Error on reproduce the aggregation experiments (step 3 of Reproducing experiments section)

[ducmanhnguyen]

Hi,

I am trying to reproducing the experiments with the blazeit system, the environment setup and data preprocessing went well, but when I tried to reproduce the aggregation experiments, it throws out some error. I tried to fix it many times but I can not solve it. Could you please help me somehow? Here is the step by step how did I run the experiment

Reproduce problem:

• Environment: prepared as requirements
• step 1: prepared jackson-town-square video and structure folders as the instruction. (succeed)
• step 2: Extract the videos into npy files by run command: python gen_small_vid.py --base_name jackson-town-square --date 2017-12-14 (succeed)
• step 3: run the aggregation experiments and it has failed and gave the errors as bellow:
  python blazeit/aggregation/run_counter.py --base_name jackson-town-square --train_date 2017-12-14 --thresh_date 2017-12-16 --test_date 2017-12-17 --objects car --no-load_video --out_csv csvs/jackson-town-square-2017-12-17.csv

Error:

Traceback (most recent call last):

File "run_counter.py", line 54, in
main()
File "run_counter.py", line 46, in main
load_video=args.load_video
File "/root/blazeit/blazeit/aggregation/counter.py", line 129, in train_and_test
spec.load_data(selection='balanced', nb_train=150000)
File "/root/blazeit/blazeit/specializers/base_specializer.py", line 155, in load_data
t1, t2 = self.get_train_val(**kwargs)
File "/root/blazeit/blazeit/specializers/base_specializer.py", line 149, in get_train_val
X_train, X_val = split(X, train_inds, val_inds)
File "/root/blazeit/blazeit/specializers/base_specializer.py", line 137, in split
return Z[train_inds], Z[val_inds]
File "/opt/conda/lib/python3.6/site-packages/numpy/core/memmap.py", line 331, in getitem
res = super(memmap, self).getitem(index)
IndexError: index 973488 is out of bounds for axis 0 with size 973488

After re-run step 3 a few time, the error above passed itself, then another error appears:

Traceback (most recent call last): | 0/8915 [00:00<?, ?it/s] File "blazeit/aggregation/run_counter.py", line 54, in
main()
File "blazeit/aggregation/run_counter.py", line 46, in main
load_video=args.load_video
File "/root/blazeit/blazeit/aggregation/counter.py", line 133, in train_and_test
spec.train(silent=True)
File "/root/blazeit/blazeit/aggregation/counter.py", line 18, in train
super().train(**kwargs, epochs=[1, 0], lrs=[0.001, 0.001])
File "/root/blazeit/blazeit/specializers/specializers.py", line 203, in train
self._train(criterion, metric='topk', **kwargs)
File "/root/blazeit/blazeit/specializers/base_specializer.py", line 206, in _train
run_epoch(lrs[0], epochs[0])
File "/root/blazeit/blazeit/specializers/base_specializer.py", line 198, in run_epoch
silent=silent)
File "/root/blazeit/blazeit/specializers/pytorch_utils.py", line 163, in trainer
train_epoch(train_loader, model, criterion, optimizer, epoch, metric, silent=silent)
File "/root/blazeit/blazeit/specializers/pytorch_utils.py", line 100, in train_epoch
output = model(input_var)
File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py", line 545, in call
result = self.forward(*input, **kwargs)
File "/root/blazeit/blazeit/specializers/resnet_simple.py", line 117, in forward
x = self.conv1(x)
File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py", line 545, in call
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 345, in forward
return self.conv2d_forward(input, self.weight)
File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 342, in conv2d_forward
self.padding, self.dilation, self.groups)
RuntimeError: Given groups=1, weight of size 16 3 3 3, expected input[16, 65, 3, 65] to have 3 channels, but got 65 channels instead

Then continue re-run a few time more, the first error appears again