Working on understanding and getting something to work

understand.py

@@ -6,7 +6,8 @@ import numpy as np
 from PIL import Image
 
 from transformers import DetrFeatureExtractor, DetrForSegmentation, MaskFormerImageProcessor, MaskFormerForInstanceSegmentation
-from transformers.models.detr.feature_extraction_detr import rgb_to_id
+# from transformers.models.detr.feature_extraction_detr import rgb_to_id
+from transformers.image_transforms import rgb_to_id
 
 TEST_IMAGE = Image.open(r"images/Test_Street_VisDrone.JPG")
 MODEL_NAME_DETR = "facebook/detr-resnet-50-panoptic"
@@ -21,15 +22,50 @@ model_name = MODEL_NAME_MASKFORMER
 
 # Starting with MaskFormer
 
-processor = MaskFormerImageProcessor.from_pretrained(model_name)
-model = MaskFormerForInstanceSegmentation.from_pretrained(model_name)
+processor = MaskFormerImageProcessor.from_pretrained(model_name) # <class 'transformers.models.maskformer.image_processing_maskformer.MaskFormerImageProcessor'>
+# DIR() --> ['__call__', '__class__', '__delattr__', '__dict__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__gt__', '__hash__', '__init__', 
+#           '__init_subclass__', '__le__', '__lt__', '__module__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__sizeof__', '__str__', '__subclasshook__', 
+#           '__weakref__', '_auto_class', '_create_repo', '_get_files_timestamps', '_max_size', '_pad_image', '_preprocess', '_preprocess_image', '_preprocess_mask', '_processor_class', 
+#           '_set_processor_class', '_upload_modified_files', 'center_crop', 'convert_segmentation_map_to_binary_masks', 'do_normalize', 'do_reduce_labels', 'do_rescale', 'do_resize', 
+#           'encode_inputs', 'fetch_images', 'from_dict', 'from_json_file', 'from_pretrained', 'get_image_processor_dict', 'ignore_index', 'image_mean', 'image_std', 'model_input_names', 
+#           'normalize', 'pad', 'post_process_instance_segmentation', 'post_process_panoptic_segmentation', 'post_process_segmentation', 'post_process_semantic_segmentation', 'preprocess', 
+#           'push_to_hub', 'register_for_auto_class', 'resample', 'rescale', 'rescale_factor', 'resize', 'save_pretrained', 'size', 'size_divisor', 'to_dict', 'to_json_file', 'to_json_string']
 
+model = MaskFormerForInstanceSegmentation.from_pretrained(model_name) # <class 'transformers.models.maskformer.modeling_maskformer.MaskFormerForInstanceSegmentation'>
+# DIR for model was too big
 model.to(DEVICE)
 
 # img = np.array(TEST_IMAGE)
 
-inputs = processor(images=image, return_tensors="pt")
+inputs = processor(images=image, return_tensors="pt") # <class 'transformers.image_processing_utils.BatchFeature'>
+# DIR() --> ['_MutableMapping__marker', '__abstractmethods__', '__class__', '__contains__', '__copy__', '__delattr__', '__delitem__', '__dict__', '__dir__', '__doc__', '__eq__', '__format__', 
+#           '__ge__', '__getattr__', '__getattribute__', '__getitem__', '__getstate__', '__gt__', '__hash__', '__init__', '__init_subclass__', '__iter__', '__le__', '__len__', '__lt__', 
+#           '__module__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__reversed__', '__setattr__', '__setitem__', '__setstate__', '__sizeof__', '__slots__', '__str__', 
+#           '__subclasshook__', '__weakref__', '_abc_impl', '_get_is_as_tensor_fns', 'clear', 'convert_to_tensors', 'copy', 'data', 'fromkeys', 'get', 'items', 'keys', 'pop', 'popitem', 
+#           'setdefault', 'to', 'update', 'values']
 inputs.to(DEVICE)
 
 
-outputs = model(**inputs)
+outputs = model(**inputs) # <class 'transformers.models.maskformer.modeling_maskformer.MaskFormerForInstanceSegmentationOutput'>
+# Each element of this class is a <class 'torch.Tensor'>
+# DIR() --> ['__annotations__', '__class__', '__contains__', '__dataclass_fields__', '__dataclass_params__', '__delattr__', '__delitem__', '__dict__', '__dir__', 
+#           '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__getitem__', '__gt__', '__hash__', '__init__', '__init_subclass__', '__iter__', 
+#           '__le__', '__len__', '__lt__', '__module__', '__ne__', '__new__', '__post_init__', '__reduce__', '__reduce_ex__', '__repr__', '__reversed__', '__setattr__', 
+#           '__setitem__', '__sizeof__', '__str__', '__subclasshook__', 'attentions', 'auxiliary_logits', 'class_queries_logits', 'clear', 'copy', 'encoder_hidden_states', 
+#           'encoder_last_hidden_state', 'fromkeys', 'get', 'hidden_states', 'items', 'keys', 'loss', 'masks_queries_logits', 'move_to_end', 'pixel_decoder_hidden_states', 
+#           'pixel_decoder_last_hidden_state', 'pop', 'popitem', 'setdefault', 'to_tuple', 'transformer_decoder_hidden_states', 'transformer_decoder_last_hidden_state', 
+#           'update', 'values']
+
+results = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
+# <class 'dict'>
+# Example of 
+
+
+# From Tutorial (Box 79)
+# def get_mask(segment_idx):
+#     segment = results['segments_info'][segment_idx]
+#     print("Visualizing mask for:", id2label[segment['label_id']])
+#     mask = (predicted_panoptic_seg == segment['id'])
+#     visual_mask = (mask * 255).astype(np.uint8)
+#     return Image.fromarray(visual_mask)
+