Reporting an Issue with Google Colab Demo

[AmirMohamadBabaee]

When trying to use the Google Colab demo to infer custom images, I encountered the following error:

# Inference the uploaded images
#@markdown `DDPM_STEPS`: Number of DDPM steps for sampling<br>
DDPM_STEPS = 200 #@param {type:"slider", min:10, max:1000, step:10}
#@markdown `FIDELITY_WEIGHT`: Balance the quality (lower number) and fidelity (higher number)<br>
FIDELITY_WEIGHT = 0.97 #@param {type:"slider", min:0, max:1, step:0.01}
#@markdown `UPSCALE`: The upscale for super-resolution, 4x SR by default<br>
UPSCALE = 4.0 #@param {type:"slider", min:1.0, max:16.0, step:0.5}
#@markdown `SEED`: The random seed for sampling<br>
SEED = 42 #@param {type:"slider", min:0, max:10000, step:1}
#@markdown `TILE_OVERLAP`: The overlap between tiles, betwwen 0 to 64<br>
TILE_OVERLAP = 32 #@param {type:"slider", min:0, max:60, step:2}
#@markdown `VQGANTILE_SIZE`: The size for VQGAN tile operation in pixel, min 512.<br>
VQGANTILE_SIZE = 1280 #@param {type:"slider", min:512, max:2000, step:2}
#@markdown `Aggregation_Sampling`: Use Aggregation Sampling if the expected resolution is not 512x512<br>
Aggregation_Sampling = False #@param {type:"boolean"}
#@markdown `Enable_Tile`: Enable tile to handle large resolution beyond 1024x1024<br>
Enable_Tile = False #@param {type:"boolean"}

VQGANTILE_STRIDE = int(VQGANTILE_SIZE * 0.9)
if Enable_Tile:
  !python scripts/sr_val_ddpm_text_T_vqganfin_oldcanvas_tile.py --config configs/stableSRNew/v2-finetune_text_T_512.yaml --ckpt './stablesr_000117.ckpt' --vqgan_ckpt './vqgan_cfw_00011.ckpt' --init-img 'inputs/user_upload' --outdir 'outputs/user_upload' --ddpm_steps {DDPM_STEPS} --dec_w {FIDELITY_WEIGHT} --upscale {UPSCALE} --tile_overlap {TILE_OVERLAP} --seed {SEED} --vqgantile_stride {VQGANTILE_STRIDE} --vqgantile_size {VQGANTILE_SIZE} --colorfix_type 'adain'
elif Aggregation_Sampling:
  !python scripts/sr_val_ddpm_text_T_vqganfin_oldcanvas.py --config configs/stableSRNew/v2-finetune_text_T_512.yaml --ckpt './stablesr_000117.ckpt' --vqgan_ckpt './vqgan_cfw_00011.ckpt' --init-img 'inputs/user_upload' --outdir 'outputs/user_upload' --ddpm_steps {DDPM_STEPS} --dec_w {FIDELITY_WEIGHT} --upscale {UPSCALE} --tile_overlap {TILE_OVERLAP} --seed {SEED} --colorfix_type 'adain'
else:
  !python scripts/sr_val_ddpm_text_T_vqganfin_old.py --config configs/stableSRNew/v2-finetune_text_T_512.yaml --ckpt './stablesr_000117.ckpt' --vqgan_ckpt './vqgan_cfw_00011.ckpt' --init-img 'inputs/user_upload' --outdir 'outputs/user_upload' --ddpm_steps {DDPM_STEPS} --dec_w {FIDELITY_WEIGHT} --seed {SEED} --colorfix_type 'adain'

Traceback (most recent call last):
  File "/content/StableSR/scripts/sr_val_ddpm_text_T_vqganfin_old.py", line 7, in <module>
    import torchvision
  File "/usr/local/lib/python3.10/site-packages/torchvision/__init__.py", line 6, in <module>
    from torchvision import _meta_registrations, datasets, io, models, ops, transforms, utils
  File "/usr/local/lib/python3.10/site-packages/torchvision/_meta_registrations.py", line 164, in <module>
    def meta_nms(dets, scores, iou_threshold):
  File "/usr/local/lib/python3.10/site-packages/torch/library.py", line 440, in inner
    handle = entry.abstract_impl.register(func_to_register, source)
  File "/usr/local/lib/python3.10/site-packages/torch/_library/abstract_impl.py", line 30, in register
    if torch._C._dispatch_has_kernel_for_dispatch_key(self.qualname, "Meta"):
RuntimeError: operator torchvision::nms does not exist

Any help in resolving this issue would be greatly appreciated.

[IceClear]

I guess the version of the torchvision is not correct?