Error While Using Test Recognizer.py On UCF101(Using Colab)After Extracting RGB Frames Only!

[lakshaymehra]

I ran: !python tools/test_recognizer.py configs/ucf101/tsn_rgb_bninception.py modelzoo/tsn_2d_rgb_bninception_seg3_f1s1_b32_g8-98160339.pth

Output(Error): Traceback (most recent call last): File "tools/test_recognizer.py", line 181, in main() File "tools/test_recognizer.py", line 140, in main raise NotImplementedError("By default, we use distributed testing, so that launcher should be pytorch") NotImplementedError: By default, we use distributed testing, so that launcher should be pytorch

Notes: I have installed all the required packages as mentioned in install.md Kindly help as soon as possible as I have been stuck here for more than a week... Thanks in advance!

[kennymckormick]

Sorry, that's because of the inconsistency in our last update. Now the testing command in GETTING_STARTED.md is updated, you can try the new command.

[lakshaymehra]

Thanks for your response.

I am running:

!bash ./tools/dist_test_recognizer.sh configs/ucf101/tsn_rgb_bninception.py tsn_2d_rgb_bninception_seg3_f1s1_b32_g8-98160339.pth 2

(I AM USING 2 SINCE RAM ON COLAB GETS PRETTY QUICKLY USED UP IF I SPECIFY 8)

However,I am getting this new error:

---

Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.

---

The model and loaded state dict do not match exactly

unexpected key in source state_dict: fc.weight, fc.bias

Traceback (most recent call last): File "./tools/test_recognizer.py", line 182, in main() File "./tools/test_recognizer.py", line 154, in main load_checkpoint(model, args.checkpoint, map_location='cpu') File "/usr/local/lib/python3.7/site-packages/mmcv-0.2.16-py3.7-linux-x86_64.egg/mmcv/runner/checkpoint.py", line 168, in load_checkpoint raise IOError('{} is not a checkpoint file'.format(filename)) OSError: tsn_2d_rgb_bninception_seg3_f1s1_b32_g8-98160339.pth is not a checkpoint file Traceback (most recent call last): File "./tools/test_recognizer.py", line 182, in main() File "./tools/test_recognizer.py", line 154, in main load_checkpoint(model, args.checkpoint, map_location='cpu') File "/usr/local/lib/python3.7/site-packages/mmcv-0.2.16-py3.7-linux-x86_64.egg/mmcv/runner/checkpoint.py", line 168, in load_checkpoint raise IOError('{} is not a checkpoint file'.format(filename)) OSError: tsn_2d_rgb_bninception_seg3_f1s1_b32_g8-98160339.pth is not a checkpoint file Traceback (most recent call last): File "/usr/local/lib/python3.7/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/usr/local/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/usr/local/lib/python3.7/site-packages/torch/distributed/launch.py", line 263, in main() File "/usr/local/lib/python3.7/site-packages/torch/distributed/launch.py", line 259, in main cmd=cmd) subprocess.CalledProcessError: Command '['/usr/local/bin/python', '-u', './tools/test_recognizer.py', '--local_rank=1', 'configs/ucf101/tsn_rgb_bninception.py', 'tsn_2d_rgb_bninception_seg3_f1s1_b32_g8-98160339.pth', '--launcher', 'pytorch']' died with <Signals.SIGSEGV: 11>.

[kennymckormick]

Hi, lakshaymehra, Seems that you haven't downloaded the checkpoint file yet, please first download it with link in model zoo.

[lakshaymehra]

Hi,thanks for the response.

There was a problem with the directory in which the checkpoint file was saved but I rectified it.

However,even after testing is completed,there is an error being displayed.Can you tell me how it can be rectified?

!bash ./tools/dist_test_recognizer.sh configs/ucf101/tsn_rgb_bninception.py tsn_2d_rgb_bninception_seg3_f1s1_b32_g8-98160339.pth 1

The model and loaded state dict do not match exactly

unexpected key in source state_dict: fc.weight, fc.bias

rank 0, data_batch 0 rank 0, begin collect results rank 0 begin dump rank 0 finished dump writing results to default.pkl Averaging score over 1 clips without softmax (ie, raw) Mean Class Accuracy = 66.67 Top-1 Accuracy = 65.00 Top-5 Accuracy = 100.00 Traceback (most recent call last): File "/usr/local/lib/python3.7/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/usr/local/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/usr/local/lib/python3.7/site-packages/torch/distributed/launch.py", line 263, in main() File "/usr/local/lib/python3.7/site-packages/torch/distributed/launch.py", line 259, in main cmd=cmd) subprocess.CalledProcessError: Command '['/usr/local/bin/python', '-u', 'tools/test_recognizer.py', '--local_rank=0', 'configs/ucf101/tsn_rgb_bninception.py', 'modelzoo/tsn_2d_rgb_bninception_seg3_f1s1_b32_g8-98160339.pth', '--launcher', 'pytorch']' died with <Signals.SIGSEGV: 11>.

[kennymckormick]

I didn't get this error on my linux machine. You can try this codabase on a linux machine to see if this error still exists.