PermuteTransform

class torchrl.envs.transforms.PermuteTransform(dims, in_keys=None, out_keys=None, in_keys_inv=None, out_keys_inv=None)

排列變換。

沿著所需維度排列輸入張量。排列必須沿特徵維度（而非批次維度）提供。

引數:

• dims (list of int) – 維度的排列順序。必須是 dims [-(len(dims)), ..., -1] 的重排。

• in_keys (list of NestedKeys) – 輸入條目（讀取）。

• out_keys (list of NestedKeys) – 輸入條目（寫入）。如果未提供，則預設為 in_keys。

• in_keys_inv (list of NestedKeys) – 在 inv() 呼叫期間的輸入條目（讀取）。

• out_keys_inv (list of NestedKeys) – 在 inv() 呼叫期間的輸入條目（寫入）。如果未提供，則預設為 in_keys_in。

示例

>>> from torchrl.envs.libs.gym import GymEnv
>>> base_env = GymEnv("ALE/Pong-v5")
>>> base_env.rollout(2)
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([2, 6]), device=cpu, dtype=torch.int64, is_shared=False),
        done: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        next: TensorDict(
            fields={
                done: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                pixels: Tensor(shape=torch.Size([2, 210, 160, 3]), device=cpu, dtype=torch.uint8, is_shared=False),
                reward: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
            batch_size=torch.Size([2]),
            device=cpu,
            is_shared=False),
        pixels: Tensor(shape=torch.Size([2, 210, 160, 3]), device=cpu, dtype=torch.uint8, is_shared=False)},
    batch_size=torch.Size([2]),
    device=cpu,
    is_shared=False)
>>> env = TransformedEnv(base_env, PermuteTransform((-1, -3, -2), in_keys=["pixels"]))
>>> env.rollout(2)  # channels are at the end
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([2, 6]), device=cpu, dtype=torch.int64, is_shared=False),
        done: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        next: TensorDict(
            fields={
                done: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                pixels: Tensor(shape=torch.Size([2, 3, 210, 160]), device=cpu, dtype=torch.uint8, is_shared=False),
                reward: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
            batch_size=torch.Size([2]),
            device=cpu,
            is_shared=False),
        pixels: Tensor(shape=torch.Size([2, 3, 210, 160]), device=cpu, dtype=torch.uint8, is_shared=False)},
    batch_size=torch.Size([2]),
    device=cpu,
    is_shared=False)

transform_input_spec(input_spec: TensorSpec) → TensorSpec

轉換輸入規範，使結果規範與轉換對映匹配。

引數:

input_spec (TensorSpec) – 轉換前的規範

返回:

轉換後的預期規範

transform_observation_spec(observation_spec: TensorSpec) → TensorSpec

轉換觀察規範，使結果規範與轉換對映匹配。

引數:

observation_spec (TensorSpec) – 轉換前的規範

返回:

轉換後的預期規範