Torch-pruning

* Bugfix for reshape, view, flatten and nn.Parameter.
* Pre-trained models for CIFAR benchmark.

* Complete support for widely used normalization layers: Batch Normalization, Instance Normalization, Layer Normalization, and Group Normalization.
* Covers 90.6% of the models in Torchvision v0.13.1.
* Improved compatibility with PyTorch<=1.8.
* Bugfix in GroupNormPruner and Benchmark

* Automatic pruning of unwrapped ``nn.Parameter`` from non-standard layers.
* Bugfix (https://github.com/VainF/Torch-Pruning/issues/135, https://github.com/VainF/Torch-Pruning/discussions/124, ...)

1. Torchvision Compatibility: https://github.com/VainF/Torch-Pruning/tree/master/benchmarks/prunability
2. Reshape Support: Support for common reshape operations like ``.view``, ``.reshape``, and ``.flatten``.
3. User-Friendly Interfaces: Easy-to-use interfaces for users of varying skill levels.
4. Robustness: Improve the robustness of Torch-Pruning
5. Yolov7: https://github.com/VainF/Torch-Pruning/tree/master/benchmarks/prunability/yolov7_detect_pruned.py
6. Bugfix

**Features:**
* Channel pruning for [CNNs](tests/test_torchvision_models.py) (e.g. ResNet, DenseNet, Deeplab) and [Transformers](tests/test_torchvision_models.py) (e.g. ViT)
* High-level pruners: MagnitudePruner, BNScalePruner, GroupPruner, etc.
* Graph Tracing and dependency fixing.
* Supported modules: Conv, Linear, BatchNorm, LayerNorm, Transposed Conv, PReLU, Embedding, MultiheadAttention, nn.Parameters and [customized modules](tests/test_customized_layer.py).
* Supported operations: split, concatenation, skip connection, flatten, etc.
* Pruning strategies: Random, L1, L2, etc.
* Low-level pruning [functions](torch_pruning/prune/structured.py)
* [Benchmarks](benchmarks) and [tutorials](tutorials)