What environment is the best to run test.py?

[nfs2119]

I did successfully train the model by connecting it with my dataset from fsoco website. When I run test.py to test the weights model after 20,000 iterations it gives the following error, which I tried to resolve the error using the issue #444. But still this error comes up:

---

/home/vikram/anaconda3/lib/python3.11/site-packages/torch/init.py:614: UserWarning: torch.set_default_tensor_type() is deprecated as of PyTorch 2.1, please use torch.set_default_dtype() and torch.set_default_device() as alternatives. (Triggered internally at ../torch/csrc/tensor/python_tensor.cpp:451.)
_C._set_default_tensor_type(t)
/home/vikram/thesis/ssd.pytorch/ssd.py:34: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
self.priors = Variable(self.priorbox.forward(), volatile=True)
Finished loading model!
Testing image 1/57....
Traceback (most recent call last):
File "/home/vikram/thesis/ssd.pytorch/test.py", line 97, in
test_voc()
File "/home/vikram/thesis/ssd.pytorch/test.py", line 92, in test_voc
test_net(args.save_folder, net, args.cuda, testset,
File "/home/vikram/thesis/ssd.pytorch/test.py", line 56, in test_net
y = net(x) # forward pass
^^^^^^
File "/home/vikram/anaconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vikram/anaconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vikram/thesis/ssd.pytorch/ssd.py", line 101, in forward
output = self.detect.apply(self.num_classes, 0, 200, 0.01, 0.45,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vikram/anaconda3/lib/python3.11/site-packages/torch/autograd/function.py", line 539, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: Detect.forward() takes 4 positional arguments but 9 were given
(base) vikram@vikram-OMEN:~/thesis/ssd.pytorch$

---

Now according to my research, I need a specific pytorch or torch or torchvision version. Can somebody help me in understanding which environment works best to test or evaluate my results? I have created the new environment but am stuck on setup.