Hey guys, I’m trying to get an intermediate feature extractor with the depth anything model. My code looks like this:
self.image_processor = AutoImageProcessor.from_pretrained(“LiheYoung/depth-anything-small-hf”)
model = AutoModelForDepthEstimation.from_pretrained(“LiheYoung/depth-anything-small-hf”)
model.eval()
self.feature_extractor = create_feature_extractor(model.neck,{‘fusion_stage’:‘layers’})
I got this error :
self.feature_extractor = create_feature_extractor(model.neck,{‘fusion_stage’:‘layers’})
*** ValueError: hidden_states should be a tuple or list of tensors
Model architecture looks like this:
DepthAnythingNeck(
(reassemble_stage): DepthAnythingReassembleStage(
(layers): ModuleList(
(0): DepthAnythingReassembleLayer(
(projection): Conv2d(384, 48, kernel_size=(1, 1), stride=(1, 1))
(resize): ConvTranspose2d(48, 48, kernel_size=(4, 4), stride=(4, 4))
)
(1): DepthAnythingReassembleLayer(
(projection): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1))
(resize): ConvTranspose2d(96, 96, kernel_size=(2, 2), stride=(2, 2))
)
(2): DepthAnythingReassembleLayer(
(projection): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1))
(resize): Identity()
)
(3): DepthAnythingReassembleLayer(
(projection): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1))
(resize): Conv2d(384, 384, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
)
)
)
(convs): ModuleList(
(0): Conv2d(48, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): Conv2d(96, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(2): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(3): Conv2d(384, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(fusion_stage): DepthAnythingFeatureFusionStage(
(layers): ModuleList(
(0-3): 4 x DepthAnythingFeatureFusionLayer(
(projection): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
(residual_layer1): DepthAnythingPreActResidualLayer(
(activation1): ReLU()
(convolution1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(activation2): ReLU()
(convolution2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(residual_layer2): DepthAnythingPreActResidualLayer(
(activation1): ReLU()
(convolution1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(activation2): ReLU()
(convolution2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
)
)
)
Any feedback is appreciated
