changes

Makefile

@@ -0,0 +1,27 @@
+install:
+	pip install --upgrade pip &&\
+		pip install -r requirements.txt
+
+test:
+	python -m pytest -vvv --cov=hello --cov=greeting \
+		--cov=smath --cov=web tests
+	python -m pytest --nbval notebook.ipynb	#tests our jupyter notebook
+	#python -m pytest -v tests/test_web.py #if you just want to test web
+
+debug:
+	python -m pytest -vv --pdb	#Debugger is invoked
+
+one-test:
+	python -m pytest -vv tests/test_greeting.py::test_my_name4
+
+debugthree:
+	#not working the way I expect
+	python -m pytest -vv --pdb --maxfail=4  # drop to PDB for first three failures
+
+format:
+	black *.py
+
+lint:
+	pylint --disable=R,C *.py
+
+all: install lint test format

app.py

@@ -0,0 +1,69 @@
+import torch 
+import re 
+import gradio as gr
+from PIL import Image
+
+from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel 
+import os
+import tensorflow as tf
+os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'
+
+device='cpu'
+
+model_id = "nttdataspain/vit-gpt2-stablediffusion2-lora"
+model = VisionEncoderDecoderModel.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+feature_extractor = ViTFeatureExtractor.from_pretrained(model_id)
+
+# Predict function
+def predict(image):
+    img = image.convert('RGB')
+    model.eval()
+    pixel_values = feature_extractor(images=[img], return_tensors="pt").pixel_values
+    with torch.no_grad():
+        output_ids = model.generate(pixel_values, max_length=16, num_beams=4, return_dict_in_generate=True).sequences
+
+    preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
+    preds = [pred.strip() for pred in preds]
+    return preds[0]
+
+input = gr.inputs.Image(label="Upload any Image", type = 'pil', optional=True)
+output = gr.outputs.Textbox(type="text",label="Captions")
+examples_folder = os.path.join(os.path.dirname(__file__), "examples")
+examples = [os.path.join(examples_folder, file) for file in os.listdir(examples_folder)]
+
+with gr.Blocks() as demo:
+    
+    gr.HTML(
+        """
+        <div style="text-align: center; max-width: 1200px; margin: 20px auto;">
+        <h2 style="font-weight: 900; font-size: 3rem; margin: 0rem">
+             Image to Text
+        </h2>
+        <br>   
+        </div>
+        """)
+    
+    with gr.Row():
+            with gr.Column(scale=1):
+                # img = gr.inputs.Image(label="Upload any Image", type = 'pil', optional=True)
+                img = gr.Image(label="Upload any Image", type = 'pil', optional=True)
+
+                # img = gr.inputs.Image(type="pil", label="Upload any Image", optional=True)
+
+                button = gr.Button(value="Convert")
+            with gr.Column(scale=1):
+                # out = gr.outputs.Textbox(type="text",label="Captions")
+                out = gr.Label(type="text", label="Captions")
+
+                
+    button.click(predict, inputs=[img], outputs=[out])
+ 
+    gr.Examples(
+        examples=examples,
+        inputs=img,
+        outputs=out,
+        fn=predict,
+        cache_examples=True,
+    )
+demo.launch(debug=True)

gradio_cached_examples/10/Captions/tmp176yaohx.json

@@ -0,0 +1 @@
+{"label": "a bird perched on top of a tree branch"}

gradio_cached_examples/10/Captions/tmp4yvgqp24.json

@@ -0,0 +1 @@
+{"label": "a bird perched on top of a tree branch"}

gradio_cached_examples/10/Captions/tmppnxqb0mg.json

@@ -0,0 +1 @@
+{"label": "a bird perched on top of a tree branch"}

gradio_cached_examples/10/log.csv

@@ -0,0 +1,4 @@
+Captions,flag,username,timestamp
+/workspaces/HF_imageText/gradio_cached_examples/10/Captions/tmp176yaohx.json,,,2023-10-15 14:03:32.176788
+/workspaces/HF_imageText/gradio_cached_examples/10/Captions/tmppnxqb0mg.json,,,2023-10-15 14:03:36.837638
+/workspaces/HF_imageText/gradio_cached_examples/10/Captions/tmp4yvgqp24.json,,,2023-10-15 14:03:41.421588

requirements.txt

@@ -0,0 +1,7 @@
+gradio
+streamlit
+transformers
+pillow
+requests
+torch
+tensorflow