We lifted 5 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| jhjacobsen/pytorch-i-revnet | canonical | 5 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| get_hms | Ran | jhjacobsen/pytorch-i-revnet/models/utils_cifar.py code served (permissive licence) · get_code("bb104479d26e39c3") |
| learning_rate | Ran | jhjacobsen/pytorch-i-revnet/models/utils_cifar.py code served (permissive licence) · get_code("947a620765d795b2") |
| merge | Ran | jhjacobsen/pytorch-i-revnet/models/model_utils.py code served (permissive licence) · get_code("2d15f050207aff53") |
| split | Ran | jhjacobsen/pytorch-i-revnet/models/model_utils.py code served (permissive licence) · get_code("781553d9de1bec97") |
| test | Ran | jhjacobsen/pytorch-i-revnet/models/utils_cifar.py code served (permissive licence) · get_code("dab1f482d324fc51") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
It is widely believed that the success of deep convolutional networks is based on progressively discarding uninformative variability about the input with respect to the problem at hand. This is supported empirically by the difficulty of recovering images from their hidden representations, in most commonly used network architectures. In this paper we show via a one-to-one mapping that this loss of information is not a necessary condition to learn representations that generalize well on complicated problems, such as ImageNet. Via a cascade of homeomorphic layers, we build the i-RevNet, a network that can be fully inverted up to the final projection onto the classes, i.e. no information is discarded. Building an invertible architecture is difficult, for one, because the local inversion is ill-conditioned, we overcome this by providing an explicit inverse. An analysis of i-RevNets learned representations suggests an alternative explanation for the success of deep networks by a progressive contraction and linear separation with depth. To shed light on the nature of the model learned by the i-RevNet we reconstruct linear interpolations between natural image representations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1802.07088")
get_code_for_paper("1802.07088")
have("1802.07088")
Connect an agent — have() is free.