, dim=10025, time_dim_axis=None, batch_shape_meta=[B]) (construction stack None)>, 'end': <_TemplateLayer(CompareLayer)(:template:compare) 'output/end' out_type=Data(shape=(..., len = 16 | |
placeholder = <not found> | |
sorted = <builtin> <built-in function sorted> | |
self._initial_outputs = <local> {'accum_att_weights': <tf.Tensor 'output/rec/accum_att_weights/init_accum_att_weights_zeros:0' shape=(1, ?, 1) dtype=float32>, 'att': <tf.Tensor 'output/rec/att/init_att_zeros:0' shape=(?, 2048) dtype=float32>, 'target_embed': <tf.Tensor 'output/rec/target_embed/init_target_embed_const/Cast:0' sh... | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFNetworkRecLayer.py", line 2141, in <listcomp> | |
line: outputs_flat = [ | |
maybe_transform(self.net.layers[k]).output.copy_compatible_to( | |
self.layer_data_templates[k].output).placeholder | |
for k in sorted(self._initial_outputs)] | |
locals: | |
outputs_flat = <not found> | |
maybe_transform = <local> <function _SubnetworkRecCell.get_output.<locals>.body.<locals>.maybe_transform at 0x7f9c3812f1e0> | |
self = <local> <_SubnetworkRecCell of <RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])>> | |
self.net = <local> <TFNetwork 'root/output:rec-subnet' parent_layer=<RecLayer 'output' out_type=Data(shape=(None,), dtype='int32', sparse=True, dim=10025, batch_dim_axis=1, batch_shape_meta=[T|?,B])> train=False> | |
self.net.layers = <local> {'prev:end': <_TemplateLayer(CompareLayer)(:prev:compare) 'output/prev:end' out_type=Data(shape=(), dtype='bool', sparse=True, dim=2, time_dim_axis=None, batch_shape_meta=[B]) (construction stack None)>, ':i': <RecStepInfoLayer 'output/:i' out_type=Data(shape=(), dtype='int32', batch_dim_axis=Non..., len = 18 | |
k = <local> 'target_embed', len = 12 | |
output = <not found> | |
output.copy_compatible_to = <not found> | |
self.layer_data_templates = <local> {'output': <_TemplateLayer(ChoiceLayer)(:template:choice) 'output/output' out_type=Data(shape=(), dtype='int32', sparse=True, dim=10025, time_dim_axis=None, batch_shape_meta=[B]) (construction stack None)>, 'end': <_TemplateLayer(CompareLayer)(:template:compare) 'output/end' out_type=Data(shape=(..., len = 16 | |
placeholder = <not found> | |
sorted = <builtin> <built-in function sorted> | |
self._initial_outputs = <local> {'accum_att_weights': <tf.Tensor 'output/rec/accum_att_weights/init_accum_att_weights_zeros:0' shape=(1, ?, 1) dtype=float32>, 'att': <tf.Tensor 'output/rec/att/init_att_zeros:0' shape=(?, 2048) dtype=float32>, 'target_embed': <tf.Tensor 'output/rec/target_embed/init_target_embed_const/Cast:0' sh... | |
File "/home/ubuntu/manish/returnn-experiments/2018-asr-attention/librispeech/full-setup-attention/returnn/TFUtil.py", line 1218, in copy_compatible_to | |
line: raise ValueError("copy_compatible_to: self %r already has more dims than target data %r" % (self, data)) | |
locals: | |
ValueError = <builtin> <class 'ValueError'> | |
self = <local> Data(name='target_embed_output', shape=(None, 621), batch_shape_meta=[B,T|'time:var:extern_data:classes',F|621]) | |
data = <local> Data(name='target_embed_output', shape=(621,), time_dim_axis=None, batch_shape_meta=[B,F|621]) | |
ValueError: copy_compatible_to: self Data(name='target_embed_output', shape=(None, 621), batch_shape_meta=[B,T|'time:var:extern_data:classes',F|621]) already has more dims than target data Data(name='target_embed_output', shape=(621,), time_dim_axis=None, batch_shape_meta=[B,F|621]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment