miffyli/minecraft-bc-2020

Behavioural cloning solution to MineRL2020 competition

minecraft-bc-2020's Issues

Issue in the middle of training

Hello! Again, thanks for releasing this code!
I got this error in the middle of training:

l.data.data_pipeline[246001] DEBUG Loading from file data/MineRLObtainIronPickaxeVectorObf-v0/v3_red_guava_merman-2_181-16308
store: 23941it [25:12, 15.83it/s]
post-process: 100%|████████████████| 1981888/1981888 [20:11<00:00, 1636.03it/s]
1981888 experiences moved into hdf5 file
100%|██████████████████████████████| 1981888/1981888 [19:07<00:00, 1726.80it/s]
Original num of samples: 1981888
New num of samples: 917409
dataset: 60%|███████████████████▊ | 9/15 [24:11<17:55, 179.18s/it]Skipping episodes/episode_starts. Has different amount of samples than expected.
dataset: 93%|█████████████████████████████▊ | 14/15 [41:07<03:01, 181.33s/it]Skipping vector_centroids. Has different amount of samples than expected.
dataset: 100%|████████████████████████████████| 15/15 [41:07<00:00, 164.52s/it]
Steps 0 Time 1 Avrg loss 7.75259
train: 0%| | 8246/3669636 [08:20<61:43:01, 16.48it/s]
Traceback (most recent call last):
File "train.py", line 110, in
main()
File "train.py", line 107, in main
main_train_bc(parsed_args, remaining_args)
File "/home/daniel/Desktop/minecraft-bc-2020/train_bc_lstm.py", line 203, in main
network_output, new_states = network(pov, obs_vector, hidden_states=hidden_states, return_sequence=True)
File "/home/daniel/anaconda3/envs/minerl/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/daniel/Desktop/minecraft-bc-2020/torch_codes/modules.py", line 347, in forward
x = self.cnn_head(x)
File "/home/daniel/anaconda3/envs/minerl/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/daniel/Desktop/minecraft-bc-2020/torch_codes/modules.py", line 107, in forward
x = self.blocks(x)
File "/home/daniel/anaconda3/envs/minerl/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/daniel/anaconda3/envs/minerl/lib/python3.6/site-packages/torch/nn/modules/container.py", line 117, in forward
input = module(input)
File "/home/daniel/anaconda3/envs/minerl/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/daniel/anaconda3/envs/minerl/lib/python3.6/site-packages/torch/nn/modules/pooling.py", line 155, in forward
self.return_indices)
File "/home/daniel/anaconda3/envs/minerl/lib/python3.6/site-packages/torch/_jit_internal.py", line 267, in fn
return if_false(*args, **kwargs)
File "/home/daniel/anaconda3/envs/minerl/lib/python3.6/site-packages/torch/nn/functional.py", line 586, in _max_pool2d
input, kernel_size, stride, padding, dilation, ceil_mode)
RuntimeError: non-empty 3D or 4D input tensor expected but got ndim: 4

I do not know what could be causing this error :/

Issue while training

Hello, thank you for releasing this wonderful code!

I have an issue during training, that I did not manage to work around:

AssertionError: Batch size 32 can not be larger than number of episodes 3
Exception ignored in: <bound method HDF5SequenceSampler.del of <dataloaders.hdf5_loader.HDF5SequenceSampler object at 0x7f1bf5c8fcf8>>
Traceback (most recent call last):
File "/home/daniel/Desktop/minecraft-bc-2020/dataloaders/hdf5_loader.py", line 424, in del
self.close()
File "/home/daniel/Desktop/minecraft-bc-2020/dataloaders/hdf5_loader.py", line 419, in close
self.task_queue.close()
AttributeError: 'HDF5SequenceSampler' object has no attribute 'task_queue'

Apparently, the number of episodes is decreasing, and if it is smaller than the batch size, it breaks :/