Mismatched parameters between loaded and populated

[avi-otterai]

When trying to either test or predict, I run into the an error. I'm new to DyNet but something similar happens here: clab/dynet#1221 to which @neubig suggests:

This sort of error normally happens when you have a different model defined at training and test time. I'd make sure that you're calling exactly the same constructor code during training and test.

ERROR:

---

Reading model from logs/fn1.7-pretrained-targetid/best-targetid-1.7-model ...
Traceback (most recent call last):
File "/usr/lib64/python2.7/runpy.py", line 162, in _run_module_as_main
"main", fname, loader, pkg_name)
File "/usr/lib64/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/nas/home/thawani/MCS/open-sesame/sesame/targetid.py", line 431, in
model.populate(model_file_name)
File "_dynet.pyx", line 1461, in _dynet.ParameterCollection.populate
File "_dynet.pyx", line 1516, in _dynet.ParameterCollection.populate_from_textfile
RuntimeError: Number of parameter/lookup parameter objects loaded from file (20/4) did not match number to be populated (20/5)

---

Here's the log before the error:

---

[dynet] random seed: 1798024527
[dynet] allocating memory: 512MB
[dynet] memory allocation done.
DATA_DIRECTORY: data/
DEBUG_MODE: False
EMBEDDINGS_FILE: data/glove.6B.100d.txt
VERSION: 1.7

---

COMMAND: /nas/home/thawani/MCS/open-sesame/sesame/targetid.py --mode predict --model_name fn1.7-pretrained-targetid --raw_input raw.txt
MODEL FOR TEST / PREDICTION: logs/fn1.7-pretrained-targetid/best-targetid-1.7-model
PARSING MODE: predict

---

Reading data/neural/fn1.7/fn1.7.fulltext.train.syntaxnet.conll ...
#examples in data/neural/fn1.7/fn1.7.fulltext.train.syntaxnet.conll : 19391 in 3413 sents
#examples with missing arguments : 526
Combined 19391 instances in data into 3413 instances.

Reading the lexical unit index file: data/fndata-1.7/luIndex.xml
#unique targets = 9421
#total targets = 13572
#targets with multiple LUs = 4151
#max LUs per target = 5

Reading pretrained embeddings from data/glove.6B.100d.txt ...

PARSER SETTINGS (see logs/fn1.7-pretrained-targetid/configuration.json)

---

DEV_EVAL_EPOCH_FREQUENCY: 3
DROPOUT_RATE: 0.01
EVAL_AFTER_EVERY_EPOCHS: 100
HIDDEN_DIM: 100
LEMMA_DIM: 100
LSTM_DEPTH: 2
LSTM_DIM: 100
LSTM_INPUT_DIM: 100
NUM_EPOCHS: 100
PATIENCE: 25
POS_DIM: 100
PRETRAINED_EMBEDDING_DIM: 100
TOKEN_DIM: 100
TRAIN: data/neural/fn1.7/fn1.7.fulltext.train.syntaxnet.conll
UNK_PROB: 0.1
USE_DROPOUT: True

#Tokens = 400574
Unseen in dev/test = 0
Unlearnt in dev/test = 390524
#POS tags = 45
Unseen in dev/test = 0
Unlearnt in dev/test = 1
#Lemmas = 9349
Unseen in dev/test = 2
Unlearnt in dev/test = 3

---

Command:
python -m sesame.targetid --mode predict --model_name fn1.7-pretrained-targetid --raw_input raw.txt

---

[MartenPostma]

I'm experiencing the same issue. Did you find out how to resolve the problem?

[MartenPostma]

What worked for me was training the model longer!

[avi-otterai]

Not yet. Thanks for the workaround!