Assertion failure when running vanilla train_nav.py

[thomason-jesse]

I'm running into an assertion error when running the train_nav.py

I'm able to train VQA models, but when I run train_nav.py (after setting the -target_obj_conn_map_dir to the appropriate path on my system), the code starts training on the first epoch, reaching about 2% before failing an assertion in training/data.py.

The issued command matches the github example:

python train_nav.py -to_log 1 -model_type pacman -identifier pacman

I sort of assume I have failed to download or move some specific file, but as far as I can tell everything checks out, so I thought it could be a bug from the changes you guys have been making recently.

Let me know what you think; I'd really appreciate it so we can get the system running!

[ZhuFengdaaa]

Me too !

[ZhuFengdaaa]

I use this function and replace default fn here to get rid of bad data. But I found that the peak performance is reached at the end of 2nd epoch(epoch 1 with d_D_50=1.36). After that, performance drops to e.g, epoch 6, d_D_50=1.22

[satyenrajpal]

@ZhuFengdaaa, thanks so much for that! By d_D_50, you mean \Delta d_50, right?

If that's the case, 1.36 is not matching with the values reported in the paper (2.38). Did you manage to get the reported values?

[JethroJC]

Hi~I meet the same error. Do you solve the problem?

[JethroJC]

@ZhuFengdaaa , thanks so much for that. I follow your change, but I still get this error. Could you please give me some advice? Thanks!

[maa04]

Found some mismatches in eqa_v1.json which leads to an AssertionError.
( Dataset: SUNCG v1 )
But older dataset from SUNCG v1 is OK.
So weird ...
E.g
House "177a757c438abc52c6f98af76b0aa630"
eqa_v1.json:

...
{
"type": "room",
"box": {
"min": [
45.075262664364345,
-3.197442239452046e-16,
27.69499938096851 <===
],
"max": [
49.394998895935714,
2.739999938756229,
35.08999921567738
]
},
"name": [
"bedroom"
],
"target": false
}
...

house.json

...
{
"id": "0_70",
"type": "Room",
"valid": 1,
"modelId": "fr_0rm_70",
"nodeIndices": [
63,
83,
88,
90,
91,
92,
93,
94,
95,
96,
97,
98,
105,
106,
110
],
"roomTypes": [
"Bedroom"
],
"bbox": {
"min": [
45.075262664364345,
-3.197442239452046e-16,
28.425263036520846 <===
],
"max": [
49.394998895935714,
2.739999938756229,
35.08999921567738
]
}
...

[yuanlixian]

I met the same assertion errors here too.
The weird thing here is that I can run the train_nav.py, but when I try to run the train_eqa.py, this assertion error shows up.

Any suggestions?

[maa04]

I met the same assertion errors here too.
The weird thing here is that I can run the train_nav.py, but when I try to run the train_eqa.py, this assertion error shows up.

Any suggestions?

Surprise! Try SUNCG_v0!

[yuanlixian]

I met the same assertion errors here too.
The weird thing here is that I can run the train_nav.py, but when I try to run the train_eqa.py, this assertion error shows up.
Any suggestions?

Surprise! Try SUNCG_v0!

I think my dataset version is v0. I don't know what actually went wrong.