HenriquesLab / ZeroCostDL4Mic

ZeroCostDL4Mic: A Google Colab based no-cost toolbox to explore Deep-Learning in Microscopy
MIT License
565 stars 129 forks source link

Cellpose - two models not found #321

Open Marien-kaefer opened 4 months ago

Marien-kaefer commented 4 months ago

Hi there,

I am trying to use pre-trained Cellpose for the segmentation of bacteria in transmitted light images in the Cellpose 2D colab notebook. All is well until using the models in step 6.

Selecting the model "Cytoplasm2_Omnipose", I get the following error message: `WARNING:cellpose.models:model_type does not exist, using default model

HTTPError Traceback (most recent call last) in <cell line: 82>() 82 if model_choice == "Cytoplasm2_Omnipose": 83 channels=[segment_channel,nuclear_channel] ---> 84 model = models.Cellpose(gpu=True, model_type="cyto2_omni") 85 print("Cytoplasm2_Omnipose model enabled") 86

9 frames /usr/lib/python3.10/urllib/request.py in http_error_default(self, req, fp, code, msg, hdrs) 641 class HTTPDefaultErrorHandler(BaseHandler): 642 def http_error_default(self, req, fp, code, msg, hdrs): --> 643 raise HTTPError(req.full_url, code, msg, hdrs, fp) 644 645 class HTTPRedirectHandler(BaseHandler):

HTTPError: HTTP Error 500: INTERNAL SERVER ERROR`

Selecting the model "Bacteria_Omnipose", I get the following error message:

`WARNING:cellpose.models:model_type does not exist, using default model

HTTPError Traceback (most recent call last) in <cell line: 97>() 97 if model_choice == "Bacteria_Omnipose": 98 channels=[segment_channel,nuclear_channel] ---> 99 model = models.Cellpose(gpu=True, model_type="bact_omni") 100 Object_diameter = 0 101 print("Bacteria_omnipose model enabled")

9 frames /usr/lib/python3.10/urllib/request.py in http_error_default(self, req, fp, code, msg, hdrs) 641 class HTTPDefaultErrorHandler(BaseHandler): 642 def http_error_default(self, req, fp, code, msg, hdrs): --> 643 raise HTTPError(req.full_url, code, msg, hdrs, fp) 644 645 class HTTPRedirectHandler(BaseHandler):

HTTPError: HTTP Error 500: INTERNAL SERVER ERROR`

Other models, e.g. Nuclei or Cytoplasm2 are fine and generate segmentations. The images are single focal plane grey scale, single channel tif images.

Any help would be much appreciated. Thanks!

Marie