init: proyect

app.py

@@ -0,0 +1,34 @@
+from PIL import Image
+import gradio as gr
+import requests
+from transformers import CLIPProcessor, CLIPModel
+
+model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+processor = CLIPProcessor.from_pretrained("tokenizer")
+
+def generate_answer(image):
+
+    clas = ['high_natural_light','neutral_natural_light','No_Light', 'artificial_lights','others']
+    classes = ['A picture of a living room filled with abundant natural light with a lot windows, without objects that prevent the light from passing through regardless of whether it is night','A picture of a living room with neutral natural light with few windows, without objects that prevent the light from passing through regardless of whether it is night','Nolights','A picture of a living room with Artificial lights like lamps or headlamps',"Objects or things that are not a room"]
+    inputs = processor(text=classes, images=image, return_tensors="pt", padding=True)
+    outputs = model(**inputs)
+    logits_per_image = outputs.logits_per_image
+    probs = logits_per_image.softmax(dim=1)
+
+    probabilities_list = probs.squeeze().tolist()
+
+    result_dict = {class_name: probability for class_name, probability in zip(clas, probabilities_list)}
+    
+    return result_dict
+
+image_input = gr.Image(type="pil", label="Upload Image")
+
+iface = gr.Interface(
+    fn=generate_answer, 
+    inputs=[image_input], 
+    outputs="text",
+    title="Room Lightning Score",
+    description="Enter text and upload an image"
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,2 @@
+transformers==4.37.2
+accelerate

tokenizer/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": "<|endoftext|>", "add_prefix_space": false, "errors": "replace", "do_lower_case": true, "name_or_path": "./clip_ViT_B_32/", "model_max_length": 77}