test the api

api_test.py

@@ -0,0 +1,82 @@
+from gradio_client import Client
+import time
+import numpy as np
+
+import torch
+
+from api_helper import preprocess_image, encode_numpy_array
+clip_image_size = 224
+
+client = Client("http://127.0.0.1:7860/")
+
+print("do we have cuda", torch.cuda.is_available())
+
+def test_text():
+    result = client.predict(
+                    "Howdy!",	# str representing string value in 'Input' Textbox component
+                    api_name="/text_to_embeddings"
+    )
+    return(result)
+
+def test_image():
+    result = client.predict(
+				"https://raw.githubusercontent.com/gradio-app/gradio/main/test/test_files/bus.png",	# str representing filepath or URL to image in 'Image Prompt' Image component
+				api_name="/image_to_embeddings"
+    )
+    return(result)
+
+def test_image_as_payload(payload):
+    result = client.predict(
+                payload,	# image as string payload
+                api_name="/image_as_payload_to_embeddings"
+    )
+    return(result)
+
+# performance test for text
+start = time.time()
+for i in range(100):
+    test_text()
+end = time.time()
+# print average time in seconds and in milliseconds and number of predictions per second
+print("Average time for text: ", (end - start) / 100, "s")
+print("Average time for text: ", (end - start) * 10, "ms")
+print("Number of predictions per second for text: ", 1 / ((end - start) / 100))
+
+# performance test for image
+start = time.time()
+for i in range(100):
+    test_image()
+end = time.time()
+# print average time in seconds and in milliseconds
+print("Average time for image: ", (end - start) / 100, "s")
+print("Average time for image: ", (end - start) * 10, "ms")
+print("Number of predictions per second for image: ", 1 / ((end - start) / 100))
+
+
+
+test_image_url = "https://raw.githubusercontent.com/gradio-app/gradio/main/test/test_files/bus.png"
+# download image from url
+import requests
+from PIL import Image
+from io import BytesIO
+response = requests.get(test_image_url)
+input_image = Image.open(BytesIO(response.content))
+input_image = input_image.convert('RGB')
+# convert image to numpy array
+input_image = np.array(input_image)
+
+
+if input_image.shape[0] > clip_image_size or input_image.shape[1] > clip_image_size:
+    input_image = preprocess_image(input_image, clip_image_size)
+payload = encode_numpy_array(input_image)
+
+# performance test for image as payload
+start = time.time()
+for i in range(100):
+    test_image_as_payload(payload)
+end = time.time()
+# print average time in seconds and in milliseconds
+print("Average time for image as payload: ", (end - start) / 100, "s")
+print("Average time for image as payload: ", (end - start) * 10, "ms")
+print("Number of predictions per second for image as payload: ", 1 / ((end - start) / 100))
+