Add pretrained weights for raft_small from original paper

[NicolasHug]

Towards #4644

This PR adds pretrained weights for raft-small from the original paper (raft-small.pth).

I will override the default weights with outs later (likely tomorrow) when the training is finished.

both --weights Raft_Small_Weights.C_T_V1 and --pretrained work properly:

(raft) ➜  vision git:(raft_pretrained_CT_small) ✗ torchrun --nproc_per_node 8 --nnodes 1 references/optical_flow/train.py --val-dataset sintel --batch-size 10 --dataset-root /data/home/nicolashug/cluster/work/downloads --model raft_small --weights Raft_Small_Weights.C_T_V1

Batch-processed 1040 / 1041 samples. Going to process the remaining samples individually, if any.
Sintel val clean epe: 2.1208	1px: 0.8486	3px: 0.9305	5px: 0.9498	per_image_epe: 2.1236	f1: 6.6777
Sintel val final Total time: 0:00:09
Batch-processed 1040 / 1041 samples. Going to process the remaining samples individually, if any.
Sintel val final epe: 3.2727	1px: 0.8075	3px: 0.8969	5px: 0.9225	per_image_epe: 3.2617	f1: 9.9382

Conversion code for ref:

def map_orig_to_ours_small(orig, mine=None):
    # TODO: remove
    d = {}
    used_s_orig = set()
    used_s_mine = set()

    def assert_and_add(s_orig, s_mine):
        # print(s_orig, s_mine)
        # print(orig[s_orig].shape, mine[s_mine].shape)

        assert s_orig not in used_s_orig, s_orig
        assert s_mine not in used_s_mine, s_mine

        if mine is not None:
            assert s_mine in mine, s_mine
        assert s_orig in orig
        if mine is not None:
            assert orig[s_orig].shape == mine[s_mine].shape
        d[s_mine] = orig[s_orig]
        used_s_orig.add(s_orig)
        used_s_mine.add(s_mine)
    
    for a, b in zip(orig, mine):
        assert_and_add(a, b)

    if mine is not None:
        print(len(d), len(orig), len(mine))
        assert not (set(mine.keys()) - set(d.keys()))
    return d

cc @datumbox

[facebook-github-bot]

💊 CI failures summary and remediations

As of commit 55d1cde (more details on the Dr. CI page):

---

• 1/1 failures introduced in this PR

---

🕵️ 1 new failure recognized by patterns

The following CI failures do not appear to be due to upstream breakages:

unittest_linux_cpu_py3.8 (1/1)

Step: "Run tests" (full log | diagnosis details | 🔁 rerun)

/root/project/torchvision/io/video.py:399: Runt...log: [mov,mp4,m4a,3gp,3g2,mj2] moov atom not found

test/test_internet.py::TestDatasetUtils::test_download_url_dont_exist
  /root/project/env/lib/python3.8/site-packages/_pytest/fixtures.py:928: ResourceWarning: unclosed <ssl.SSLSocket [closed] fd=13, family=AddressFamily.AF_INET, type=SocketKind.SOCK_STREAM, proto=6>
    finalizer = functools.partial(_teardown_yield_fixture, fixturefunc, generator)

test/test_internet.py::TestDatasetUtils::test_download_url_dont_exist
  /root/project/env/lib/python3.8/site-packages/_pytest/fixtures.py:928: ResourceWarning: unclosed <ssl.SSLSocket [closed] fd=14, family=AddressFamily.AF_INET, type=SocketKind.SOCK_STREAM, proto=6>
    finalizer = functools.partial(_teardown_yield_fixture, fixturefunc, generator)

test/test_io.py::TestVideo::test_read_video_timestamps_corrupted_file
  /root/project/torchvision/io/video.py:399: RuntimeWarning: Failed to open container for /tmp/tmp5ufjmbrm.mp4; Caught error: [Errno 1094995529] Invalid data found when processing input: '/tmp/tmp5ufjmbrm.mp4'; last error log: [mov,mp4,m4a,3gp,3g2,mj2] moov atom not found
    warnings.warn(msg, RuntimeWarning)

test/test_models.py::test_memory_efficient_densenet[densenet121]
test/test_models.py::test_memory_efficient_densenet[densenet169]
test/test_models.py::test_memory_efficient_densenet[densenet201]
test/test_models.py::test_memory_efficient_densenet[densenet161]
  /root/project/env/lib/python3.8/site-packages/torch/autocast_mode.py:162: UserWarning: User provided device_type of 'cuda', but CUDA is not available. Disabling
    warnings.warn('User provided device_type of \'cuda\', but CUDA is not available. Disabling')

test/test_models.py::test_inception_v3_eval

---

This comment was automatically generated by Dr. CI (expand for details).

Please report bugs/suggestions to the (internal) Dr. CI Users group.

Click here to manually regenerate this comment.

[datumbox]

LGTM, thanks!