def test_jit(self, device, dtype): B, C, H, W = 1, 1, 32, 32 patches = torch.rand(B, C, H, W, device=device, dtype=dtype) patches2x = resize(patches, (48, 48)) input = {"image0": patches, "image1": patches2x} model = LoFTR().to(patches.device, patches.dtype).eval() model_jit = torch.jit.script(model) out = model(input) out_jit = model_jit(input) for k, v in out.items(): assert_close(v, out_jit[k])
def test_gradcheck(self, device): patches = torch.rand(1, 1, 32, 32, device=device) patches05 = resize(patches, (48, 48)) patches = utils.tensor_to_gradcheck_var(patches) # to var patches05 = utils.tensor_to_gradcheck_var(patches05) # to var loftr = LoFTR().to(patches.device, patches.dtype) def proxy_forward(x, y): return loftr.forward({"image0": x, "image1": y})["keypoints0"] assert gradcheck(proxy_forward, (patches, patches05), eps=1e-4, atol=1e-4, raise_exception=True)
def test_jit(self, device, dtype): B, C, H, W = 1, 1, 32, 32 patches = torch.rand(B, C, H, W, device=device, dtype=dtype) patches2x = resize(patches, (48, 48)) inputs = {"image0": patches, "image1": patches2x} model = LocalFeatureMatcher(SIFTDescriptor(32), DescriptorMatcher('snn', 0.8)).to(device).eval() model_jit = torch.jit.script(model) out = model(inputs) out_jit = model_jit(inputs) for k, v in out.items(): assert_close(v, out_jit[k])
def test_gradcheck(self, device): matcher = LocalFeatureMatcher(SIFTFeature(5), DescriptorMatcher('nn', 1.0)).to(device) patches = torch.rand(1, 1, 32, 32, device=device) patches05 = resize(patches, (48, 48)) patches = utils.tensor_to_gradcheck_var(patches) # to var patches05 = utils.tensor_to_gradcheck_var(patches05) # to var def proxy_forward(x, y): return matcher({"image0": x, "image1": y})["keypoints0"] assert gradcheck(proxy_forward, (patches, patches05), eps=1e-4, atol=1e-4, raise_exception=True)
def forward(self, x): return geometry.resize(x[None], self.size)[0]
def forward(self, data: dict) -> Dict[str, torch.Tensor]: """ Args: data: dictionary containing the input data in the following format: Keyword Args: image0: left image with shape :math:`(N, 1, H1, W1)`. image1: right image with shape :math:`(N, 1, H2, W2)`. mask0 (optional): left image mask. '0' indicates a padded position :math:`(N, H1, W1)`. mask1 (optional): right image mask. '0' indicates a padded position :math:`(N, H2, W2)`. Returns: - ``keypoints0``, matching keypoints from image0 :math:`(NC, 2)`. - ``keypoints1``, matching keypoints from image1 :math:`(NC, 2)`. - ``confidence``, confidence score [0, 1] :math:`(NC)`. - ``batch_indexes``, batch indexes for the keypoints and lafs :math:`(NC)`. """ # 1. Local Feature CNN data.update({ 'bs': data['image0'].size(0), 'hw0_i': data['image0'].shape[2:], 'hw1_i': data['image1'].shape[2:] }) if data['hw0_i'] == data['hw1_i']: # faster & better BN convergence feats_c, feats_f = self.backbone(torch.cat([data['image0'], data['image1']], dim=0)) (feat_c0, feat_c1), (feat_f0, feat_f1) = feats_c.split(data['bs']), feats_f.split(data['bs']) else: # handle different input shapes (feat_c0, feat_f0), (feat_c1, feat_f1) = self.backbone(data['image0']), self.backbone(data['image1']) data.update({ 'hw0_c': feat_c0.shape[2:], 'hw1_c': feat_c1.shape[2:], 'hw0_f': feat_f0.shape[2:], 'hw1_f': feat_f1.shape[2:] }) # 2. coarse-level loftr module # add featmap with positional encoding, then flatten it to sequence [N, HW, C] # feat_c0 = rearrange(self.pos_encoding(feat_c0), 'n c h w -> n (h w) c') # feat_c1 = rearrange(self.pos_encoding(feat_c1), 'n c h w -> n (h w) c') feat_c0 = self.pos_encoding(feat_c0).permute(0, 2, 3, 1) n, h, w, c = feat_c0.shape feat_c0 = feat_c0.reshape(n, -1, c) feat_c1 = self.pos_encoding(feat_c1).permute(0, 2, 3, 1) n1, h1, w1, c1 = feat_c1.shape feat_c1 = feat_c1.reshape(n1, -1, c1) mask_c0 = mask_c1 = None # mask is useful in training if 'mask0' in data: mask_c0 = resize(data['mask0'], data['hw0_c'], interpolation='nearest').flatten(-2) if 'mask1' in data: mask_c1 = resize(data['mask1'], data['hw1_c'], interpolation='nearest').flatten(-2) feat_c0, feat_c1 = self.loftr_coarse(feat_c0, feat_c1, mask_c0, mask_c1) # 3. match coarse-level self.coarse_matching(feat_c0, feat_c1, data, mask_c0=mask_c0, mask_c1=mask_c1) # 4. fine-level refinement feat_f0_unfold, feat_f1_unfold = self.fine_preprocess(feat_f0, feat_f1, feat_c0, feat_c1, data) if feat_f0_unfold.size(0) != 0: # at least one coarse level predicted feat_f0_unfold, feat_f1_unfold = self.loftr_fine(feat_f0_unfold, feat_f1_unfold) # 5. match fine-level self.fine_matching(feat_f0_unfold, feat_f1_unfold, data) rename_keys: Dict[str, str] = {"mkpts0_f": 'keypoints0', "mkpts1_f": 'keypoints1', "mconf": 'confidence', "b_ids": 'batch_indexes'} out = {} for k, v in rename_keys.items(): out[v] = data[k] return out