Help with Configuration File and Issue with Input Pathway Dimensions

Hello everyone,

I have been trying to utilize the SlowFast library for a project, but have been encountering some difficulties with understanding the configuration file and resolving an input pathway dimensions error.

My project involves using a series of .avi videos from surveillance cameras for classification. The challenge here is that the videos come in different sizes. An additional piece of information is that each video I am working with is a clip of 150 frames.

Following [this guide](https://github.com/facebookresearch/SlowFast/issues/149#issuecomment-723265461), I adjusted the configuration settings and the data accordingly. However, I am met with the following error:

`AssertionError: Input pathway dimensions are not consistent. 1 2 2 2 2`

This is my current configuration:

```
TRAIN:
ENABLE: True
DATASET: mydata
BATCH_SIZE: 2
EVAL_PERIOD: 10
#CHECKPOINT_FILE_PATH: "./demo/Kinetics/SLOWFAST_8x8_R50.pkl"
CHECKPOINT_TYPE: caffe2
CHECKPOINT_PERIOD: 1
AUTO_RESUME: True
DATA:
NUM_FRAMES: 32
SAMPLING_RATE: 2
TRAIN_JITTER_SCALES: [256, 320]
TRAIN_CROP_SIZE: 224
TEST_CROP_SIZE: 256
INPUT_CHANNEL_NUM: [3]
PATH_TO_DATA_DIR: "./slowfast/data/MyData"
PATH_LABEL_SEPARATOR: ","
SLOWFAST:
ALPHA: 4
BETA_INV: 8
FUSION_CONV_CHANNEL_RATIO: 2
FUSION_KERNEL_SZ: 7
RESNET:
ZERO_INIT_FINAL_BN: True
WIDTH_PER_GROUP: 64
NUM_GROUPS: 1
DEPTH: 50
TRANS_FUNC: bottleneck_transform
STRIDE_1X1: False
NUM_BLOCK_TEMP_KERNEL: [[3, 3], [4, 4], [6, 6], [3, 3]]
SPATIAL_STRIDES: [[1, 1], [2, 2], [2, 2], [2, 2]]
SPATIAL_DILATIONS: [[1, 1], [1, 1], [1, 1], [1, 1]]
NONLOCAL:
LOCATION: [[[], []], [[], []], [[], []], [[], []]]
GROUP: [[1, 1], [1, 1], [1, 1], [1, 1]]
INSTANTIATION: dot_product
BN:
USE_PRECISE_STATS: True
NUM_BATCHES_PRECISE: 200
SOLVER:
BASE_LR: 0.0125
LR_POLICY: cosine
MAX_EPOCH: 10
MOMENTUM: 0.9
WEIGHT_DECAY: 1e-4
WARMUP_EPOCHS: 34.0
WARMUP_START_LR: 0.01
OPTIMIZING_METHOD: sgd
MODEL:
NUM_CLASSES: 1
ARCH: slowfast
MODEL_NAME: SlowFast
LOSS_FUNC: cross_entropy
DROPOUT_RATE: 0.5
TEST:
ENABLE: True
DATASET: mydata
BATCH_SIZE: 2
DATA_LOADER:
NUM_WORKERS: 8
PIN_MEMORY: True
NUM_GPUS: 1
NUM_SHARDS: 1
RNG_SEED: 0
OUTPUT_DIR: .
```

- Is there any resource available that explains the configuration variables in more detail? The current documentation does not seem to cover everything.
- How can I adjust my configuration or pre-processing to handle different video sizes, and resolve the "Input pathway dimensions are not consistent" error?
- With each video being a clip of 150 frames, is there a specific setting or adjustment I need to consider in the configuration?

Any help or advice would be greatly appreciated.